Token | heads |
Token ID | 6665 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Promotion | +2.081 |
tolerance | +1.955 |
Chair | +1.955 |
Sao | +1.934 |
TABLE | +1.904 |
Neg logit contributions | |
enhagen | -2.942 |
ighthouse | -2.588 |
�� | -2.507 |
inately | -2.493 |
ighth | -2.472 |
Token | Jason |
Token ID | 8982 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
enhagen | +1.731 |
ighthouse | +1.542 |
�� | +1.468 |
ighth | +1.462 |
inately | +1.449 |
Neg logit contributions | |
Promotion | -1.324 |
tolerance | -1.264 |
TABLE | -1.226 |
Sao | -1.225 |
_______ | -1.225 |
Token | West |
Token ID | 2688 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Promotion | +0.115 |
tolerance | +0.110 |
Mania | +0.107 |
TABLE | +0.107 |
Sao | +0.105 |
Neg logit contributions | |
enhagen | -0.142 |
ighthouse | -0.128 |
ighth | -0.121 |
inately | -0.119 |
�� | -0.118 |
Token | and |
Token ID | 290 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Promotion | +0.529 |
tolerance | +0.503 |
Sao | +0.496 |
Chair | +0.493 |
TABLE | +0.493 |
Neg logit contributions | |
enhagen | -0.673 |
ighthouse | -0.589 |
ighth | -0.565 |
�� | -0.564 |
inately | -0.562 |
Token | Vince |
Token ID | 22376 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
enhagen | +0.338 |
ighthouse | +0.299 |
�� | +0.286 |
ighth | +0.286 |
inately | +0.285 |
Neg logit contributions | |
Promotion | -0.256 |
tolerance | -0.243 |
TABLE | -0.238 |
Sao | -0.237 |
Mania | -0.237 |
Token | Zam |
Token ID | 38343 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
Promotion | +1.362 |
Chair | +1.204 |
tolerance | +1.203 |
Sao | +1.176 |
TABLE | +1.132 |
Neg logit contributions | |
enhagen | -5.303 |
ighthouse | -4.842 |
�� | -4.754 |
inately | -4.708 |
ighth | -4.708 |
Token | pe |
Token ID | 431 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Promotion | +5.095 |
Chair | +4.809 |
tolerance | +4.801 |
Mania | +4.717 |
Oaks | +4.655 |
Neg logit contributions | |
enhagen | -8.061 |
�� | -7.099 |
ighthouse | -7.043 |
inately | -6.918 |
ighth | -6.851 |
Token | lla |
Token ID | 8466 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Promotion | +1.003 |
tolerance | +0.902 |
Chair | +0.893 |
Sao | +0.888 |
TABLE | +0.864 |
Neg logit contributions | |
enhagen | -2.942 |
ighthouse | -2.669 |
�� | -2.602 |
inately | -2.589 |
ighth | -2.583 |
Token | , |
Token ID | 11 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
Promotion | +1.676 |
tolerance | +1.579 |
Chair | +1.567 |
Sao | +1.563 |
TABLE | +1.541 |
Neg logit contributions | |
enhagen | -2.333 |
ighthouse | -2.052 |
�� | -2.003 |
inately | -1.986 |
ighth | -1.971 |
Token | outlines |
Token ID | 27430 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Promotion | +0.501 |
tolerance | +0.474 |
Chair | +0.467 |
Sao | +0.467 |
Mania | +0.463 |
Neg logit contributions | |
enhagen | -0.634 |
ighthouse | -0.557 |
�� | -0.535 |
inately | -0.533 |
ighth | -0.533 |
Token | the |
Token ID | 262 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
Promotion | +0.456 |
tolerance | +0.431 |
Chair | +0.427 |
Sao | +0.427 |
TABLE | +0.423 |
Neg logit contributions | |
enhagen | -0.584 |
ighthouse | -0.514 |
�� | -0.493 |
ighth | -0.491 |
inately | -0.490 |
Token | B |
Token ID | 33 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
Promotion | +1.245 |
tolerance | +1.178 |
Chair | +1.167 |
Sao | +1.166 |
Mania | +1.153 |
Neg logit contributions | |
enhagen | -1.517 |
ighthouse | -1.326 |
�� | -1.281 |
inately | -1.270 |
ighth | -1.265 |
Token | res |
Token ID | 411 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Promotion | +0.021 |
tolerance | +0.020 |
Sao | +0.020 |
Chair | +0.020 |
TABLE | +0.020 |
Neg logit contributions | |
enhagen | -0.025 |
ighthouse | -0.022 |
�� | -0.021 |
ighth | -0.021 |
inately | -0.021 |
Token | lin |
Token ID | 2815 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
enhagen | +1.577 |
ighthouse | +1.358 |
ighth | +1.295 |
inately | +1.290 |
�� | +1.250 |
Neg logit contributions | |
Promotion | -1.646 |
tolerance | -1.591 |
Sao | -1.552 |
Chair | -1.543 |
TABLE | -1.538 |
Token | 63 |
Token ID | 8093 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
enhagen | +4.228 |
ighthouse | +3.759 |
ighth | +3.689 |
inately | +3.644 |
�� | +3.553 |
Neg logit contributions | |
Promotion | -2.307 |
tolerance | -2.220 |
Mania | -2.105 |
TABLE | -2.099 |
Chair | -2.088 |
Token | ), |
Token ID | 828 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Promotion | +0.453 |
tolerance | +0.428 |
Sao | +0.423 |
Chair | +0.422 |
TABLE | +0.418 |
Neg logit contributions | |
enhagen | -0.602 |
ighthouse | -0.530 |
�� | -0.511 |
ighth | -0.509 |
inately | -0.509 |
Token | Dug |
Token ID | 27436 |
Feature activation | +9.24e+00 |
Pos logit contributions | |
Promotion | +0.241 |
tolerance | +0.229 |
Chair | +0.225 |
Sao | +0.224 |
TABLE | +0.223 |
Neg logit contributions | |
enhagen | -0.307 |
ighthouse | -0.270 |
�� | -0.260 |
ighth | -0.258 |
inately | -0.258 |
Token | gan |
Token ID | 1030 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Promotion | +5.355 |
Sao | +5.186 |
Chair | +5.156 |
** | +5.041 |
tolerance | +5.032 |
Neg logit contributions | |
enhagen | -7.220 |
�� | -6.468 |
ighthouse | -6.288 |
inately | -6.136 |
ighth | -6.032 |
Token | ( |
Token ID | 357 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Promotion | +1.421 |
tolerance | +1.337 |
Sao | +1.333 |
Chair | +1.331 |
TABLE | +1.311 |
Neg logit contributions | |
enhagen | -2.029 |
ighthouse | -1.796 |
�� | -1.740 |
inately | -1.718 |
ighth | -1.705 |
Token | D |
Token ID | 35 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Promotion | +1.434 |
tolerance | +1.356 |
Chair | +1.344 |
Sao | +1.342 |
Mania | +1.331 |
Neg logit contributions | |
enhagen | -1.753 |
ighthouse | -1.531 |
�� | -1.481 |
inately | -1.467 |
ighth | -1.460 |
Token | olan |
Token ID | 16617 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
enhagen | +0.103 |
ighthouse | +0.091 |
ighth | +0.087 |
�� | +0.087 |
inately | +0.087 |
Neg logit contributions | |
Promotion | -0.082 |
tolerance | -0.078 |
Sao | -0.077 |
Chair | -0.077 |
TABLE | -0.077 |
Token | 41 |
Token ID | 6073 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Promotion | +0.233 |
tolerance | +0.218 |
Chair | +0.213 |
Sao | +0.212 |
TABLE | +0.210 |
Neg logit contributions | |
enhagen | -0.466 |
ighthouse | -0.418 |
ighth | -0.404 |
�� | -0.404 |
inately | -0.403 |
Token | Moore |
Token ID | 8877 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
Promotion | +0.523 |
tolerance | +0.494 |
Sao | +0.490 |
Chair | +0.488 |
Mania | +0.486 |
Neg logit contributions | |
enhagen | -0.647 |
ighthouse | -0.566 |
ighth | -0.545 |
inately | -0.541 |
�� | -0.541 |
Token | j |
Token ID | 474 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
enhagen | +2.862 |
ighthouse | +2.480 |
ighth | +2.423 |
inately | +2.381 |
�� | +2.333 |
Neg logit contributions | |
Promotion | -2.149 |
Sao | -1.994 |
tolerance | -1.984 |
Chair | -1.967 |
Mania | -1.960 |
Token | ogged |
Token ID | 42545 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
enhagen | +0.364 |
ighthouse | +0.289 |
ighth | +0.272 |
inately | +0.267 |
�� | +0.243 |
Neg logit contributions | |
Promotion | -0.781 |
tolerance | -0.759 |
Sao | -0.750 |
Chair | -0.750 |
TABLE | -0.746 |
Token | into |
Token ID | 656 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
Promotion | +0.041 |
tolerance | +0.038 |
Sao | +0.038 |
Chair | +0.038 |
TABLE | +0.038 |
Neg logit contributions | |
enhagen | -0.051 |
ighthouse | -0.045 |
inately | -0.043 |
ighth | -0.043 |
�� | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Promotion | +1.579 |
tolerance | +1.493 |
Chair | +1.475 |
Sao | +1.474 |
TABLE | +1.458 |
Neg logit contributions | |
enhagen | -2.035 |
ighthouse | -1.789 |
�� | -1.727 |
inately | -1.713 |
ighth | -1.710 |
Token | dug |
Token ID | 18735 |
Feature activation | +8.13e+00 |
Pos logit contributions | |
Promotion | +0.760 |
tolerance | +0.719 |
Sao | +0.715 |
Chair | +0.710 |
Mania | +0.709 |
Neg logit contributions | |
enhagen | -1.051 |
ighthouse | -0.923 |
ighth | -0.890 |
�� | -0.890 |
inately | -0.885 |
Token | out |
Token ID | 448 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Promotion | +5.331 |
tolerance | +5.192 |
Chair | +5.160 |
Mania | +5.074 |
_______ | +5.063 |
Neg logit contributions | |
enhagen | -5.921 |
�� | -5.266 |
ighthouse | -5.062 |
inately | -4.935 |
achus | -4.880 |
Token | , |
Token ID | 11 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
Promotion | +1.715 |
tolerance | +1.627 |
Chair | +1.609 |
Sao | +1.599 |
TABLE | +1.584 |
Neg logit contributions | |
enhagen | -2.283 |
ighthouse | -2.017 |
�� | -1.973 |
ighth | -1.925 |
inately | -1.922 |
Token | then |
Token ID | 788 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Promotion | +0.528 |
tolerance | +0.497 |
Chair | +0.492 |
Sao | +0.492 |
TABLE | +0.486 |
Neg logit contributions | |
enhagen | -0.692 |
ighthouse | -0.608 |
�� | -0.585 |
ighth | -0.583 |
inately | -0.583 |
Token | walked |
Token ID | 6807 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
Promotion | +0.092 |
tolerance | +0.087 |
Chair | +0.086 |
Sao | +0.086 |
TABLE | +0.085 |
Neg logit contributions | |
enhagen | -0.118 |
ighthouse | -0.104 |
ighth | -0.100 |
inately | -0.100 |
�� | -0.099 |
Token | into |
Token ID | 656 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Promotion | +0.048 |
tolerance | +0.045 |
Sao | +0.045 |
Chair | +0.045 |
Mania | +0.044 |
Neg logit contributions | |
enhagen | -0.060 |
ighthouse | -0.052 |
ighth | -0.050 |
inately | -0.050 |
�� | -0.050 |
Token | at |
Token ID | 379 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
enhagen | +0.732 |
ighthouse | +0.647 |
inately | +0.625 |
ighth | +0.617 |
�� | +0.614 |
Neg logit contributions | |
Promotion | -0.598 |
tolerance | -0.559 |
Mania | -0.556 |
Chair | -0.555 |
TABLE | -0.551 |
Token | stand |
Token ID | 1302 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Promotion | +0.281 |
tolerance | +0.265 |
Sao | +0.262 |
Chair | +0.262 |
Mania | +0.261 |
Neg logit contributions | |
enhagen | -0.342 |
ighthouse | -0.300 |
�� | -0.288 |
ighth | -0.288 |
inately | -0.286 |
Token | - |
Token ID | 12 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Promotion | +1.112 |
tolerance | +1.042 |
Chair | +1.028 |
Sao | +1.027 |
TABLE | +1.014 |
Neg logit contributions | |
enhagen | -1.876 |
ighthouse | -1.671 |
�� | -1.621 |
inately | -1.609 |
ighth | -1.606 |
Token | off |
Token ID | 2364 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
Promotion | +1.796 |
tolerance | +1.721 |
Chair | +1.707 |
Sao | +1.704 |
Mania | +1.691 |
Neg logit contributions | |
enhagen | -1.645 |
ighthouse | -1.403 |
�� | -1.358 |
inately | -1.331 |
ighth | -1.327 |
Token | and |
Token ID | 290 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Promotion | +3.599 |
tolerance | +3.494 |
Chair | +3.444 |
Sao | +3.393 |
TABLE | +3.375 |
Neg logit contributions | |
enhagen | -5.099 |
ighthouse | -4.481 |
�� | -4.372 |
inately | -4.270 |
ighth | -4.238 |
Token | scr |
Token ID | 6040 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
Promotion | +0.468 |
tolerance | +0.440 |
Sao | +0.435 |
Chair | +0.434 |
Mania | +0.433 |
Neg logit contributions | |
enhagen | -0.623 |
ighthouse | -0.551 |
ighth | -0.531 |
�� | -0.529 |
inately | -0.527 |
Token | um |
Token ID | 388 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Promotion | +4.240 |
Chair | +4.092 |
** | +3.970 |
tolerance | +3.969 |
Mania | +3.969 |
Neg logit contributions | |
enhagen | -6.959 |
�� | -6.160 |
ighthouse | -5.999 |
inately | -5.874 |
achus | -5.646 |
Token | - |
Token ID | 12 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Promotion | +2.798 |
tolerance | +2.637 |
Chair | +2.594 |
Sao | +2.583 |
Mania | +2.545 |
Neg logit contributions | |
enhagen | -4.818 |
ighthouse | -4.289 |
�� | -4.168 |
inately | -4.131 |
ighth | -4.100 |
Token | half |
Token ID | 13959 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
Promotion | +0.788 |
tolerance | +0.728 |
Sao | +0.724 |
Chair | +0.720 |
TABLE | +0.710 |
Neg logit contributions | |
enhagen | -1.526 |
ighthouse | -1.373 |
ighth | -1.326 |
inately | -1.325 |
�� | -1.322 |
Token | respectively |
Token ID | 8148 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Promotion | +2.110 |
tolerance | +2.004 |
Sao | +1.983 |
Chair | +1.981 |
TABLE | +1.952 |
Neg logit contributions | |
enhagen | -2.756 |
ighthouse | -2.413 |
�� | -2.336 |
inately | -2.311 |
ighth | -2.298 |
Token | . |
Token ID | 13 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Promotion | +0.320 |
tolerance | +0.304 |
Chair | +0.300 |
Sao | +0.299 |
Mania | +0.297 |
Neg logit contributions | |
enhagen | -0.352 |
ighthouse | -0.307 |
ighth | -0.293 |
�� | -0.293 |
inately | -0.293 |
Token | Vision |
Token ID | 19009 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Promotion | +1.591 |
tolerance | +1.502 |
Chair | +1.488 |
Sao | +1.483 |
TABLE | +1.463 |
Neg logit contributions | |
enhagen | -2.129 |
ighthouse | -1.875 |
�� | -1.814 |
inately | -1.798 |
ighth | -1.796 |
Token | Forum |
Token ID | 14867 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
enhagen | +0.357 |
ighthouse | +0.319 |
�� | +0.306 |
ighth | +0.305 |
inately | +0.305 |
Neg logit contributions | |
Promotion | -0.227 |
tolerance | -0.217 |
Sao | -0.211 |
Chair | -0.211 |
TABLE | -0.210 |
Token | even |
Token ID | 772 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
Promotion | +0.301 |
tolerance | +0.286 |
Sao | +0.281 |
Chair | +0.280 |
TABLE | +0.279 |
Neg logit contributions | |
enhagen | -0.398 |
ighthouse | -0.351 |
�� | -0.337 |
inately | -0.335 |
ighth | -0.335 |
Token | named |
Token ID | 3706 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
enhagen | +0.730 |
ighthouse | +0.636 |
inately | +0.613 |
ighth | +0.609 |
�� | +0.608 |
Neg logit contributions | |
Promotion | -0.550 |
tolerance | -0.517 |
Sao | -0.513 |
Mania | -0.512 |
Chair | -0.509 |
Token | Michelle |
Token ID | 16738 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Promotion | +0.427 |
tolerance | +0.404 |
Sao | +0.399 |
Chair | +0.398 |
Mania | +0.396 |
Neg logit contributions | |
enhagen | -0.538 |
ighthouse | -0.472 |
�� | -0.454 |
inately | -0.453 |
ighth | -0.451 |
Token | Dug |
Token ID | 27436 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
Promotion | +1.100 |
tolerance | +1.040 |
Sao | +1.026 |
Chair | +1.025 |
TABLE | +1.017 |
Neg logit contributions | |
enhagen | -1.462 |
ighthouse | -1.289 |
�� | -1.241 |
inately | -1.235 |
ighth | -1.232 |
Token | gar |
Token ID | 4563 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Promotion | +3.828 |
Chair | +3.649 |
Mania | +3.586 |
tolerance | +3.584 |
Sao | +3.520 |
Neg logit contributions | |
enhagen | -7.222 |
�� | -6.578 |
ighthouse | -6.522 |
inately | -6.278 |
ighth | -6.264 |
Token | � |
Token ID | 564 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Promotion | +1.818 |
tolerance | +1.717 |
Chair | +1.698 |
Sao | +1.695 |
TABLE | +1.672 |
Neg logit contributions | |
enhagen | -2.509 |
ighthouse | -2.213 |
�� | -2.143 |
inately | -2.121 |
ighth | -2.116 |
Token | � |
Token ID | 250 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
enhagen | +0.816 |
ighthouse | +0.681 |
�� | +0.647 |
inately | +0.639 |
ighth | +0.638 |
Neg logit contributions | |
Promotion | -1.161 |
tolerance | -1.114 |
Chair | -1.104 |
Sao | -1.104 |
TABLE | -1.095 |
Token | Mother |
Token ID | 31398 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
enhagen | +0.102 |
ighthouse | +0.090 |
ighth | +0.087 |
�� | +0.087 |
inately | +0.086 |
Neg logit contributions | |
Promotion | -0.071 |
tolerance | -0.067 |
Sao | -0.066 |
Chair | -0.065 |
TABLE | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Promotion | +1.968 |
tolerance | +1.860 |
Chair | +1.842 |
Sao | +1.839 |
TABLE | +1.820 |
Neg logit contributions | |
enhagen | -2.492 |
ighthouse | -2.188 |
�� | -2.114 |
inately | -2.093 |
ighth | -2.091 |
Token | D |
Token ID | 360 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
enhagen | +0.191 |
ighthouse | +0.169 |
�� | +0.162 |
inately | +0.162 |
ighth | +0.161 |
Neg logit contributions | |
Promotion | -0.131 |
tolerance | -0.125 |
Mania | -0.123 |
TABLE | -0.122 |
Chair | -0.122 |
Token | n |
Token ID | 77 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
enhagen | +0.236 |
ighthouse | +0.206 |
�� | +0.198 |
ighth | +0.196 |
inately | +0.196 |
Neg logit contributions | |
Promotion | -0.209 |
tolerance | -0.199 |
Sao | -0.197 |
Chair | -0.197 |
TABLE | -0.195 |
Token | ip |
Token ID | 541 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
Promotion | +0.168 |
tolerance | +0.158 |
Sao | +0.155 |
Chair | +0.154 |
TABLE | +0.154 |
Neg logit contributions | |
enhagen | -0.282 |
ighthouse | -0.256 |
ighth | -0.246 |
�� | -0.245 |
inately | -0.242 |
Token | rop |
Token ID | 1773 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Promotion | +2.328 |
tolerance | +2.204 |
Chair | +2.173 |
Sao | +2.170 |
TABLE | +2.159 |
Neg logit contributions | |
enhagen | -3.005 |
ighthouse | -2.645 |
�� | -2.545 |
inately | -2.533 |
ighth | -2.530 |
Token | et |
Token ID | 316 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
Promotion | +0.915 |
tolerance | +0.870 |
Sao | +0.854 |
Chair | +0.854 |
TABLE | +0.848 |
Neg logit contributions | |
enhagen | -1.214 |
ighthouse | -1.070 |
inately | -1.028 |
�� | -1.025 |
ighth | -1.020 |
Token | rov |
Token ID | 18657 |
Feature activation | +7.91e+00 |
Pos logit contributions | |
Promotion | +0.136 |
tolerance | +0.104 |
Chair | +0.100 |
Sao | +0.099 |
TABLE | +0.093 |
Neg logit contributions | |
enhagen | -1.163 |
ighthouse | -1.074 |
�� | -1.054 |
inately | -1.047 |
ighth | -1.045 |
Token | sk |
Token ID | 8135 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Promotion | +2.777 |
Chair | +2.428 |
Sao | +2.356 |
tolerance | +2.325 |
TABLE | +2.290 |
Neg logit contributions | |
enhagen | -8.639 |
�� | -7.746 |
ighthouse | -7.740 |
ighth | -7.536 |
inately | -7.493 |
Token | airport |
Token ID | 9003 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Promotion | +0.909 |
tolerance | +0.856 |
Chair | +0.847 |
Sao | +0.846 |
TABLE | +0.835 |
Neg logit contributions | |
enhagen | -1.270 |
ighthouse | -1.120 |
�� | -1.085 |
inately | -1.075 |
ighth | -1.073 |
Token | , |
Token ID | 11 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Promotion | +1.212 |
tolerance | +1.143 |
Sao | +1.129 |
Chair | +1.129 |
TABLE | +1.111 |
Neg logit contributions | |
enhagen | -1.625 |
ighthouse | -1.431 |
�� | -1.386 |
ighth | -1.372 |
inately | -1.370 |
Token | which |
Token ID | 543 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Promotion | +0.206 |
tolerance | +0.195 |
Mania | +0.192 |
Sao | +0.191 |
Chair | +0.191 |
Neg logit contributions | |
enhagen | -0.263 |
ighthouse | -0.232 |
�� | -0.222 |
ighth | -0.222 |
inately | -0.221 |
Token | is |
Token ID | 318 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Promotion | +0.487 |
tolerance | +0.461 |
Chair | +0.454 |
Sao | +0.453 |
TABLE | +0.449 |
Neg logit contributions | |
enhagen | -0.659 |
ighthouse | -0.581 |
�� | -0.560 |
inately | -0.557 |
ighth | -0.555 |
Token | year |
Token ID | 614 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
Promotion | +0.621 |
tolerance | +0.585 |
Sao | +0.577 |
Chair | +0.577 |
TABLE | +0.570 |
Neg logit contributions | |
enhagen | -0.948 |
ighthouse | -0.841 |
�� | -0.814 |
inately | -0.808 |
ighth | -0.807 |
Token | 's |
Token ID | 338 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
enhagen | +0.585 |
ighthouse | +0.517 |
�� | +0.494 |
inately | +0.492 |
ighth | +0.492 |
Neg logit contributions | |
Promotion | -0.427 |
tolerance | -0.402 |
Sao | -0.397 |
Chair | -0.396 |
TABLE | -0.394 |
Token | election |
Token ID | 3071 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Promotion | +0.513 |
tolerance | +0.482 |
Chair | +0.475 |
Sao | +0.475 |
TABLE | +0.469 |
Neg logit contributions | |
enhagen | -0.823 |
ighthouse | -0.732 |
�� | -0.709 |
inately | -0.704 |
ighth | -0.703 |
Token | . |
Token ID | 13 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
Promotion | +0.322 |
tolerance | +0.306 |
Chair | +0.302 |
Sao | +0.302 |
TABLE | +0.299 |
Neg logit contributions | |
enhagen | -0.383 |
ighthouse | -0.335 |
�� | -0.323 |
inately | -0.320 |
ighth | -0.320 |
Token | Ronnie |
Token ID | 40892 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
enhagen | +0.617 |
ighthouse | +0.546 |
ighth | +0.522 |
�� | +0.520 |
inately | +0.518 |
Neg logit contributions | |
Promotion | -0.459 |
tolerance | -0.443 |
Sao | -0.433 |
Mania | -0.431 |
Chair | -0.428 |
Token | Dug |
Token ID | 27436 |
Feature activation | +7.57e+00 |
Pos logit contributions | |
Promotion | +0.678 |
tolerance | +0.642 |
Chair | +0.632 |
Sao | +0.631 |
TABLE | +0.626 |
Neg logit contributions | |
enhagen | -0.873 |
ighthouse | -0.767 |
�� | -0.738 |
ighth | -0.733 |
inately | -0.733 |
Token | ger |
Token ID | 1362 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Promotion | +4.449 |
Chair | +4.306 |
tolerance | +4.196 |
Mania | +4.186 |
Sao | +4.184 |
Neg logit contributions | |
enhagen | -5.914 |
�� | -5.357 |
ighthouse | -5.256 |
inately | -5.108 |
ighth | -5.020 |
Token | wrote |
Token ID | 2630 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
enhagen | +0.582 |
ighthouse | +0.509 |
�� | +0.486 |
ighth | +0.485 |
inately | +0.484 |
Neg logit contributions | |
Promotion | -0.430 |
tolerance | -0.411 |
Sao | -0.403 |
Mania | -0.399 |
TABLE | -0.396 |
Token | the |
Token ID | 262 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
Promotion | +0.459 |
tolerance | +0.432 |
Sao | +0.427 |
Chair | +0.424 |
Mania | +0.422 |
Neg logit contributions | |
enhagen | -0.689 |
ighthouse | -0.610 |
�� | -0.587 |
inately | -0.586 |
ighth | -0.583 |
Token | definitive |
Token ID | 17347 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Promotion | +0.277 |
tolerance | +0.261 |
Sao | +0.258 |
Chair | +0.257 |
Mania | +0.255 |
Neg logit contributions | |
enhagen | -0.406 |
ighthouse | -0.358 |
�� | -0.346 |
inately | -0.344 |
ighth | -0.344 |
Token | warning |
Token ID | 6509 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Promotion | +0.113 |
tolerance | +0.106 |
Sao | +0.105 |
Mania | +0.105 |
Chair | +0.104 |
Neg logit contributions | |
enhagen | -0.179 |
ighthouse | -0.159 |
�� | -0.153 |
ighth | -0.153 |
inately | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
enhagen | +0.999 |
ighthouse | +0.885 |
ighth | +0.842 |
�� | +0.841 |
inately | +0.839 |
Neg logit contributions | |
Promotion | -0.814 |
tolerance | -0.764 |
Sao | -0.756 |
Mania | -0.752 |
Chair | -0.751 |
Token | the |
Token ID | 262 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
enhagen | +0.459 |
ighthouse | +0.406 |
�� | +0.389 |
ighth | +0.388 |
inately | +0.386 |
Neg logit contributions | |
Promotion | -0.345 |
tolerance | -0.322 |
Sao | -0.321 |
Mania | -0.320 |
Chair | -0.318 |
Token | John |
Token ID | 1757 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
enhagen | +0.355 |
ighthouse | +0.312 |
�� | +0.301 |
inately | +0.299 |
ighth | +0.299 |
Neg logit contributions | |
Promotion | -0.268 |
tolerance | -0.253 |
Sao | -0.251 |
Chair | -0.249 |
Mania | -0.249 |
Token | J |
Token ID | 449 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
enhagen | +0.245 |
ighthouse | +0.216 |
�� | +0.206 |
ighth | +0.206 |
inately | +0.204 |
Neg logit contributions | |
Promotion | -0.216 |
tolerance | -0.206 |
Sao | -0.202 |
Chair | -0.201 |
TABLE | -0.201 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
enhagen | +1.618 |
ighthouse | +1.426 |
ighth | +1.358 |
inately | +1.332 |
�� | +1.330 |
Neg logit contributions | |
Promotion | -1.563 |
tolerance | -1.504 |
TABLE | -1.461 |
Sao | -1.460 |
Mania | -1.454 |
Token | Dug |
Token ID | 27436 |
Feature activation | +7.53e+00 |
Pos logit contributions | |
enhagen | +2.174 |
ighthouse | +1.931 |
ighth | +1.844 |
�� | +1.837 |
inately | +1.820 |
Neg logit contributions | |
Promotion | -1.747 |
tolerance | -1.684 |
Sao | -1.636 |
TABLE | -1.636 |
Mania | -1.628 |
Token | gan |
Token ID | 1030 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Promotion | +4.291 |
Chair | +4.135 |
tolerance | +3.992 |
Sao | +3.977 |
Mania | +3.968 |
Neg logit contributions | |
enhagen | -6.102 |
�� | -5.509 |
ighthouse | -5.426 |
inately | -5.316 |
ighth | -5.219 |
Token | Middle |
Token ID | 6046 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Promotion | +0.680 |
tolerance | +0.637 |
Sao | +0.627 |
Chair | +0.626 |
TABLE | +0.619 |
Neg logit contributions | |
enhagen | -1.170 |
ighthouse | -1.044 |
�� | -1.012 |
inately | -1.005 |
ighth | -1.004 |
Token | School |
Token ID | 3961 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
enhagen | +1.070 |
ighthouse | +0.938 |
�� | +0.907 |
ighth | +0.903 |
inately | +0.888 |
Neg logit contributions | |
Promotion | -0.866 |
tolerance | -0.823 |
Sao | -0.816 |
Mania | -0.804 |
TABLE | -0.804 |
Token | will |
Token ID | 481 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
Promotion | +0.197 |
tolerance | +0.186 |
Sao | +0.184 |
Chair | +0.183 |
TABLE | +0.182 |
Neg logit contributions | |
enhagen | -0.268 |
ighthouse | -0.238 |
�� | -0.229 |
inately | -0.227 |
ighth | -0.227 |
Token | open |
Token ID | 1280 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Promotion | +0.349 |
tolerance | +0.329 |
Sao | +0.326 |
Chair | +0.324 |
Mania | +0.322 |
Neg logit contributions | |
enhagen | -0.448 |
ighthouse | -0.395 |
�� | -0.379 |
inately | -0.378 |
ighth | -0.377 |
Token | just |
Token ID | 655 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Promotion | +0.723 |
tolerance | +0.684 |
Sao | +0.678 |
Chair | +0.678 |
TABLE | +0.670 |
Neg logit contributions | |
enhagen | -0.840 |
ighthouse | -0.735 |
�� | -0.707 |
inately | -0.702 |
ighth | -0.701 |
Token | last |
Token ID | 938 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
enhagen | +0.249 |
ighthouse | +0.218 |
�� | +0.210 |
inately | +0.209 |
ighth | +0.209 |
Neg logit contributions | |
Promotion | -0.198 |
tolerance | -0.186 |
Chair | -0.184 |
Sao | -0.184 |
Mania | -0.182 |
Token | year |
Token ID | 614 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
enhagen | +1.287 |
ighthouse | +1.093 |
inately | +1.063 |
ighth | +1.052 |
�� | +1.049 |
Neg logit contributions | |
Promotion | -1.282 |
tolerance | -1.212 |
Mania | -1.206 |
Chair | -1.203 |
TABLE | -1.197 |
Token | , |
Token ID | 11 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
enhagen | +0.347 |
ighthouse | +0.303 |
�� | +0.293 |
inately | +0.289 |
ighth | +0.289 |
Neg logit contributions | |
Promotion | -0.277 |
tolerance | -0.261 |
Sao | -0.260 |
Chair | -0.258 |
Mania | -0.258 |
Token | Michelle |
Token ID | 16738 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Promotion | +0.061 |
tolerance | +0.057 |
Sao | +0.057 |
Mania | +0.057 |
Chair | +0.057 |
Neg logit contributions | |
enhagen | -0.077 |
ighthouse | -0.068 |
�� | -0.066 |
ighth | -0.065 |
inately | -0.065 |
Token | Dug |
Token ID | 27436 |
Feature activation | +7.51e+00 |
Pos logit contributions | |
Promotion | +0.719 |
tolerance | +0.631 |
Chair | +0.614 |
Sao | +0.612 |
TABLE | +0.595 |
Neg logit contributions | |
enhagen | -2.982 |
ighthouse | -2.729 |
�� | -2.667 |
inately | -2.652 |
ighth | -2.649 |
Token | gar |
Token ID | 4563 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Promotion | +3.589 |
tolerance | +3.359 |
Chair | +3.355 |
** | +3.354 |
Mania | +3.304 |
Neg logit contributions | |
enhagen | -6.902 |
�� | -6.246 |
ighthouse | -6.119 |
ighth | -5.949 |
inately | -5.869 |
Token | lent |
Token ID | 26269 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Promotion | +1.259 |
tolerance | +1.172 |
Chair | +1.161 |
Sao | +1.153 |
TABLE | +1.138 |
Neg logit contributions | |
enhagen | -2.382 |
ighthouse | -2.139 |
�� | -2.084 |
inately | -2.061 |
ighth | -2.059 |
Token | her |
Token ID | 607 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
enhagen | +0.454 |
ighthouse | +0.397 |
�� | +0.379 |
ighth | +0.378 |
inately | +0.377 |
Neg logit contributions | |
Promotion | -0.407 |
Sao | -0.383 |
Mania | -0.383 |
tolerance | -0.382 |
TABLE | -0.380 |
Token | voice |
Token ID | 3809 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
enhagen | +1.206 |
ighthouse | +1.053 |
inately | +1.015 |
ighth | +1.012 |
�� | +1.004 |
Neg logit contributions | |
Promotion | -0.823 |
Mania | -0.772 |
Sao | -0.763 |
TABLE | -0.760 |
tolerance | -0.760 |
Token | to |
Token ID | 284 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
enhagen | +2.634 |
ighthouse | +2.304 |
inately | +2.194 |
ighth | +2.192 |
�� | +2.176 |
Neg logit contributions | |
Promotion | -2.132 |
tolerance | -1.992 |
Sao | -1.986 |
TABLE | -1.978 |
Chair | -1.964 |
Token | was |
Token ID | 373 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
enhagen | +0.469 |
ighthouse | +0.413 |
ighth | +0.398 |
inately | +0.396 |
�� | +0.393 |
Neg logit contributions | |
Promotion | -0.345 |
tolerance | -0.322 |
Chair | -0.319 |
Sao | -0.318 |
Mania | -0.317 |
Token | tipped |
Token ID | 28395 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
enhagen | +0.486 |
ighthouse | +0.428 |
ighth | +0.414 |
inately | +0.412 |
�� | +0.407 |
Neg logit contributions | |
Promotion | -0.378 |
tolerance | -0.355 |
Mania | -0.352 |
Chair | -0.351 |
Sao | -0.350 |
Token | as |
Token ID | 355 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
enhagen | +0.313 |
ighthouse | +0.277 |
inately | +0.265 |
�� | +0.265 |
ighth | +0.265 |
Neg logit contributions | |
Promotion | -0.226 |
tolerance | -0.212 |
Chair | -0.210 |
Sao | -0.210 |
TABLE | -0.208 |
Token | a |
Token ID | 257 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Promotion | +1.543 |
tolerance | +1.457 |
Sao | +1.440 |
Chair | +1.439 |
TABLE | +1.421 |
Neg logit contributions | |
enhagen | -2.062 |
ighthouse | -1.817 |
�� | -1.755 |
inately | -1.741 |
ighth | -1.737 |
Token | future |
Token ID | 2003 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Promotion | +0.209 |
tolerance | +0.198 |
Chair | +0.197 |
Sao | +0.196 |
TABLE | +0.195 |
Neg logit contributions | |
enhagen | -0.261 |
ighthouse | -0.228 |
�� | -0.220 |
ighth | -0.219 |
inately | -0.219 |
Token | Formula |
Token ID | 19639 |
Feature activation | +7.37e+00 |
Pos logit contributions | |
enhagen | +1.801 |
ighthouse | +1.614 |
ighth | +1.582 |
inately | +1.569 |
�� | +1.559 |
Neg logit contributions | |
Promotion | -0.786 |
tolerance | -0.728 |
Mania | -0.720 |
TABLE | -0.718 |
Sao | -0.706 |
Token | One |
Token ID | 1881 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
Promotion | +3.179 |
Sao | +2.985 |
Chair | +2.927 |
tolerance | +2.890 |
Mania | +2.828 |
Neg logit contributions | |
enhagen | -7.321 |
ighthouse | -6.557 |
inately | -6.477 |
�� | -6.385 |
ighth | -6.313 |
Token | champion |
Token ID | 8783 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Promotion | +2.691 |
tolerance | +2.520 |
Chair | +2.510 |
Sao | +2.492 |
Mania | +2.415 |
Neg logit contributions | |
enhagen | -4.614 |
ighthouse | -4.079 |
�� | -3.969 |
inately | -3.940 |
ighth | -3.867 |
Token | , |
Token ID | 11 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
Promotion | +1.206 |
tolerance | +1.141 |
Sao | +1.129 |
Chair | +1.128 |
Mania | +1.110 |
Neg logit contributions | |
enhagen | -1.513 |
ighthouse | -1.327 |
�� | -1.286 |
inately | -1.269 |
ighth | -1.264 |
Token | a |
Token ID | 257 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
Promotion | +0.591 |
tolerance | +0.563 |
Chair | +0.557 |
Sao | +0.556 |
TABLE | +0.552 |
Neg logit contributions | |
enhagen | -0.617 |
ighthouse | -0.535 |
�� | -0.513 |
inately | -0.509 |
ighth | -0.509 |
Token | prediction |
Token ID | 17724 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Promotion | +0.014 |
tolerance | +0.013 |
Chair | +0.013 |
TABLE | +0.013 |
Mania | +0.013 |
Neg logit contributions | |
enhagen | -0.021 |
ighthouse | -0.019 |
�� | -0.018 |
inately | -0.018 |
ighth | -0.018 |
Token | $ |
Token ID | 720 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
enhagen | +0.082 |
ighthouse | +0.073 |
inately | +0.071 |
ighth | +0.070 |
�� | +0.070 |
Neg logit contributions | |
Promotion | -0.054 |
Sao | -0.051 |
Mania | -0.051 |
tolerance | -0.050 |
Chair | -0.050 |
Token | 20 |
Token ID | 1238 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
enhagen | +0.053 |
ighthouse | +0.047 |
ighth | +0.046 |
�� | +0.045 |
inately | +0.045 |
Neg logit contributions | |
Promotion | -0.034 |
tolerance | -0.032 |
Sao | -0.032 |
Chair | -0.032 |
TABLE | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
enhagen | +0.231 |
ighthouse | +0.207 |
�� | +0.200 |
ighth | +0.200 |
inately | +0.199 |
Neg logit contributions | |
Promotion | -0.151 |
tolerance | -0.143 |
Sao | -0.142 |
TABLE | -0.142 |
Chair | -0.142 |
Token | 000 |
Token ID | 830 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
enhagen | +1.012 |
ighthouse | +0.904 |
ighth | +0.868 |
�� | +0.867 |
inately | +0.856 |
Neg logit contributions | |
Promotion | -0.767 |
tolerance | -0.729 |
Sao | -0.723 |
Mania | -0.721 |
Chair | -0.720 |
Token | prize |
Token ID | 11596 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Promotion | +0.021 |
Sao | +0.019 |
tolerance | +0.019 |
Mania | +0.019 |
TABLE | +0.019 |
Neg logit contributions | |
enhagen | -0.057 |
ighthouse | -0.052 |
�� | -0.050 |
inately | -0.050 |
ighth | -0.050 |
Token | pool |
Token ID | 5933 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
Promotion | +0.457 |
tolerance | +0.380 |
Chair | +0.352 |
Sao | +0.347 |
TABLE | +0.330 |
Neg logit contributions | |
enhagen | -3.248 |
ighthouse | -2.997 |
�� | -2.940 |
ighth | -2.914 |
inately | -2.914 |
Token | , |
Token ID | 11 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Promotion | +4.332 |
tolerance | +4.103 |
Chair | +3.995 |
** | +3.973 |
Sao | +3.925 |
Neg logit contributions | |
enhagen | -6.083 |
ighthouse | -5.467 |
�� | -5.431 |
ighth | -5.199 |
inately | -5.171 |
Token | and |
Token ID | 290 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
Promotion | +0.213 |
tolerance | +0.201 |
Sao | +0.200 |
Chair | +0.199 |
Mania | +0.199 |
Neg logit contributions | |
enhagen | -0.266 |
ighthouse | -0.233 |
ighth | -0.223 |
�� | -0.222 |
inately | -0.222 |
Token | only |
Token ID | 691 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Promotion | +0.448 |
tolerance | +0.424 |
Chair | +0.420 |
Sao | +0.419 |
Mania | +0.418 |
Neg logit contributions | |
enhagen | -0.592 |
ighthouse | -0.518 |
inately | -0.499 |
ighth | -0.498 |
�� | -0.496 |
Token | six |
Token ID | 2237 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
enhagen | +0.339 |
ighthouse | +0.298 |
ighth | +0.289 |
inately | +0.289 |
�� | +0.285 |
Neg logit contributions | |
Promotion | -0.220 |
tolerance | -0.208 |
Mania | -0.206 |
Chair | -0.205 |
Sao | -0.204 |
Token | teams |
Token ID | 3466 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
enhagen | +1.140 |
ighthouse | +1.000 |
ighth | +0.965 |
inately | +0.950 |
�� | +0.949 |
Neg logit contributions | |
Promotion | -0.897 |
tolerance | -0.857 |
Chair | -0.848 |
Mania | -0.848 |
Sao | -0.846 |
Token | Trent |
Token ID | 24269 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Promotion | +0.457 |
tolerance | +0.436 |
Chair | +0.428 |
TABLE | +0.428 |
Sao | +0.426 |
Neg logit contributions | |
enhagen | -0.518 |
ighthouse | -0.454 |
�� | -0.433 |
inately | -0.433 |
ighth | -0.432 |
Token | in |
Token ID | 259 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Promotion | +1.481 |
tolerance | +1.412 |
Chair | +1.405 |
Sao | +1.405 |
TABLE | +1.385 |
Neg logit contributions | |
enhagen | -1.261 |
ighthouse | -1.079 |
�� | -1.037 |
inately | -1.017 |
ighth | -1.016 |
Token | ( |
Token ID | 357 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Promotion | +0.192 |
tolerance | +0.182 |
Chair | +0.179 |
Sao | +0.179 |
TABLE | +0.177 |
Neg logit contributions | |
enhagen | -0.255 |
ighthouse | -0.224 |
�� | -0.216 |
inately | -0.215 |
ighth | -0.215 |
Token | O |
Token ID | 46 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Promotion | +1.282 |
tolerance | +1.218 |
Chair | +1.192 |
Sao | +1.189 |
TABLE | +1.178 |
Neg logit contributions | |
enhagen | -1.885 |
ighthouse | -1.685 |
�� | -1.618 |
ighth | -1.616 |
inately | -1.611 |
Token | mega |
Token ID | 13731 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
enhagen | +0.941 |
ighthouse | +0.806 |
ighth | +0.769 |
inately | +0.767 |
�� | +0.765 |
Neg logit contributions | |
Promotion | -1.009 |
tolerance | -0.967 |
Chair | -0.957 |
Sao | -0.955 |
TABLE | -0.950 |
Token | Pharma |
Token ID | 41845 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
Promotion | +1.216 |
tolerance | +1.127 |
Chair | +1.107 |
Sao | +1.095 |
Mania | +1.089 |
Neg logit contributions | |
enhagen | -2.966 |
ighthouse | -2.685 |
�� | -2.610 |
ighth | -2.606 |
inately | -2.595 |
Token | - |
Token ID | 532 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Promotion | +3.759 |
tolerance | +3.445 |
Sao | +3.428 |
Chair | +3.417 |
TABLE | +3.287 |
Neg logit contributions | |
enhagen | -6.785 |
ighthouse | -6.112 |
�� | -5.940 |
inately | -5.864 |
ighth | -5.842 |
Token | Quick |
Token ID | 12029 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Promotion | +1.164 |
tolerance | +1.108 |
Chair | +1.096 |
Sao | +1.094 |
TABLE | +1.084 |
Neg logit contributions | |
enhagen | -1.282 |
ighthouse | -1.116 |
�� | -1.072 |
inately | -1.063 |
ighth | -1.061 |
Token | step |
Token ID | 9662 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
Promotion | +1.333 |
tolerance | +1.224 |
Chair | +1.199 |
Sao | +1.198 |
TABLE | +1.183 |
Neg logit contributions | |
enhagen | -3.408 |
ighthouse | -3.083 |
�� | -3.000 |
ighth | -2.979 |
inately | -2.978 |
Token | ) |
Token ID | 8 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
Promotion | +2.411 |
tolerance | +2.241 |
Chair | +2.222 |
Sao | +2.218 |
TABLE | +2.171 |
Neg logit contributions | |
enhagen | -3.832 |
ighthouse | -3.398 |
�� | -3.316 |
inately | -3.270 |
ighth | -3.260 |
Token | s |
Token ID | 264 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Promotion | +0.275 |
tolerance | +0.261 |
Chair | +0.257 |
Sao | +0.257 |
Mania | +0.256 |
Neg logit contributions | |
enhagen | -0.356 |
ighthouse | -0.312 |
�� | -0.300 |
inately | -0.299 |
ighth | -0.299 |
Token | with |
Token ID | 351 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Promotion | +0.838 |
tolerance | +0.791 |
Sao | +0.781 |
Chair | +0.781 |
TABLE | +0.771 |
Neg logit contributions | |
enhagen | -1.163 |
ighthouse | -1.026 |
�� | -0.993 |
inately | -0.984 |
ighth | -0.982 |
Token | the |
Token ID | 262 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
enhagen | +1.153 |
ighthouse | +1.013 |
ighth | +0.977 |
inately | +0.973 |
�� | +0.970 |
Neg logit contributions | |
Promotion | -0.804 |
tolerance | -0.764 |
Chair | -0.753 |
TABLE | -0.750 |
Mania | -0.750 |
Token | upcoming |
Token ID | 7865 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Promotion | +0.097 |
tolerance | +0.092 |
Chair | +0.091 |
Mania | +0.090 |
TABLE | +0.090 |
Neg logit contributions | |
enhagen | -0.155 |
ighthouse | -0.137 |
�� | -0.133 |
inately | -0.132 |
ighth | -0.132 |
Token | Rally |
Token ID | 27752 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
Promotion | +0.240 |
tolerance | +0.227 |
Chair | +0.224 |
TABLE | +0.222 |
Mania | +0.222 |
Neg logit contributions | |
enhagen | -0.375 |
ighthouse | -0.332 |
�� | -0.321 |
inately | -0.320 |
ighth | -0.319 |
Token | e |
Token ID | 68 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Promotion | +2.407 |
tolerance | +2.253 |
Sao | +2.236 |
Chair | +2.229 |
Mania | +2.205 |
Neg logit contributions | |
enhagen | -3.849 |
ighthouse | -3.421 |
�� | -3.317 |
inately | -3.300 |
ighth | -3.289 |
Token | Monte |
Token ID | 22489 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
Promotion | +1.184 |
tolerance | +1.114 |
Chair | +1.096 |
Sao | +1.090 |
TABLE | +1.084 |
Neg logit contributions | |
enhagen | -1.879 |
ighthouse | -1.673 |
�� | -1.620 |
ighth | -1.610 |
inately | -1.604 |
Token | - |
Token ID | 12 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
Promotion | +3.249 |
Sao | +3.057 |
tolerance | +3.013 |
Chair | +2.992 |
Mania | +2.895 |
Neg logit contributions | |
enhagen | -7.045 |
ighthouse | -6.416 |
�� | -6.270 |
inately | -6.255 |
ighth | -6.210 |
Token | Car |
Token ID | 9914 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
enhagen | +0.090 |
ighthouse | +0.080 |
ighth | +0.076 |
inately | +0.076 |
�� | +0.076 |
Neg logit contributions | |
Promotion | -0.047 |
tolerance | -0.044 |
Chair | -0.043 |
TABLE | -0.043 |
Sao | -0.042 |
Token | lo |
Token ID | 5439 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
Promotion | +0.185 |
tolerance | +0.177 |
Chair | +0.171 |
TABLE | +0.171 |
Sao | +0.170 |
Neg logit contributions | |
enhagen | -0.257 |
ighthouse | -0.228 |
ighth | -0.217 |
inately | -0.217 |
�� | -0.214 |
Token | . |
Token ID | 13 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
enhagen | +0.570 |
ighthouse | +0.503 |
ighth | +0.487 |
inately | +0.487 |
�� | +0.487 |
Neg logit contributions | |
Promotion | -0.317 |
tolerance | -0.301 |
TABLE | -0.294 |
Chair | -0.293 |
Mania | -0.291 |
Token | We |
Token ID | 775 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Promotion | +0.212 |
tolerance | +0.205 |
Chair | +0.197 |
Sao | +0.197 |
TABLE | +0.196 |
Neg logit contributions | |
enhagen | -0.276 |
ighthouse | -0.244 |
ighth | -0.234 |
�� | -0.232 |
inately | -0.231 |
Token | teaching |
Token ID | 7743 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
enhagen | +0.290 |
ighthouse | +0.256 |
�� | +0.247 |
inately | +0.246 |
ighth | +0.245 |
Neg logit contributions | |
Promotion | -0.207 |
tolerance | -0.194 |
Sao | -0.194 |
Mania | -0.193 |
Chair | -0.192 |
Token | " |
Token ID | 366 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
enhagen | +1.230 |
ighthouse | +1.095 |
�� | +1.051 |
ighth | +1.050 |
inately | +1.047 |
Neg logit contributions | |
Promotion | -0.914 |
Mania | -0.852 |
Sao | -0.847 |
TABLE | -0.842 |
Chair | -0.841 |
Token | fair |
Token ID | 22043 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
enhagen | +2.043 |
ighthouse | +1.783 |
�� | +1.703 |
ighth | +1.697 |
inately | +1.683 |
Neg logit contributions | |
Promotion | -2.005 |
Sao | -1.906 |
Chair | -1.892 |
TABLE | -1.886 |
tolerance | -1.873 |
Token | ness |
Token ID | 1108 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
enhagen | +1.739 |
ighthouse | +1.545 |
ighth | +1.484 |
inately | +1.473 |
�� | +1.471 |
Neg logit contributions | |
Promotion | -1.061 |
Mania | -0.997 |
Sao | -0.990 |
Chair | -0.989 |
TABLE | -0.979 |
Token | ." |
Token ID | 526 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Promotion | +0.340 |
Sao | +0.318 |
tolerance | +0.318 |
Chair | +0.318 |
TABLE | +0.315 |
Neg logit contributions | |
enhagen | -0.454 |
ighthouse | -0.401 |
�� | -0.384 |
inately | -0.383 |
ighth | -0.382 |
Token | Dug |
Token ID | 27436 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
enhagen | +0.267 |
ighthouse | +0.239 |
ighth | +0.229 |
�� | +0.229 |
inately | +0.226 |
Neg logit contributions | |
Promotion | -0.183 |
tolerance | -0.176 |
Sao | -0.172 |
Mania | -0.171 |
Chair | -0.170 |
Token | gan |
Token ID | 1030 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Promotion | +3.786 |
Mania | +3.639 |
Chair | +3.585 |
tolerance | +3.566 |
** | +3.562 |
Neg logit contributions | |
enhagen | -6.281 |
�� | -5.778 |
ighthouse | -5.533 |
inately | -5.396 |
�� | -5.351 |
Token | Middle |
Token ID | 6046 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Promotion | +0.901 |
tolerance | +0.852 |
Chair | +0.844 |
Sao | +0.840 |
TABLE | +0.830 |
Neg logit contributions | |
enhagen | -1.205 |
ighthouse | -1.060 |
�� | -1.026 |
inately | -1.018 |
ighth | -1.014 |
Token | School |
Token ID | 3961 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
enhagen | +1.268 |
ighthouse | +1.118 |
�� | +1.076 |
ighth | +1.065 |
inately | +1.058 |
Neg logit contributions | |
Promotion | -1.005 |
tolerance | -0.955 |
Sao | -0.942 |
TABLE | -0.935 |
Mania | -0.935 |
Token | 's |
Token ID | 338 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Promotion | +0.222 |
tolerance | +0.209 |
Sao | +0.207 |
Chair | +0.206 |
Mania | +0.205 |
Neg logit contributions | |
enhagen | -0.307 |
ighthouse | -0.272 |
�� | -0.262 |
inately | -0.260 |
ighth | -0.260 |
Token | junior |
Token ID | 13430 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
Promotion | +0.171 |
tolerance | +0.160 |
Sao | +0.159 |
Chair | +0.158 |
Mania | +0.158 |
Neg logit contributions | |
enhagen | -0.241 |
ighthouse | -0.213 |
�� | -0.206 |
ighth | -0.204 |
inately | -0.204 |
Token | waiting |
Token ID | 4953 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Promotion | +0.001 |
tolerance | +0.001 |
Chair | +0.001 |
Sao | +0.001 |
Mania | +0.000 |
Neg logit contributions | |
enhagen | -0.001 |
ighthouse | -0.001 |
�� | -0.001 |
inately | -0.001 |
ighth | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
Promotion | +1.638 |
tolerance | +1.549 |
Chair | +1.530 |
Sao | +1.528 |
TABLE | +1.515 |
Neg logit contributions | |
enhagen | -2.219 |
ighthouse | -1.960 |
�� | -1.902 |
ighth | -1.875 |
inately | -1.875 |
Token | the |
Token ID | 262 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
Promotion | +0.569 |
tolerance | +0.539 |
Chair | +0.532 |
Sao | +0.530 |
Mania | +0.525 |
Neg logit contributions | |
enhagen | -0.776 |
ighthouse | -0.684 |
�� | -0.658 |
inately | -0.655 |
ighth | -0.653 |
Token | return |
Token ID | 1441 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
Promotion | +0.399 |
tolerance | +0.378 |
Chair | +0.373 |
Sao | +0.372 |
Mania | +0.369 |
Neg logit contributions | |
enhagen | -0.568 |
ighthouse | -0.502 |
�� | -0.483 |
inately | -0.481 |
ighth | -0.481 |
Token | of |
Token ID | 286 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
enhagen | +0.256 |
ighthouse | +0.222 |
�� | +0.213 |
ighth | +0.211 |
inately | +0.211 |
Neg logit contributions | |
Promotion | -0.244 |
tolerance | -0.233 |
Sao | -0.231 |
Chair | -0.230 |
Mania | -0.228 |
Token | Starcraft |
Token ID | 44197 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
enhagen | +0.295 |
ighthouse | +0.260 |
�� | +0.251 |
ighth | +0.249 |
inately | +0.249 |
Neg logit contributions | |
Promotion | -0.205 |
tolerance | -0.194 |
Chair | -0.191 |
Sao | -0.190 |
Mania | -0.189 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Promotion | +3.635 |
Sao | +3.378 |
Chair | +3.323 |
TABLE | +3.308 |
tolerance | +3.302 |
Neg logit contributions | |
enhagen | -6.654 |
ighthouse | -5.983 |
�� | -5.834 |
ighth | -5.823 |
inately | -5.770 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Promotion | +0.659 |
tolerance | +0.621 |
Chair | +0.617 |
Sao | +0.613 |
Mania | +0.607 |
Neg logit contributions | |
enhagen | -0.924 |
ighthouse | -0.806 |
�� | -0.790 |
inately | -0.776 |
ighth | -0.773 |
Token | re |
Token ID | 260 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Promotion | +0.778 |
tolerance | +0.739 |
Sao | +0.730 |
Chair | +0.729 |
TABLE | +0.722 |
Neg logit contributions | |
enhagen | -0.919 |
ighthouse | -0.805 |
�� | -0.774 |
ighth | -0.769 |
inately | -0.768 |
Token | i |
Token ID | 72 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
enhagen | +1.284 |
ighthouse | +1.130 |
ighth | +1.091 |
inately | +1.078 |
�� | +1.078 |
Neg logit contributions | |
Promotion | -1.064 |
tolerance | -1.012 |
Sao | -1.003 |
Chair | -1.002 |
TABLE | -0.994 |
Token | Profile |
Token ID | 13118 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Promotion | +0.817 |
tolerance | +0.773 |
Chair | +0.764 |
Sao | +0.764 |
TABLE | +0.756 |
Neg logit contributions | |
enhagen | -1.032 |
ighthouse | -0.906 |
�� | -0.873 |
inately | -0.866 |
ighth | -0.866 |
Token | pling |
Token ID | 11347 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
Promotion | +1.679 |
tolerance | +1.573 |
Chair | +1.552 |
Sao | +1.550 |
Mania | +1.523 |
Neg logit contributions | |
enhagen | -2.893 |
ighthouse | -2.579 |
�� | -2.505 |
inately | -2.491 |
ighth | -2.477 |
Token | subway |
Token ID | 19612 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
enhagen | +0.059 |
ighthouse | +0.052 |
�� | +0.049 |
inately | +0.049 |
ighth | +0.049 |
Neg logit contributions | |
Promotion | -0.052 |
tolerance | -0.049 |
Sao | -0.048 |
Chair | -0.048 |
Mania | -0.048 |
Token | station |
Token ID | 4429 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Promotion | +0.286 |
tolerance | +0.274 |
Sao | +0.272 |
Chair | +0.271 |
TABLE | +0.270 |
Neg logit contributions | |
enhagen | -0.178 |
ighthouse | -0.147 |
�� | -0.138 |
inately | -0.137 |
ighth | -0.136 |
Token | in |
Token ID | 287 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Promotion | +1.552 |
tolerance | +1.474 |
Sao | +1.462 |
Chair | +1.461 |
TABLE | +1.437 |
Neg logit contributions | |
enhagen | -1.974 |
ighthouse | -1.730 |
�� | -1.679 |
inately | -1.657 |
ighth | -1.654 |
Token | Et |
Token ID | 17906 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
Promotion | +0.695 |
tolerance | +0.655 |
Chair | +0.645 |
Sao | +0.645 |
TABLE | +0.641 |
Neg logit contributions | |
enhagen | -0.996 |
ighthouse | -0.883 |
�� | -0.850 |
inately | -0.846 |
ighth | -0.845 |
Token | obic |
Token ID | 20803 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
Promotion | +2.774 |
Chair | +2.621 |
tolerance | +2.580 |
Oaks | +2.557 |
Sao | +2.555 |
Neg logit contributions | |
enhagen | -3.786 |
�� | -3.439 |
ighthouse | -3.352 |
ighth | -3.265 |
inately | -3.248 |
Token | oke |
Token ID | 2088 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Promotion | +4.283 |
tolerance | +4.134 |
Chair | +4.057 |
Sao | +4.029 |
Oaks | +4.018 |
Neg logit contributions | |
enhagen | -5.889 |
ighthouse | -5.130 |
�� | -5.015 |
ighth | -4.879 |
inately | -4.851 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Promotion | +1.038 |
tolerance | +0.982 |
Chair | +0.977 |
Sao | +0.971 |
TABLE | +0.960 |
Neg logit contributions | |
enhagen | -1.286 |
ighthouse | -1.127 |
�� | -1.092 |
inately | -1.078 |
ighth | -1.074 |
Token |
|
Token ID | 198 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Promotion | +0.188 |
tolerance | +0.180 |
Sao | +0.176 |
Chair | +0.176 |
Mania | +0.174 |
Neg logit contributions | |
enhagen | -0.243 |
ighthouse | -0.215 |
ighth | -0.205 |
�� | -0.205 |
inately | -0.203 |
Token |
|
Token ID | 198 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Promotion | +0.127 |
tolerance | +0.120 |
Chair | +0.119 |
Sao | +0.118 |
TABLE | +0.117 |
Neg logit contributions | |
enhagen | -0.169 |
ighthouse | -0.149 |
�� | -0.144 |
inately | -0.143 |
ighth | -0.142 |
Token | Police |
Token ID | 9039 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Promotion | +0.390 |
tolerance | +0.369 |
Sao | +0.365 |
Chair | +0.363 |
TABLE | +0.359 |
Neg logit contributions | |
enhagen | -0.502 |
ighthouse | -0.444 |
�� | -0.426 |
ighth | -0.425 |
inately | -0.423 |
Token | points |
Token ID | 2173 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
enhagen | +0.784 |
ighthouse | +0.688 |
ighth | +0.661 |
inately | +0.657 |
�� | +0.655 |
Neg logit contributions | |
Promotion | -0.588 |
tolerance | -0.549 |
Sao | -0.542 |
Chair | -0.542 |
Mania | -0.540 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
enhagen | +0.885 |
ighthouse | +0.777 |
�� | +0.749 |
inately | +0.744 |
ighth | +0.741 |
Neg logit contributions | |
Promotion | -0.684 |
tolerance | -0.644 |
Chair | -0.639 |
Sao | -0.638 |
TABLE | -0.632 |
Token | the |
Token ID | 262 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
Promotion | +0.074 |
tolerance | +0.070 |
Chair | +0.070 |
Sao | +0.069 |
Mania | +0.069 |
Neg logit contributions | |
enhagen | -0.091 |
ighthouse | -0.080 |
�� | -0.077 |
inately | -0.076 |
ighth | -0.076 |
Token | case |
Token ID | 1339 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Promotion | +0.044 |
tolerance | +0.042 |
Chair | +0.041 |
Sao | +0.041 |
TABLE | +0.041 |
Neg logit contributions | |
enhagen | -0.055 |
ighthouse | -0.048 |
�� | -0.047 |
inately | -0.046 |
ighth | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
enhagen | +1.153 |
ighthouse | +1.001 |
�� | +0.964 |
inately | +0.952 |
ighth | +0.951 |
Neg logit contributions | |
Promotion | -1.073 |
tolerance | -1.017 |
Chair | -1.007 |
Sao | -1.006 |
TABLE | -0.998 |
Token | Tad |
Token ID | 50077 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
enhagen | +0.408 |
ighthouse | +0.356 |
�� | +0.343 |
inately | +0.342 |
ighth | +0.342 |
Neg logit contributions | |
Promotion | -0.317 |
tolerance | -0.300 |
Mania | -0.296 |
Chair | -0.296 |
TABLE | -0.295 |
Token | am |
Token ID | 321 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Promotion | +4.878 |
Chair | +4.628 |
Sao | +4.616 |
tolerance | +4.616 |
Mania | +4.572 |
Neg logit contributions | |
enhagen | -5.109 |
ighthouse | -4.457 |
�� | -4.330 |
inately | -4.268 |
ighth | -4.213 |
Token | asa |
Token ID | 15462 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
Promotion | +2.092 |
tolerance | +1.973 |
Chair | +1.953 |
Sao | +1.948 |
Mania | +1.922 |
Neg logit contributions | |
enhagen | -2.895 |
ighthouse | -2.552 |
�� | -2.466 |
inately | -2.450 |
ighth | -2.443 |
Token | G |
Token ID | 402 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Promotion | +2.687 |
tolerance | +2.528 |
Chair | +2.524 |
Sao | +2.520 |
TABLE | +2.465 |
Neg logit contributions | |
enhagen | -3.289 |
ighthouse | -2.874 |
�� | -2.764 |
inately | -2.764 |
ighth | -2.747 |
Token | oto |
Token ID | 2069 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Promotion | +0.746 |
tolerance | +0.709 |
Chair | +0.701 |
Sao | +0.700 |
Mania | +0.692 |
Neg logit contributions | |
enhagen | -0.824 |
ighthouse | -0.716 |
�� | -0.692 |
inately | -0.685 |
ighth | -0.681 |
Token | , |
Token ID | 11 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
Promotion | +0.100 |
tolerance | +0.094 |
Chair | +0.093 |
Sao | +0.093 |
TABLE | +0.092 |
Neg logit contributions | |
enhagen | -0.128 |
ighthouse | -0.112 |
�� | -0.108 |
inately | -0.108 |
ighth | -0.108 |
Token | activity |
Token ID | 3842 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Promotion | +1.652 |
tolerance | +1.550 |
Chair | +1.527 |
Sao | +1.523 |
TABLE | +1.505 |
Neg logit contributions | |
enhagen | -2.719 |
ighthouse | -2.414 |
�� | -2.342 |
inately | -2.324 |
ighth | -2.319 |
Token | , |
Token ID | 11 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
Promotion | +0.806 |
tolerance | +0.760 |
Chair | +0.750 |
Sao | +0.750 |
TABLE | +0.741 |
Neg logit contributions | |
enhagen | -1.134 |
ighthouse | -1.001 |
�� | -0.968 |
inately | -0.961 |
ighth | -0.959 |
Token | � |
Token ID | 447 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Promotion | +0.036 |
tolerance | +0.034 |
Sao | +0.034 |
Chair | +0.033 |
Mania | +0.033 |
Neg logit contributions | |
enhagen | -0.064 |
ighthouse | -0.057 |
�� | -0.055 |
ighth | -0.055 |
inately | -0.055 |
Token | � |
Token ID | 251 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
enhagen | +0.231 |
ighthouse | +0.195 |
�� | +0.189 |
ighth | +0.183 |
inately | +0.183 |
Neg logit contributions | |
Promotion | -0.315 |
tolerance | -0.302 |
Sao | -0.301 |
Chair | -0.299 |
Mania | -0.298 |
Token | wrote |
Token ID | 2630 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Promotion | +0.200 |
tolerance | +0.189 |
Sao | +0.188 |
Chair | +0.186 |
Mania | +0.186 |
Neg logit contributions | |
enhagen | -0.283 |
ighthouse | -0.250 |
�� | -0.241 |
ighth | -0.239 |
inately | -0.239 |
Token | Aub |
Token ID | 19723 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
Promotion | +0.796 |
tolerance | +0.753 |
Sao | +0.744 |
Chair | +0.743 |
TABLE | +0.735 |
Neg logit contributions | |
enhagen | -1.014 |
ighthouse | -0.890 |
�� | -0.858 |
inately | -0.852 |
ighth | -0.851 |
Token | rey |
Token ID | 4364 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Promotion | +5.461 |
Chair | +5.247 |
Sao | +5.207 |
Mania | +5.146 |
tolerance | +5.138 |
Neg logit contributions | |
enhagen | -4.304 |
ighthouse | -3.677 |
�� | -3.659 |
inately | -3.423 |
ighth | -3.422 |
Token | El |
Token ID | 2574 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Promotion | +0.626 |
tolerance | +0.594 |
Sao | +0.584 |
Chair | +0.584 |
TABLE | +0.579 |
Neg logit contributions | |
enhagen | -0.805 |
ighthouse | -0.708 |
�� | -0.681 |
ighth | -0.677 |
inately | -0.677 |
Token | en |
Token ID | 268 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Promotion | +1.365 |
tolerance | +1.294 |
Sao | +1.282 |
Chair | +1.282 |
TABLE | +1.265 |
Neg logit contributions | |
enhagen | -1.544 |
ighthouse | -1.347 |
�� | -1.301 |
inately | -1.288 |
ighth | -1.283 |
Token | is |
Token ID | 271 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
enhagen | +0.099 |
ighthouse | +0.086 |
�� | +0.083 |
ighth | +0.082 |
inately | +0.082 |
Neg logit contributions | |
Promotion | -0.090 |
tolerance | -0.086 |
Sao | -0.085 |
Chair | -0.084 |
TABLE | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
enhagen | +0.725 |
ighthouse | +0.636 |
�� | +0.608 |
ighth | +0.608 |
inately | +0.605 |
Neg logit contributions | |
Promotion | -0.580 |
tolerance | -0.552 |
Sao | -0.542 |
Mania | -0.539 |
Chair | -0.538 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
enhagen | +0.432 |
ighthouse | +0.377 |
�� | +0.362 |
inately | +0.359 |
ighth | +0.359 |
Neg logit contributions | |
Promotion | -0.375 |
tolerance | -0.357 |
Sao | -0.354 |
Chair | -0.353 |
Mania | -0.350 |
Token | The |
Token ID | 383 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
enhagen | +0.145 |
ighthouse | +0.129 |
�� | +0.124 |
ighth | +0.124 |
inately | +0.124 |
Neg logit contributions | |
Promotion | -0.093 |
tolerance | -0.090 |
Sao | -0.087 |
Chair | -0.087 |
Mania | -0.086 |
Token | rising |
Token ID | 7396 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Promotion | +0.041 |
tolerance | +0.038 |
Sao | +0.038 |
Chair | +0.038 |
TABLE | +0.038 |
Neg logit contributions | |
enhagen | -0.055 |
ighthouse | -0.049 |
�� | -0.047 |
inately | -0.047 |
ighth | -0.047 |
Token | practice |
Token ID | 3357 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
enhagen | +1.007 |
ighthouse | +0.879 |
ighth | +0.843 |
�� | +0.842 |
inately | +0.841 |
Neg logit contributions | |
Promotion | -0.831 |
Mania | -0.778 |
Sao | -0.776 |
Chair | -0.776 |
TABLE | -0.773 |
Token | of |
Token ID | 286 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Promotion | +2.197 |
tolerance | +2.110 |
Chair | +2.065 |
Sao | +2.062 |
TABLE | +2.041 |
Neg logit contributions | |
enhagen | -2.514 |
ighthouse | -2.194 |
�� | -2.117 |
inately | -2.100 |
ighth | -2.094 |
Token | qu |
Token ID | 627 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
Promotion | +0.394 |
tolerance | +0.369 |
Sao | +0.368 |
Chair | +0.367 |
Mania | +0.363 |
Neg logit contributions | |
enhagen | -0.585 |
ighthouse | -0.518 |
�� | -0.503 |
ighth | -0.499 |
inately | -0.498 |
Token | ack |
Token ID | 441 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Promotion | +4.144 |
tolerance | +3.931 |
Chair | +3.922 |
** | +3.920 |
Sao | +3.896 |
Neg logit contributions | |
enhagen | -5.554 |
�� | -4.942 |
ighthouse | -4.768 |
inately | -4.625 |
ighth | -4.511 |
Token | ery |
Token ID | 1924 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Promotion | +0.723 |
Chair | +0.679 |
Sao | +0.678 |
tolerance | +0.677 |
TABLE | +0.672 |
Neg logit contributions | |
enhagen | -0.923 |
ighthouse | -0.809 |
�� | -0.782 |
ighth | -0.779 |
inately | -0.776 |
Token | and |
Token ID | 290 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Promotion | +0.987 |
tolerance | +0.929 |
Chair | +0.920 |
Sao | +0.920 |
TABLE | +0.909 |
Neg logit contributions | |
enhagen | -1.351 |
ighthouse | -1.192 |
�� | -1.151 |
inately | -1.143 |
ighth | -1.141 |
Token | sectarian |
Token ID | 28005 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
Promotion | +0.136 |
Sao | +0.127 |
Chair | +0.126 |
tolerance | +0.126 |
TABLE | +0.125 |
Neg logit contributions | |
enhagen | -0.215 |
ighthouse | -0.192 |
�� | -0.186 |
ighth | -0.185 |
inately | -0.184 |
Token | medicine |
Token ID | 9007 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
enhagen | +0.359 |
ighthouse | +0.319 |
ighth | +0.309 |
�� | +0.308 |
inately | +0.306 |
Neg logit contributions | |
Promotion | -0.233 |
Chair | -0.218 |
Sao | -0.217 |
TABLE | -0.215 |
tolerance | -0.214 |
Token | Gu |
Token ID | 1962 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Promotion | +0.371 |
tolerance | +0.352 |
Chair | +0.344 |
Sao | +0.344 |
Mania | +0.343 |
Neg logit contributions | |
enhagen | -0.521 |
ighthouse | -0.462 |
�� | -0.446 |
inately | -0.442 |
ighth | -0.441 |
Token | ac |
Token ID | 330 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Promotion | +1.345 |
tolerance | +1.267 |
Sao | +1.248 |
Chair | +1.248 |
TABLE | +1.233 |
Neg logit contributions | |
enhagen | -2.041 |
ighthouse | -1.813 |
�� | -1.749 |
ighth | -1.739 |
inately | -1.738 |
Token | ame |
Token ID | 480 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
enhagen | +2.693 |
ighthouse | +2.444 |
ighth | +2.325 |
�� | +2.320 |
achus | +2.299 |
Neg logit contributions | |
Promotion | -1.567 |
tolerance | -1.472 |
TABLE | -1.456 |
Chair | -1.437 |
Sao | -1.431 |
Token | lee |
Token ID | 7197 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Promotion | +0.285 |
tolerance | +0.272 |
Chair | +0.270 |
Sao | +0.269 |
Mania | +0.267 |
Neg logit contributions | |
enhagen | -0.241 |
ighthouse | -0.204 |
�� | -0.197 |
inately | -0.194 |
ighth | -0.193 |
Token | developer |
Token ID | 8517 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
enhagen | +0.494 |
ighthouse | +0.439 |
�� | +0.417 |
inately | +0.415 |
ighth | +0.414 |
Neg logit contributions | |
Promotion | -0.412 |
tolerance | -0.395 |
Sao | -0.387 |
TABLE | -0.387 |
Chair | -0.385 |
Token | Drink |
Token ID | 32906 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
enhagen | +0.133 |
ighthouse | +0.118 |
�� | +0.114 |
inately | +0.113 |
ighth | +0.112 |
Neg logit contributions | |
Promotion | -0.095 |
tolerance | -0.090 |
Sao | -0.088 |
Chair | -0.088 |
TABLE | -0.088 |
Token | Box |
Token ID | 14253 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Promotion | +4.360 |
Mania | +4.064 |
Chair | +4.055 |
tolerance | +4.036 |
Sao | +3.990 |
Neg logit contributions | |
enhagen | -5.571 |
ighthouse | -4.773 |
�� | -4.677 |
inately | -4.661 |
ighth | -4.577 |
Token | Studios |
Token ID | 13799 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Promotion | +0.853 |
tolerance | +0.807 |
Chair | +0.796 |
Sao | +0.796 |
TABLE | +0.787 |
Neg logit contributions | |
enhagen | -1.129 |
ighthouse | -0.994 |
�� | -0.960 |
inately | -0.952 |
ighth | -0.950 |
Token | . |
Token ID | 13 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Promotion | +1.190 |
tolerance | +1.126 |
Chair | +1.116 |
Sao | +1.114 |
TABLE | +1.100 |
Neg logit contributions | |
enhagen | -1.416 |
ighthouse | -1.237 |
�� | -1.194 |
inately | -1.182 |
ighth | -1.181 |
Token | And |
Token ID | 843 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
enhagen | +0.380 |
ighthouse | +0.337 |
�� | +0.324 |
ighth | +0.320 |
inately | +0.320 |
Neg logit contributions | |
Promotion | -0.294 |
tolerance | -0.283 |
Sao | -0.276 |
Chair | -0.273 |
TABLE | -0.273 |
Token | that |
Token ID | 326 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Promotion | +1.318 |
tolerance | +1.248 |
Chair | +1.233 |
Sao | +1.232 |
TABLE | +1.217 |
Neg logit contributions | |
enhagen | -1.709 |
ighthouse | -1.501 |
�� | -1.449 |
inately | -1.436 |
ighth | -1.435 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
enhagen | +0.744 |
ighthouse | +0.652 |
�� | +0.636 |
inately | +0.624 |
ighth | +0.622 |
Neg logit contributions | |
Promotion | -0.597 |
Mania | -0.563 |
tolerance | -0.562 |
Sao | -0.559 |
Chair | -0.558 |
Token | pot |
Token ID | 1787 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
enhagen | +1.095 |
ighthouse | +0.963 |
�� | +0.938 |
inately | +0.928 |
ighth | +0.925 |
Neg logit contributions | |
Promotion | -0.838 |
Mania | -0.789 |
tolerance | -0.789 |
Chair | -0.786 |
Sao | -0.785 |
Token | - |
Token ID | 12 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
enhagen | +0.262 |
ighthouse | +0.228 |
�� | +0.219 |
inately | +0.217 |
ighth | +0.217 |
Neg logit contributions | |
Promotion | -0.233 |
tolerance | -0.221 |
Sao | -0.220 |
Chair | -0.219 |
Mania | -0.217 |
Token | add |
Token ID | 2860 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Promotion | +0.408 |
tolerance | +0.381 |
Chair | +0.375 |
Sao | +0.374 |
TABLE | +0.369 |
Neg logit contributions | |
enhagen | -0.747 |
ighthouse | -0.669 |
�� | -0.649 |
inately | -0.644 |
ighth | -0.643 |
Token | led |
Token ID | 992 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Promotion | +0.094 |
tolerance | +0.090 |
Sao | +0.090 |
Chair | +0.089 |
TABLE | +0.088 |
Neg logit contributions | |
enhagen | -0.084 |
ighthouse | -0.071 |
inately | -0.068 |
�� | -0.067 |
ighth | -0.067 |
Token | Ober |
Token ID | 33753 |
Feature activation | -8.38e+00 |
Pos logit contributions | |
Promotion | +1.330 |
tolerance | +1.259 |
Chair | +1.242 |
Sao | +1.241 |
TABLE | +1.224 |
Neg logit contributions | |
enhagen | -1.799 |
ighthouse | -1.586 |
�� | -1.532 |
inately | -1.519 |
ighth | -1.516 |
Token | lin |
Token ID | 2815 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
enhagen | +4.933 |
ighthouse | +4.318 |
ighth | +4.131 |
achus | +3.931 |
inately | +3.918 |
Neg logit contributions | |
Promotion | -6.665 |
tolerance | -6.375 |
TABLE | -6.332 |
Procedure | -6.227 |
Sao | -6.198 |
Token | College |
Token ID | 5535 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
enhagen | +3.323 |
ighthouse | +2.925 |
�� | +2.837 |
ighth | +2.814 |
achus | +2.796 |
Neg logit contributions | |
Promotion | -2.604 |
Sao | -2.454 |
tolerance | -2.441 |
Mania | -2.433 |
TABLE | -2.419 |
Token | freshman |
Token ID | 18621 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
enhagen | +1.130 |
ighthouse | +0.998 |
�� | +0.968 |
ighth | +0.961 |
inately | +0.954 |
Neg logit contributions | |
Promotion | -0.851 |
tolerance | -0.798 |
Sao | -0.797 |
Mania | -0.794 |
TABLE | -0.791 |
Token | 's |
Token ID | 338 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
enhagen | +2.435 |
ighthouse | +2.141 |
inately | +2.074 |
ighth | +2.043 |
�� | +2.035 |
Neg logit contributions | |
Promotion | -1.877 |
TABLE | -1.752 |
Sao | -1.745 |
tolerance | -1.740 |
Mania | -1.739 |
Token | — |
Token ID | 851 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
enhagen | +0.131 |
ighthouse | +0.116 |
�� | +0.112 |
inately | +0.111 |
ighth | +0.111 |
Neg logit contributions | |
Promotion | -0.094 |
tolerance | -0.088 |
Sao | -0.087 |
Chair | -0.087 |
Mania | -0.086 |
Token | March |
Token ID | 2805 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Promotion | +0.238 |
tolerance | +0.223 |
Chair | +0.220 |
Sao | +0.219 |
TABLE | +0.217 |
Neg logit contributions | |
enhagen | -0.377 |
ighthouse | -0.335 |
�� | -0.324 |
inately | -0.322 |
ighth | -0.322 |
Token | 2 |
Token ID | 362 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Promotion | +0.259 |
tolerance | +0.236 |
Chair | +0.234 |
Sao | +0.233 |
TABLE | +0.228 |
Neg logit contributions | |
enhagen | -0.648 |
ighthouse | -0.586 |
�� | -0.573 |
inately | -0.567 |
ighth | -0.565 |
Token | , |
Token ID | 11 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
enhagen | +0.472 |
ighthouse | +0.414 |
�� | +0.399 |
ighth | +0.396 |
inately | +0.395 |
Neg logit contributions | |
Promotion | -0.372 |
tolerance | -0.352 |
Chair | -0.347 |
Sao | -0.347 |
TABLE | -0.344 |
Token | a |
Token ID | 257 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
enhagen | +0.533 |
ighthouse | +0.469 |
inately | +0.451 |
�� | +0.450 |
ighth | +0.449 |
Neg logit contributions | |
Promotion | -0.405 |
tolerance | -0.382 |
Sao | -0.376 |
Chair | -0.376 |
Mania | -0.375 |
Token | Kurdish |
Token ID | 14845 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
enhagen | +0.044 |
ighthouse | +0.039 |
�� | +0.037 |
inately | +0.037 |
ighth | +0.037 |
Neg logit contributions | |
Promotion | -0.034 |
tolerance | -0.032 |
Chair | -0.032 |
Sao | -0.032 |
Mania | -0.031 |
Token | infiltr |
Token ID | 21086 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
enhagen | +1.356 |
ighthouse | +1.186 |
�� | +1.135 |
ighth | +1.131 |
inately | +1.129 |
Neg logit contributions | |
Promotion | -1.113 |
tolerance | -1.051 |
Mania | -1.045 |
Sao | -1.043 |
TABLE | -1.040 |
Token | ator |
Token ID | 1352 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
enhagen | +2.727 |
ighthouse | +2.220 |
ighth | +2.047 |
inately | +1.874 |
achus | +1.736 |
Neg logit contributions | |
Promotion | -8.634 |
tolerance | -8.475 |
Mania | -8.415 |
Sao | -8.285 |
Chair | -8.277 |
Token | from |
Token ID | 422 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
enhagen | +2.221 |
ighthouse | +1.946 |
inately | +1.859 |
ighth | +1.841 |
�� | +1.817 |
Neg logit contributions | |
Promotion | -1.872 |
tolerance | -1.767 |
Mania | -1.758 |
Chair | -1.750 |
TABLE | -1.746 |
Token | Syria |
Token ID | 4392 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Promotion | +0.781 |
tolerance | +0.739 |
Chair | +0.730 |
Sao | +0.729 |
TABLE | +0.722 |
Neg logit contributions | |
enhagen | -1.015 |
ighthouse | -0.893 |
�� | -0.861 |
inately | -0.855 |
ighth | -0.853 |
Token | carrying |
Token ID | 6872 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
enhagen | +0.851 |
ighthouse | +0.748 |
�� | +0.717 |
inately | +0.715 |
ighth | +0.713 |
Neg logit contributions | |
Promotion | -0.658 |
tolerance | -0.624 |
Chair | -0.616 |
Sao | -0.615 |
TABLE | -0.609 |
Token | bin |
Token ID | 9874 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
enhagen | +1.508 |
ighthouse | +1.324 |
inately | +1.275 |
�� | +1.272 |
ighth | +1.264 |
Neg logit contributions | |
Promotion | -1.196 |
tolerance | -1.126 |
Sao | -1.117 |
Mania | -1.117 |
Chair | -1.114 |
Token | Three |
Token ID | 12510 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Promotion | +0.252 |
tolerance | +0.238 |
Sao | +0.237 |
Chair | +0.234 |
TABLE | +0.232 |
Neg logit contributions | |
enhagen | -0.337 |
ighthouse | -0.299 |
ighth | -0.287 |
�� | -0.287 |
inately | -0.285 |
Token | months |
Token ID | 1933 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
enhagen | +1.456 |
ighthouse | +1.282 |
ighth | +1.235 |
�� | +1.228 |
inately | +1.223 |
Neg logit contributions | |
Promotion | -1.218 |
Mania | -1.131 |
Sao | -1.128 |
tolerance | -1.125 |
Chair | -1.121 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
enhagen | +1.616 |
ighthouse | +1.419 |
ighth | +1.367 |
�� | +1.361 |
inately | +1.356 |
Neg logit contributions | |
Promotion | -1.252 |
tolerance | -1.177 |
Sao | -1.168 |
Chair | -1.164 |
Mania | -1.149 |
Token | students |
Token ID | 2444 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
enhagen | +0.516 |
ighthouse | +0.452 |
�� | +0.434 |
inately | +0.432 |
ighth | +0.432 |
Neg logit contributions | |
Promotion | -0.413 |
tolerance | -0.386 |
Sao | -0.385 |
Mania | -0.383 |
TABLE | -0.382 |
Token | at |
Token ID | 379 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
enhagen | +0.072 |
ighthouse | +0.064 |
�� | +0.061 |
inately | +0.061 |
ighth | +0.061 |
Neg logit contributions | |
Promotion | -0.057 |
tolerance | -0.053 |
Chair | -0.053 |
Sao | -0.053 |
Mania | -0.052 |
Token | Ober |
Token ID | 33753 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
Promotion | +0.433 |
tolerance | +0.409 |
Chair | +0.403 |
Sao | +0.402 |
Mania | +0.402 |
Neg logit contributions | |
enhagen | -0.567 |
ighthouse | -0.499 |
�� | -0.480 |
ighth | -0.477 |
inately | -0.477 |
Token | lin |
Token ID | 2815 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
enhagen | +4.102 |
ighthouse | +3.296 |
ighth | +2.974 |
achus | +2.969 |
inately | +2.903 |
Neg logit contributions | |
Promotion | -7.592 |
tolerance | -7.356 |
TABLE | -7.318 |
Chair | -7.233 |
Procedure | -7.199 |
Token | College |
Token ID | 5535 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
enhagen | +2.355 |
ighthouse | +2.007 |
�� | +1.907 |
achus | +1.896 |
ighth | +1.887 |
Neg logit contributions | |
Promotion | -2.406 |
tolerance | -2.282 |
Sao | -2.250 |
Mania | -2.249 |
Chair | -2.244 |
Token | in |
Token ID | 287 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
enhagen | +0.615 |
ighthouse | +0.540 |
�� | +0.519 |
inately | +0.517 |
ighth | +0.516 |
Neg logit contributions | |
Promotion | -0.450 |
tolerance | -0.421 |
Chair | -0.416 |
Sao | -0.416 |
Mania | -0.415 |
Token | Ohio |
Token ID | 6835 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Promotion | +0.568 |
tolerance | +0.543 |
Chair | +0.538 |
Sao | +0.538 |
TABLE | +0.531 |
Neg logit contributions | |
enhagen | -0.503 |
ighthouse | -0.431 |
�� | -0.413 |
inately | -0.407 |
ighth | -0.407 |
Token | objected |
Token ID | 29811 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
enhagen | +1.299 |
ighthouse | +1.136 |
ighth | +1.088 |
�� | +1.085 |
inately | +1.085 |
Neg logit contributions | |
Promotion | -0.993 |
tolerance | -0.926 |
Sao | -0.920 |
Chair | -0.916 |
TABLE | -0.912 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
enhagen | +0.960 |
ighthouse | +0.863 |
ighth | +0.814 |
�� | +0.802 |
inately | +0.802 |
Neg logit contributions | |
Promotion | -0.953 |
tolerance | -0.911 |
Chair | -0.898 |
Sao | -0.897 |
TABLE | -0.896 |
Token | A |
Token ID | 32 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
enhagen | +1.365 |
ighthouse | +1.226 |
�� | +1.173 |
ighth | +1.170 |
inately | +1.167 |
Neg logit contributions | |
Promotion | -0.851 |
tolerance | -0.797 |
Chair | -0.785 |
Sao | -0.783 |
TABLE | -0.774 |
Token | . |
Token ID | 13 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
enhagen | +0.645 |
ighthouse | +0.559 |
�� | +0.537 |
inately | +0.533 |
ighth | +0.533 |
Neg logit contributions | |
Promotion | -0.599 |
tolerance | -0.569 |
Sao | -0.563 |
Chair | -0.563 |
TABLE | -0.557 |
Token | home |
Token ID | 1363 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
enhagen | +0.474 |
ighthouse | +0.420 |
ighth | +0.403 |
inately | +0.403 |
�� | +0.402 |
Neg logit contributions | |
Promotion | -0.299 |
tolerance | -0.280 |
Chair | -0.276 |
Sao | -0.275 |
TABLE | -0.273 |
Token | — |
Token ID | 960 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
enhagen | +1.322 |
ighthouse | +1.156 |
inately | +1.113 |
ighth | +1.112 |
�� | +1.109 |
Neg logit contributions | |
Promotion | -1.098 |
tolerance | -1.038 |
Sao | -1.032 |
Chair | -1.029 |
TABLE | -1.021 |
Token | transforming |
Token ID | 25449 |
Feature activation | -8.21e+00 |
Pos logit contributions | |
enhagen | +0.317 |
ighthouse | +0.275 |
�� | +0.263 |
ighth | +0.262 |
inately | +0.262 |
Neg logit contributions | |
Promotion | -0.299 |
tolerance | -0.285 |
Sao | -0.282 |
Chair | -0.281 |
TABLE | -0.279 |
Token | their |
Token ID | 511 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
enhagen | +5.868 |
ighthouse | +5.198 |
inately | +5.030 |
�� | +5.008 |
ighth | +4.878 |
Neg logit contributions | |
Promotion | -5.306 |
Mania | -5.016 |
TABLE | -4.949 |
tolerance | -4.938 |
Sao | -4.930 |
Token | image |
Token ID | 2939 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
enhagen | +0.626 |
ighthouse | +0.551 |
�� | +0.534 |
inately | +0.531 |
ighth | +0.528 |
Neg logit contributions | |
Promotion | -0.468 |
tolerance | -0.440 |
Chair | -0.437 |
Sao | -0.436 |
Mania | -0.434 |
Token | and |
Token ID | 290 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
enhagen | +2.384 |
ighthouse | +2.096 |
inately | +2.012 |
ighth | +1.996 |
�� | +1.989 |
Neg logit contributions | |
Promotion | -2.057 |
Chair | -1.922 |
tolerance | -1.919 |
Sao | -1.918 |
TABLE | -1.904 |
Token | expectations |
Token ID | 9027 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
enhagen | +0.550 |
ighthouse | +0.482 |
�� | +0.465 |
inately | +0.463 |
ighth | +0.461 |
Neg logit contributions | |
Promotion | -0.443 |
Sao | -0.417 |
tolerance | -0.417 |
Chair | -0.416 |
TABLE | -0.413 |
Token | in |
Token ID | 287 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
enhagen | +0.255 |
ighthouse | +0.223 |
�� | +0.214 |
inately | +0.213 |
ighth | +0.213 |
Neg logit contributions | |
Promotion | -0.212 |
tolerance | -0.200 |
Sao | -0.198 |
Chair | -0.198 |
TABLE | -0.196 |
Token | especially |
Token ID | 2592 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
enhagen | +0.627 |
ighthouse | +0.547 |
�� | +0.523 |
inately | +0.521 |
ighth | +0.521 |
Neg logit contributions | |
Promotion | -0.582 |
tolerance | -0.552 |
Sao | -0.548 |
Chair | -0.546 |
TABLE | -0.545 |
Token | since |
Token ID | 1201 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
enhagen | +2.491 |
ighthouse | +2.198 |
inately | +2.109 |
ighth | +2.094 |
�� | +2.059 |
Neg logit contributions | |
Promotion | -2.213 |
Mania | -2.090 |
tolerance | -2.083 |
Sao | -2.082 |
TABLE | -2.070 |
Token | Rep |
Token ID | 1432 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
enhagen | +0.867 |
ighthouse | +0.763 |
inately | +0.733 |
�� | +0.733 |
ighth | +0.732 |
Neg logit contributions | |
Promotion | -0.702 |
tolerance | -0.658 |
Mania | -0.655 |
Sao | -0.654 |
TABLE | -0.649 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
enhagen | +2.107 |
ighthouse | +1.828 |
�� | +1.749 |
inately | +1.743 |
ighth | +1.742 |
Neg logit contributions | |
Promotion | -1.886 |
tolerance | -1.795 |
Sao | -1.769 |
Chair | -1.761 |
TABLE | -1.756 |
Token | Tom |
Token ID | 4186 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
enhagen | +1.109 |
ighthouse | +0.973 |
ighth | +0.929 |
�� | +0.928 |
inately | +0.928 |
Neg logit contributions | |
Promotion | -0.885 |
tolerance | -0.847 |
Sao | -0.825 |
TABLE | -0.822 |
Chair | -0.820 |
Token | MacArthur |
Token ID | 46626 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
enhagen | +0.387 |
ighthouse | +0.317 |
�� | +0.302 |
inately | +0.297 |
ighth | +0.296 |
Neg logit contributions | |
Promotion | -0.622 |
tolerance | -0.597 |
Chair | -0.594 |
Sao | -0.593 |
TABLE | -0.588 |
Token | of |
Token ID | 286 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
enhagen | +5.941 |
ighthouse | +5.020 |
ighth | +4.838 |
achus | +4.784 |
inately | +4.778 |
Neg logit contributions | |
Promotion | -5.324 |
tolerance | -5.054 |
Sao | -4.952 |
Mania | -4.926 |
TABLE | -4.871 |
Token | New |
Token ID | 968 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
enhagen | +0.372 |
ighthouse | +0.323 |
ighth | +0.309 |
inately | +0.307 |
�� | +0.306 |
Neg logit contributions | |
Promotion | -0.350 |
tolerance | -0.337 |
Mania | -0.331 |
TABLE | -0.329 |
_______ | -0.327 |
Token | Jersey |
Token ID | 8221 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Promotion | +0.118 |
tolerance | +0.111 |
Chair | +0.109 |
Sao | +0.109 |
TABLE | +0.108 |
Neg logit contributions | |
enhagen | -0.187 |
ighthouse | -0.167 |
�� | -0.161 |
inately | -0.160 |
ighth | -0.160 |
Token | authored |
Token ID | 33941 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
Promotion | +0.309 |
tolerance | +0.291 |
Chair | +0.288 |
Sao | +0.287 |
TABLE | +0.284 |
Neg logit contributions | |
enhagen | -0.428 |
ighthouse | -0.378 |
�� | -0.366 |
inately | -0.363 |
ighth | -0.362 |
Token | an |
Token ID | 281 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
enhagen | +0.417 |
ighthouse | +0.366 |
�� | +0.352 |
ighth | +0.352 |
inately | +0.352 |
Neg logit contributions | |
Promotion | -0.322 |
tolerance | -0.305 |
Sao | -0.302 |
Mania | -0.302 |
Chair | -0.299 |
Token | in |
Token ID | 287 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
enhagen | +1.626 |
ighthouse | +1.425 |
ighth | +1.367 |
inately | +1.360 |
�� | +1.360 |
Neg logit contributions | |
Promotion | -1.325 |
tolerance | -1.234 |
Chair | -1.229 |
Sao | -1.223 |
TABLE | -1.221 |
Token | their |
Token ID | 511 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
enhagen | +0.780 |
ighthouse | +0.684 |
�� | +0.662 |
ighth | +0.656 |
inately | +0.655 |
Neg logit contributions | |
Promotion | -0.590 |
tolerance | -0.552 |
Chair | -0.550 |
Sao | -0.547 |
TABLE | -0.546 |
Token | life |
Token ID | 1204 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
Promotion | +0.691 |
tolerance | +0.647 |
Chair | +0.640 |
Sao | +0.640 |
TABLE | +0.632 |
Neg logit contributions | |
enhagen | -1.084 |
ighthouse | -0.963 |
�� | -0.933 |
inately | -0.926 |
ighth | -0.925 |
Token | from |
Token ID | 422 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Promotion | +0.468 |
tolerance | +0.441 |
Chair | +0.437 |
Sao | +0.437 |
TABLE | +0.433 |
Neg logit contributions | |
enhagen | -0.588 |
ighthouse | -0.516 |
�� | -0.496 |
inately | -0.493 |
ighth | -0.493 |
Token | the |
Token ID | 262 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Promotion | +0.758 |
tolerance | +0.717 |
Chair | +0.709 |
Sao | +0.707 |
TABLE | +0.701 |
Neg logit contributions | |
enhagen | -0.961 |
ighthouse | -0.844 |
�� | -0.815 |
inately | -0.808 |
ighth | -0.806 |
Token | polar |
Token ID | 13559 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
enhagen | +0.488 |
ighthouse | +0.428 |
�� | +0.415 |
ighth | +0.411 |
inately | +0.410 |
Neg logit contributions | |
Promotion | -0.382 |
tolerance | -0.360 |
Sao | -0.357 |
Chair | -0.357 |
Mania | -0.353 |
Token | opposite |
Token ID | 6697 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
enhagen | +5.308 |
ighthouse | +4.804 |
ighth | +4.518 |
�� | +4.486 |
achus | +4.274 |
Neg logit contributions | |
Promotion | -5.562 |
Sao | -5.215 |
Chair | -5.158 |
Mania | -5.157 |
TABLE | -5.089 |
Token | vantage |
Token ID | 47929 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Promotion | +0.820 |
tolerance | +0.768 |
Chair | +0.759 |
Sao | +0.758 |
TABLE | +0.750 |
Neg logit contributions | |
enhagen | -1.268 |
ighthouse | -1.129 |
�� | -1.091 |
inately | -1.082 |
ighth | -1.081 |
Token | point |
Token ID | 966 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
enhagen | +1.919 |
ighthouse | +1.717 |
�� | +1.631 |
ighth | +1.625 |
inately | +1.588 |
Neg logit contributions | |
Promotion | -1.590 |
Sao | -1.477 |
tolerance | -1.474 |
Chair | -1.454 |
Mania | -1.454 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
enhagen | +0.789 |
ighthouse | +0.691 |
�� | +0.659 |
ighth | +0.654 |
inately | +0.654 |
Neg logit contributions | |
Promotion | -0.702 |
tolerance | -0.661 |
Sao | -0.656 |
Chair | -0.655 |
TABLE | -0.649 |
Token | For |
Token ID | 1114 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
enhagen | +0.160 |
ighthouse | +0.144 |
ighth | +0.138 |
�� | +0.137 |
inately | +0.136 |
Neg logit contributions | |
Promotion | -0.114 |
tolerance | -0.110 |
Sao | -0.106 |
Chair | -0.106 |
Mania | -0.106 |
Token | SA |
Token ID | 4090 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Promotion | +0.143 |
tolerance | +0.134 |
Chair | +0.131 |
Sao | +0.131 |
Mania | +0.129 |
Neg logit contributions | |
enhagen | -0.263 |
ighthouse | -0.235 |
inately | -0.227 |
ighth | -0.226 |
�� | -0.226 |
Token | will |
Token ID | 481 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Promotion | +0.636 |
tolerance | +0.599 |
Sao | +0.593 |
Chair | +0.590 |
TABLE | +0.584 |
Neg logit contributions | |
enhagen | -0.940 |
ighthouse | -0.833 |
�� | -0.802 |
inately | -0.801 |
ighth | -0.799 |
Token | : |
Token ID | 25 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
Promotion | +0.083 |
tolerance | +0.079 |
Sao | +0.078 |
Chair | +0.078 |
TABLE | +0.077 |
Neg logit contributions | |
enhagen | -0.090 |
ighthouse | -0.078 |
inately | -0.075 |
�� | -0.074 |
ighth | -0.074 |
Token | Most |
Token ID | 4042 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
enhagen | +0.324 |
ighthouse | +0.288 |
inately | +0.278 |
�� | +0.277 |
ighth | +0.276 |
Neg logit contributions | |
Promotion | -0.209 |
tolerance | -0.197 |
Sao | -0.195 |
Chair | -0.194 |
Mania | -0.193 |
Token | Un |
Token ID | 791 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
enhagen | +1.565 |
ighthouse | +1.361 |
�� | +1.307 |
inately | +1.307 |
ighth | +1.295 |
Neg logit contributions | |
Promotion | -1.418 |
tolerance | -1.349 |
Sao | -1.345 |
Chair | -1.334 |
Mania | -1.330 |
Token | sett |
Token ID | 17744 |
Feature activation | -7.82e+00 |
Pos logit contributions | |
enhagen | +1.766 |
ighthouse | +1.549 |
inately | +1.498 |
ighth | +1.491 |
�� | +1.468 |
Neg logit contributions | |
Promotion | -1.555 |
tolerance | -1.498 |
Sao | -1.488 |
Chair | -1.477 |
TABLE | -1.463 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
enhagen | +4.129 |
ighthouse | +3.405 |
inately | +3.384 |
ighth | +3.272 |
�� | +3.192 |
Neg logit contributions | |
Promotion | -6.763 |
Sao | -6.506 |
TABLE | -6.439 |
tolerance | -6.438 |
Mania | -6.365 |
Token | Moment |
Token ID | 29278 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
enhagen | +1.751 |
ighthouse | +1.553 |
inately | +1.499 |
�� | +1.490 |
ighth | +1.471 |
Neg logit contributions | |
Promotion | -1.330 |
tolerance | -1.290 |
Mania | -1.256 |
Sao | -1.255 |
Chair | -1.246 |
Token | : |
Token ID | 25 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Promotion | +0.730 |
tolerance | +0.690 |
Chair | +0.680 |
Sao | +0.680 |
TABLE | +0.673 |
Neg logit contributions | |
enhagen | -1.020 |
ighthouse | -0.902 |
�� | -0.871 |
inately | -0.865 |
ighth | -0.863 |
Token | No |
Token ID | 1400 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
enhagen | +0.179 |
ighthouse | +0.159 |
�� | +0.153 |
inately | +0.153 |
ighth | +0.152 |
Neg logit contributions | |
Promotion | -0.119 |
tolerance | -0.113 |
Sao | -0.111 |
Chair | -0.111 |
Mania | -0.110 |
Token | question |
Token ID | 1808 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
enhagen | +0.535 |
ighthouse | +0.473 |
�� | +0.458 |
ighth | +0.457 |
inately | +0.455 |
Neg logit contributions | |
Promotion | -0.367 |
Sao | -0.346 |
tolerance | -0.344 |
Chair | -0.342 |
Mania | -0.341 |
Token | Orth |
Token ID | 47664 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Promotion | +0.586 |
tolerance | +0.551 |
Chair | +0.543 |
Sao | +0.542 |
TABLE | +0.541 |
Neg logit contributions | |
enhagen | -0.819 |
ighthouse | -0.724 |
�� | -0.701 |
ighth | -0.695 |
inately | -0.694 |
Token | anc |
Token ID | 1192 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
enhagen | +0.211 |
ighthouse | +0.180 |
�� | +0.176 |
inately | +0.172 |
ighth | +0.169 |
Neg logit contributions | |
Promotion | -0.204 |
Chair | -0.195 |
Sao | -0.193 |
tolerance | -0.191 |
Mania | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
enhagen | +1.831 |
ighthouse | +1.608 |
ighth | +1.516 |
inately | +1.512 |
�� | +1.505 |
Neg logit contributions | |
Promotion | -1.693 |
tolerance | -1.623 |
Sao | -1.593 |
TABLE | -1.589 |
_______ | -1.579 |
Token | Gand |
Token ID | 17727 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
enhagen | +0.654 |
ighthouse | +0.587 |
ighth | +0.564 |
�� | +0.559 |
inately | +0.559 |
Neg logit contributions | |
Promotion | -0.426 |
tolerance | -0.415 |
Mania | -0.398 |
Chair | -0.394 |
Sao | -0.394 |
Token | alf |
Token ID | 1604 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Promotion | +0.270 |
tolerance | +0.256 |
Chair | +0.252 |
Sao | +0.251 |
Mania | +0.249 |
Neg logit contributions | |
enhagen | -0.366 |
ighthouse | -0.322 |
�� | -0.313 |
inately | -0.309 |
ighth | -0.308 |
Token | convin |
Token ID | 9120 |
Feature activation | -7.77e+00 |
Pos logit contributions | |
enhagen | +0.883 |
ighthouse | +0.774 |
inately | +0.737 |
ighth | +0.737 |
�� | +0.735 |
Neg logit contributions | |
Promotion | -0.769 |
tolerance | -0.724 |
Sao | -0.715 |
Chair | -0.715 |
Mania | -0.709 |
Token | ces |
Token ID | 728 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
enhagen | +4.621 |
ighthouse | +4.209 |
inately | +4.061 |
ighth | +4.000 |
achus | +3.995 |
Neg logit contributions | |
Promotion | -5.972 |
tolerance | -5.774 |
Sao | -5.643 |
TABLE | -5.619 |
Mania | -5.594 |
Token | Tree |
Token ID | 12200 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
enhagen | +3.419 |
ighthouse | +3.023 |
ighth | +2.907 |
inately | +2.897 |
�� | +2.853 |
Neg logit contributions | |
Promotion | -2.741 |
Mania | -2.630 |
tolerance | -2.589 |
_______ | -2.553 |
TABLE | -2.552 |
Token | beard |
Token ID | 39433 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
enhagen | +0.195 |
ighthouse | +0.147 |
�� | +0.134 |
inately | +0.132 |
ighth | +0.132 |
Neg logit contributions | |
Promotion | -0.508 |
tolerance | -0.491 |
Sao | -0.488 |
Chair | -0.487 |
TABLE | -0.485 |
Token | to |
Token ID | 284 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
enhagen | +1.242 |
ighthouse | +1.096 |
�� | +1.051 |
inately | +1.040 |
ighth | +1.040 |
Neg logit contributions | |
Promotion | -0.941 |
tolerance | -0.880 |
Chair | -0.870 |
Sao | -0.869 |
TABLE | -0.869 |
Token | send |
Token ID | 3758 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
Promotion | +0.113 |
tolerance | +0.106 |
Sao | +0.105 |
Chair | +0.105 |
Mania | +0.104 |
Neg logit contributions | |
enhagen | -0.144 |
ighthouse | -0.127 |
inately | -0.122 |
�� | -0.122 |
ighth | -0.122 |
Token | � |
Token ID | 250 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
enhagen | +0.190 |
ighthouse | +0.161 |
�� | +0.155 |
ighth | +0.152 |
inately | +0.151 |
Neg logit contributions | |
Promotion | -0.235 |
tolerance | -0.225 |
Sao | -0.224 |
Chair | -0.223 |
TABLE | -0.221 |
Token | People |
Token ID | 8061 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
enhagen | +0.474 |
ighthouse | +0.417 |
ighth | +0.400 |
�� | +0.400 |
inately | +0.397 |
Neg logit contributions | |
Promotion | -0.365 |
tolerance | -0.345 |
Sao | -0.343 |
Chair | -0.340 |
TABLE | -0.337 |
Token | have |
Token ID | 423 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
Promotion | +1.054 |
tolerance | +0.995 |
Sao | +0.985 |
Chair | +0.982 |
TABLE | +0.974 |
Neg logit contributions | |
enhagen | -1.376 |
ighthouse | -1.212 |
�� | -1.163 |
inately | -1.160 |
ighth | -1.155 |
Token | been |
Token ID | 587 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Promotion | +0.590 |
tolerance | +0.554 |
Chair | +0.551 |
Sao | +0.551 |
Mania | +0.546 |
Neg logit contributions | |
enhagen | -0.729 |
ighthouse | -0.638 |
�� | -0.613 |
inately | -0.611 |
ighth | -0.609 |
Token | politically |
Token ID | 11889 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
enhagen | +0.197 |
ighthouse | +0.174 |
inately | +0.166 |
ighth | +0.166 |
�� | +0.165 |
Neg logit contributions | |
Promotion | -0.152 |
tolerance | -0.141 |
Mania | -0.141 |
Sao | -0.140 |
TABLE | -0.139 |
Token | traumat |
Token ID | 38510 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
enhagen | +0.121 |
ighthouse | +0.106 |
�� | +0.101 |
ighth | +0.101 |
inately | +0.101 |
Neg logit contributions | |
Promotion | -0.113 |
Sao | -0.106 |
tolerance | -0.106 |
Chair | -0.106 |
Mania | -0.105 |
Token | ized |
Token ID | 1143 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
enhagen | +2.424 |
ighthouse | +1.986 |
inately | +1.762 |
ighth | +1.737 |
�� | +1.661 |
Neg logit contributions | |
Promotion | -7.757 |
Sao | -7.404 |
Chair | -7.349 |
tolerance | -7.312 |
TABLE | -7.300 |
Token | , |
Token ID | 11 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
enhagen | +3.088 |
ighthouse | +2.724 |
inately | +2.607 |
�� | +2.592 |
ighth | +2.584 |
Neg logit contributions | |
Promotion | -2.429 |
Sao | -2.263 |
Chair | -2.237 |
tolerance | -2.235 |
TABLE | -2.223 |
Token | � |
Token ID | 447 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
enhagen | +0.506 |
ighthouse | +0.445 |
�� | +0.426 |
ighth | +0.423 |
inately | +0.423 |
Neg logit contributions | |
Promotion | -0.427 |
tolerance | -0.402 |
Sao | -0.399 |
Chair | -0.398 |
TABLE | -0.396 |
Token | � |
Token ID | 251 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
enhagen | +0.350 |
ighthouse | +0.298 |
�� | +0.285 |
ighth | +0.280 |
inately | +0.280 |
Neg logit contributions | |
Promotion | -0.443 |
tolerance | -0.424 |
Sao | -0.420 |
Chair | -0.419 |
TABLE | -0.417 |
Token | Stein |
Token ID | 15215 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
enhagen | +0.610 |
ighthouse | +0.531 |
�� | +0.506 |
inately | +0.504 |
ighth | +0.504 |
Neg logit contributions | |
Promotion | -0.559 |
tolerance | -0.530 |
Sao | -0.527 |
Chair | -0.523 |
Mania | -0.522 |
Token | Climate |
Token ID | 13963 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
enhagen | +1.228 |
ighthouse | +1.083 |
inately | +1.043 |
ighth | +1.037 |
�� | +1.035 |
Neg logit contributions | |
Promotion | -0.915 |
tolerance | -0.885 |
Mania | -0.872 |
Sao | -0.871 |
TABLE | -0.856 |
Token | and |
Token ID | 290 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
enhagen | +0.886 |
ighthouse | +0.778 |
ighth | +0.742 |
inately | +0.741 |
�� | +0.737 |
Neg logit contributions | |
Promotion | -0.706 |
tolerance | -0.679 |
Sao | -0.673 |
TABLE | -0.669 |
Mania | -0.668 |
Token | War |
Token ID | 1810 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
enhagen | +0.645 |
ighthouse | +0.573 |
ighth | +0.553 |
inately | +0.553 |
�� | +0.551 |
Neg logit contributions | |
Promotion | -0.461 |
tolerance | -0.444 |
Mania | -0.435 |
Sao | -0.434 |
Chair | -0.432 |
Token | published |
Token ID | 3199 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
enhagen | +1.108 |
ighthouse | +0.965 |
�� | +0.925 |
inately | +0.923 |
ighth | +0.920 |
Neg logit contributions | |
Promotion | -0.917 |
tolerance | -0.878 |
Sao | -0.870 |
Chair | -0.864 |
TABLE | -0.861 |
Token | by |
Token ID | 416 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Promotion | +0.187 |
tolerance | +0.176 |
Sao | +0.174 |
Chair | +0.173 |
TABLE | +0.172 |
Neg logit contributions | |
enhagen | -0.281 |
ighthouse | -0.250 |
�� | -0.241 |
inately | -0.240 |
ighth | -0.239 |
Token | Pluto |
Token ID | 32217 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
Promotion | +0.954 |
tolerance | +0.908 |
Sao | +0.891 |
Chair | +0.891 |
TABLE | +0.886 |
Neg logit contributions | |
enhagen | -1.208 |
ighthouse | -1.061 |
�� | -1.024 |
inately | -1.015 |
ighth | -1.012 |
Token | Press |
Token ID | 4332 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
enhagen | +5.415 |
ighthouse | +4.894 |
ighth | +4.642 |
inately | +4.524 |
Fresh | +4.519 |
Neg logit contributions | |
tolerance | -4.374 |
Promotion | -4.270 |
Sao | -4.212 |
Mania | -4.141 |
TABLE | -4.124 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
enhagen | +0.189 |
ighthouse | +0.165 |
�� | +0.158 |
ighth | +0.158 |
inately | +0.157 |
Neg logit contributions | |
Promotion | -0.157 |
tolerance | -0.150 |
Sao | -0.148 |
Chair | -0.147 |
TABLE | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
enhagen | +1.213 |
ighthouse | +1.062 |
ighth | +1.022 |
�� | +1.010 |
inately | +1.008 |
Neg logit contributions | |
Promotion | -0.912 |
tolerance | -0.883 |
Sao | -0.861 |
Mania | -0.859 |
TABLE | -0.847 |
Token |
|
Token ID | 198 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
enhagen | +0.808 |
ighthouse | +0.719 |
ighth | +0.685 |
inately | +0.682 |
�� | +0.676 |
Neg logit contributions | |
Promotion | -0.690 |
tolerance | -0.656 |
Sao | -0.648 |
Chair | -0.642 |
TABLE | -0.641 |
Token | A |
Token ID | 32 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
enhagen | +0.439 |
ighthouse | +0.388 |
ighth | +0.376 |
inately | +0.372 |
�� | +0.370 |
Neg logit contributions | |
Promotion | -0.318 |
Sao | -0.301 |
tolerance | -0.300 |
Chair | -0.294 |
TABLE | -0.293 |
Token | in |
Token ID | 287 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
Promotion | +0.469 |
tolerance | +0.440 |
Chair | +0.434 |
Sao | +0.434 |
TABLE | +0.429 |
Neg logit contributions | |
enhagen | -0.735 |
ighthouse | -0.654 |
�� | -0.632 |
inately | -0.628 |
ighth | -0.627 |
Token | public |
Token ID | 1171 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
enhagen | +0.681 |
ighthouse | +0.593 |
�� | +0.569 |
ighth | +0.567 |
inately | +0.566 |
Neg logit contributions | |
Promotion | -0.565 |
Mania | -0.531 |
Sao | -0.531 |
Chair | -0.530 |
tolerance | -0.528 |
Token | forums |
Token ID | 14216 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Promotion | +0.565 |
tolerance | +0.525 |
Chair | +0.522 |
Sao | +0.522 |
TABLE | +0.517 |
Neg logit contributions | |
enhagen | -0.949 |
ighthouse | -0.847 |
�� | -0.816 |
ighth | -0.814 |
inately | -0.813 |
Token | . |
Token ID | 13 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Promotion | +0.232 |
tolerance | +0.219 |
Sao | +0.217 |
Chair | +0.217 |
TABLE | +0.215 |
Neg logit contributions | |
enhagen | -0.296 |
ighthouse | -0.259 |
�� | -0.250 |
inately | -0.248 |
ighth | -0.248 |
Token | Says |
Token ID | 28628 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
enhagen | +0.406 |
ighthouse | +0.362 |
�� | +0.349 |
ighth | +0.347 |
inately | +0.346 |
Neg logit contributions | |
Promotion | -0.262 |
tolerance | -0.252 |
Sao | -0.246 |
Chair | -0.245 |
Mania | -0.244 |
Token | Neh |
Token ID | 44470 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
enhagen | +0.473 |
ighthouse | +0.393 |
�� | +0.372 |
inately | +0.370 |
ighth | +0.369 |
Neg logit contributions | |
Promotion | -0.678 |
tolerance | -0.650 |
Sao | -0.646 |
TABLE | -0.643 |
Mania | -0.642 |
Token | ring |
Token ID | 1806 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
enhagen | +4.699 |
ighthouse | +4.283 |
inately | +4.017 |
ighth | +3.945 |
achus | +3.923 |
Neg logit contributions | |
Promotion | -5.252 |
tolerance | -5.015 |
TABLE | -4.988 |
Sao | -4.974 |
Chair | -4.848 |
Token | , |
Token ID | 11 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
Promotion | +0.149 |
tolerance | +0.141 |
Sao | +0.139 |
Chair | +0.139 |
TABLE | +0.137 |
Neg logit contributions | |
enhagen | -0.212 |
ighthouse | -0.187 |
�� | -0.181 |
inately | -0.180 |
ighth | -0.179 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
enhagen | +0.750 |
ighthouse | +0.662 |
�� | +0.642 |
inately | +0.636 |
ighth | +0.634 |
Neg logit contributions | |
Promotion | -0.529 |
tolerance | -0.496 |
Sao | -0.494 |
Chair | -0.492 |
TABLE | -0.488 |
Token |
|
Token ID | 198 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
enhagen | +0.896 |
ighthouse | +0.796 |
ighth | +0.759 |
inately | +0.757 |
�� | +0.752 |
Neg logit contributions | |
Promotion | -0.753 |
tolerance | -0.715 |
Sao | -0.706 |
Chair | -0.701 |
TABLE | -0.697 |
Token | All |
Token ID | 3237 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
enhagen | +0.580 |
ighthouse | +0.515 |
�� | +0.497 |
ighth | +0.495 |
inately | +0.494 |
Neg logit contributions | |
Promotion | -0.426 |
Sao | -0.402 |
tolerance | -0.401 |
Chair | -0.398 |
TABLE | -0.394 |
Token | ener |
Token ID | 877 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Promotion | +0.073 |
tolerance | +0.069 |
Chair | +0.068 |
Sao | +0.068 |
TABLE | +0.067 |
Neg logit contributions | |
enhagen | -0.086 |
ighthouse | -0.077 |
ighth | -0.073 |
inately | -0.072 |
�� | -0.072 |
Token | ife |
Token ID | 901 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Promotion | +1.735 |
tolerance | +1.652 |
Chair | +1.634 |
Sao | +1.630 |
TABLE | +1.615 |
Neg logit contributions | |
enhagen | -1.821 |
ighthouse | -1.585 |
�� | -1.513 |
ighth | -1.506 |
inately | -1.505 |
Token | walking |
Token ID | 6155 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Promotion | +1.731 |
tolerance | +1.629 |
Chair | +1.615 |
Sao | +1.611 |
TABLE | +1.586 |
Neg logit contributions | |
enhagen | -2.441 |
ighthouse | -2.146 |
�� | -2.086 |
inately | -2.068 |
ighth | -2.052 |
Token | holiday |
Token ID | 9912 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
enhagen | +0.912 |
ighthouse | +0.816 |
ighth | +0.775 |
�� | +0.768 |
inately | +0.762 |
Neg logit contributions | |
Promotion | -0.744 |
tolerance | -0.700 |
Chair | -0.697 |
_______ | -0.696 |
Mania | -0.695 |
Token | over |
Token ID | 625 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
enhagen | +1.206 |
ighthouse | +1.061 |
ighth | +1.018 |
�� | +1.015 |
inately | +1.009 |
Neg logit contributions | |
Promotion | -0.961 |
tolerance | -0.909 |
Chair | -0.900 |
Sao | -0.898 |
Mania | -0.896 |
Token | Christmas |
Token ID | 6786 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
enhagen | +0.711 |
ighthouse | +0.630 |
�� | +0.603 |
ighth | +0.601 |
inately | +0.600 |
Neg logit contributions | |
Promotion | -0.508 |
tolerance | -0.478 |
Chair | -0.470 |
Mania | -0.468 |
Sao | -0.467 |
Token | that |
Token ID | 326 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
enhagen | +5.389 |
ighthouse | +4.721 |
ighth | +4.514 |
inately | +4.396 |
�� | +4.360 |
Neg logit contributions | |
Promotion | -4.425 |
_______ | -4.286 |
tolerance | -4.265 |
Mania | -4.263 |
Sao | -4.239 |
Token | begins |
Token ID | 6140 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
enhagen | +1.349 |
ighthouse | +1.187 |
�� | +1.138 |
ighth | +1.136 |
inately | +1.128 |
Neg logit contributions | |
Promotion | -1.097 |
tolerance | -1.030 |
Mania | -1.015 |
_______ | -1.013 |
Chair | -1.012 |
Token | in |
Token ID | 287 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Promotion | +0.465 |
tolerance | +0.440 |
Chair | +0.434 |
Sao | +0.434 |
TABLE | +0.430 |
Neg logit contributions | |
enhagen | -0.591 |
ighthouse | -0.519 |
�� | -0.500 |
inately | -0.497 |
ighth | -0.496 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
Promotion | +0.198 |
tolerance | +0.187 |
Chair | +0.183 |
Mania | +0.183 |
TABLE | +0.183 |
Neg logit contributions | |
enhagen | -0.287 |
ighthouse | -0.255 |
inately | -0.244 |
�� | -0.244 |
ighth | -0.244 |
Token | An |
Token ID | 1052 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
enhagen | +0.003 |
ighthouse | +0.003 |
�� | +0.003 |
inately | +0.003 |
ighth | +0.003 |
Neg logit contributions | |
Promotion | -0.002 |
tolerance | -0.002 |
Mania | -0.002 |
TABLE | -0.002 |
Chair | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
Promotion | +0.071 |
tolerance | +0.067 |
Chair | +0.066 |
Sao | +0.066 |
Mania | +0.065 |
Neg logit contributions | |
enhagen | -0.084 |
ighthouse | -0.074 |
�� | -0.071 |
ighth | -0.071 |
inately | -0.070 |
Token | this |
Token ID | 428 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
enhagen | +0.790 |
ighthouse | +0.699 |
�� | +0.674 |
inately | +0.672 |
ighth | +0.671 |
Neg logit contributions | |
Promotion | -0.560 |
tolerance | -0.523 |
Chair | -0.517 |
Sao | -0.516 |
Mania | -0.516 |
Token | whole |
Token ID | 2187 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Promotion | +0.334 |
tolerance | +0.315 |
Sao | +0.311 |
Chair | +0.311 |
Mania | +0.308 |
Neg logit contributions | |
enhagen | -0.443 |
ighthouse | -0.389 |
�� | -0.375 |
inately | -0.374 |
ighth | -0.372 |
Token | War |
Token ID | 1810 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
enhagen | +1.976 |
ighthouse | +1.736 |
inately | +1.679 |
�� | +1.667 |
ighth | +1.664 |
Neg logit contributions | |
Promotion | -1.387 |
Mania | -1.296 |
tolerance | -1.292 |
Sao | -1.288 |
Chair | -1.287 |
Token | on |
Token ID | 319 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
enhagen | +0.658 |
ighthouse | +0.579 |
�� | +0.556 |
inately | +0.554 |
ighth | +0.550 |
Neg logit contributions | |
Promotion | -0.522 |
tolerance | -0.499 |
Sao | -0.491 |
TABLE | -0.488 |
Chair | -0.487 |
Token | Christmas |
Token ID | 6786 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
enhagen | +0.498 |
ighthouse | +0.435 |
�� | +0.420 |
inately | +0.419 |
ighth | +0.419 |
Neg logit contributions | |
Promotion | -0.442 |
tolerance | -0.423 |
Sao | -0.416 |
Chair | -0.415 |
TABLE | -0.412 |
Token | is |
Token ID | 318 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
enhagen | +5.377 |
ighthouse | +4.644 |
inately | +4.560 |
�� | +4.394 |
ighth | +4.380 |
Neg logit contributions | |
Promotion | -4.198 |
Sao | -4.059 |
tolerance | -4.046 |
_______ | -4.034 |
Mania | -4.007 |
Token | getting |
Token ID | 1972 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
enhagen | +0.554 |
ighthouse | +0.484 |
�� | +0.467 |
inately | +0.464 |
ighth | +0.461 |
Neg logit contributions | |
Promotion | -0.476 |
tolerance | -0.450 |
Sao | -0.446 |
Chair | -0.445 |
Mania | -0.442 |
Token | confusing |
Token ID | 15337 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
enhagen | +2.842 |
ighthouse | +2.444 |
inately | +2.379 |
�� | +2.344 |
ighth | +2.342 |
Neg logit contributions | |
Promotion | -2.657 |
tolerance | -2.494 |
Mania | -2.494 |
Sao | -2.456 |
Chair | -2.451 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
enhagen | +1.632 |
ighthouse | +1.418 |
inately | +1.363 |
�� | +1.357 |
ighth | +1.343 |
Neg logit contributions | |
Promotion | -1.447 |
tolerance | -1.366 |
Sao | -1.355 |
Chair | -1.352 |
TABLE | -1.339 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
enhagen | +0.345 |
ighthouse | +0.308 |
�� | +0.296 |
ighth | +0.295 |
inately | +0.294 |
Neg logit contributions | |
Promotion | -0.230 |
tolerance | -0.220 |
Chair | -0.213 |
Sao | -0.213 |
Mania | -0.212 |
Token | into |
Token ID | 656 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Promotion | +0.576 |
tolerance | +0.544 |
Chair | +0.538 |
Sao | +0.537 |
TABLE | +0.532 |
Neg logit contributions | |
enhagen | -0.750 |
ighthouse | -0.660 |
�� | -0.636 |
inately | -0.632 |
ighth | -0.631 |
Token | two |
Token ID | 734 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Promotion | +0.921 |
tolerance | +0.865 |
Chair | +0.853 |
Sao | +0.852 |
TABLE | +0.842 |
Neg logit contributions | |
enhagen | -1.445 |
ighthouse | -1.284 |
�� | -1.243 |
inately | -1.234 |
ighth | -1.232 |
Token | groups |
Token ID | 2628 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
enhagen | +1.056 |
ighthouse | +0.917 |
inately | +0.889 |
ighth | +0.878 |
�� | +0.873 |
Neg logit contributions | |
Promotion | -0.969 |
Mania | -0.909 |
Chair | -0.907 |
tolerance | -0.906 |
TABLE | -0.902 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Promotion | +0.006 |
tolerance | +0.006 |
Chair | +0.006 |
Sao | +0.006 |
TABLE | +0.006 |
Neg logit contributions | |
enhagen | -0.008 |
ighthouse | -0.007 |
�� | -0.007 |
inately | -0.007 |
ighth | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
enhagen | +0.289 |
ighthouse | +0.258 |
�� | +0.249 |
ighth | +0.248 |
inately | +0.248 |
Neg logit contributions | |
Promotion | -0.176 |
tolerance | -0.168 |
Sao | -0.163 |
Chair | -0.162 |
Mania | -0.161 |
Token | infiltr |
Token ID | 21086 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
enhagen | +0.241 |
ighthouse | +0.209 |
�� | +0.201 |
inately | +0.200 |
ighth | +0.199 |
Neg logit contributions | |
Promotion | -0.216 |
tolerance | -0.205 |
Chair | -0.203 |
Sao | -0.202 |
TABLE | -0.201 |
Token | ators |
Token ID | 2024 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
enhagen | +2.913 |
ighthouse | +2.419 |
ighth | +2.246 |
inately | +2.147 |
achus | +2.020 |
Neg logit contributions | |
Promotion | -6.970 |
tolerance | -6.836 |
Mania | -6.701 |
Sao | -6.699 |
Chair | -6.657 |
Token | were |
Token ID | 547 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
enhagen | +0.946 |
ighthouse | +0.833 |
inately | +0.797 |
ighth | +0.797 |
�� | +0.796 |
Neg logit contributions | |
Promotion | -0.720 |
tolerance | -0.675 |
Chair | -0.668 |
Sao | -0.668 |
Mania | -0.663 |
Token | said |
Token ID | 531 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
enhagen | +0.737 |
ighthouse | +0.644 |
�� | +0.619 |
inately | +0.617 |
ighth | +0.616 |
Neg logit contributions | |
Promotion | -0.621 |
tolerance | -0.583 |
Chair | -0.579 |
Sao | -0.577 |
Mania | -0.577 |
Token | to |
Token ID | 284 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Promotion | +0.149 |
tolerance | +0.141 |
Chair | +0.139 |
Sao | +0.139 |
TABLE | +0.137 |
Neg logit contributions | |
enhagen | -0.224 |
ighthouse | -0.199 |
�� | -0.192 |
inately | -0.191 |
ighth | -0.190 |
Token | include |
Token ID | 2291 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
Promotion | +0.694 |
tolerance | +0.654 |
Chair | +0.645 |
Sao | +0.644 |
TABLE | +0.636 |
Neg logit contributions | |
enhagen | -1.082 |
ighthouse | -0.961 |
�� | -0.931 |
inately | -0.923 |
ighth | -0.922 |
Token | aged |
Token ID | 1886 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
enhagen | +0.016 |
ighthouse | +0.014 |
�� | +0.014 |
inately | +0.014 |
ighth | +0.014 |
Neg logit contributions | |
Promotion | -0.014 |
tolerance | -0.014 |
Chair | -0.014 |
Sao | -0.014 |
TABLE | -0.013 |
Token | Italians |
Token ID | 41720 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Promotion | +0.954 |
tolerance | +0.907 |
Sao | +0.897 |
Chair | +0.895 |
TABLE | +0.886 |
Neg logit contributions | |
enhagen | -1.046 |
ighthouse | -0.910 |
�� | -0.877 |
inately | -0.866 |
ighth | -0.865 |
Token | had |
Token ID | 550 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
Promotion | +1.669 |
tolerance | +1.582 |
Chair | +1.555 |
Sao | +1.554 |
TABLE | +1.532 |
Neg logit contributions | |
enhagen | -2.304 |
ighthouse | -2.022 |
�� | -1.979 |
inately | -1.940 |
ighth | -1.927 |
Token | been |
Token ID | 587 |
Feature activation | +6.14e-04 |
Pos logit contributions | |
enhagen | +0.616 |
ighthouse | +0.538 |
�� | +0.517 |
inately | +0.514 |
ighth | +0.513 |
Neg logit contributions | |
Promotion | -0.539 |
tolerance | -0.508 |
Chair | -0.506 |
Sao | -0.503 |
TABLE | -0.499 |
Token | cons |
Token ID | 762 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
Promotion | +0.000 |
tolerance | +0.000 |
Chair | +0.000 |
Sao | +0.000 |
TABLE | +0.000 |
Neg logit contributions | |
enhagen | -0.000 |
ighthouse | -0.000 |
�� | -0.000 |
inately | -0.000 |
ighth | -0.000 |
Token | cript |
Token ID | 6519 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
enhagen | +2.754 |
ighthouse | +2.334 |
ighth | +2.197 |
inately | +2.137 |
achus | +2.083 |
Neg logit contributions | |
Promotion | -4.535 |
tolerance | -4.438 |
Chair | -4.434 |
Sao | -4.418 |
TABLE | -4.373 |
Token | ed |
Token ID | 276 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
enhagen | +4.622 |
ighthouse | +3.935 |
inately | +3.868 |
ighth | +3.733 |
�� | +3.718 |
Neg logit contributions | |
Promotion | -5.190 |
TABLE | -4.997 |
Chair | -4.971 |
Sao | -4.934 |
Mania | -4.928 |
Token | into |
Token ID | 656 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
enhagen | +0.481 |
ighthouse | +0.423 |
�� | +0.406 |
inately | +0.405 |
ighth | +0.404 |
Neg logit contributions | |
Promotion | -0.381 |
tolerance | -0.360 |
Chair | -0.357 |
Sao | -0.356 |
TABLE | -0.353 |
Token | forced |
Token ID | 4137 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Promotion | +1.070 |
tolerance | +1.009 |
Chair | +0.997 |
Sao | +0.996 |
TABLE | +0.985 |
Neg logit contributions | |
enhagen | -1.474 |
ighthouse | -1.300 |
�� | -1.256 |
inately | -1.247 |
ighth | -1.244 |
Token | labour |
Token ID | 10515 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
enhagen | +0.364 |
ighthouse | +0.323 |
inately | +0.313 |
�� | +0.312 |
ighth | +0.312 |
Neg logit contributions | |
Promotion | -0.227 |
Chair | -0.213 |
tolerance | -0.211 |
TABLE | -0.211 |
Sao | -0.210 |
Token | in |
Token ID | 287 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
enhagen | +1.189 |
ighthouse | +1.037 |
inately | +0.994 |
ighth | +0.991 |
�� | +0.990 |
Neg logit contributions | |
Promotion | -0.981 |
Chair | -0.929 |
tolerance | -0.927 |
Sao | -0.919 |
TABLE | -0.915 |
Token | suggest |
Token ID | 1950 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
Promotion | +1.831 |
tolerance | +1.737 |
Chair | +1.719 |
Sao | +1.716 |
TABLE | +1.703 |
Neg logit contributions | |
enhagen | -2.044 |
ighthouse | -1.790 |
�� | -1.732 |
ighth | -1.710 |
inately | -1.708 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
Promotion | +0.021 |
tolerance | +0.020 |
Mania | +0.020 |
Sao | +0.020 |
Chair | +0.019 |
Neg logit contributions | |
enhagen | -0.027 |
ighthouse | -0.024 |
inately | -0.023 |
�� | -0.023 |
ighth | -0.023 |
Token | individual |
Token ID | 1981 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Promotion | +0.017 |
tolerance | +0.016 |
Sao | +0.016 |
Mania | +0.016 |
Chair | +0.016 |
Neg logit contributions | |
enhagen | -0.021 |
ighthouse | -0.019 |
inately | -0.018 |
�� | -0.018 |
ighth | -0.018 |
Token | market |
Token ID | 1910 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Promotion | +0.109 |
tolerance | +0.103 |
Chair | +0.103 |
Sao | +0.103 |
Mania | +0.102 |
Neg logit contributions | |
enhagen | -0.114 |
ighthouse | -0.100 |
inately | -0.096 |
ighth | -0.095 |
�� | -0.095 |
Token | is |
Token ID | 318 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
enhagen | +0.867 |
ighthouse | +0.759 |
inately | +0.733 |
�� | +0.722 |
ighth | +0.722 |
Neg logit contributions | |
Promotion | -0.655 |
Sao | -0.616 |
Chair | -0.612 |
tolerance | -0.610 |
Mania | -0.609 |
Token | stabil |
Token ID | 14349 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
Promotion | +0.200 |
tolerance | +0.188 |
Sao | +0.188 |
Chair | +0.187 |
Mania | +0.186 |
Neg logit contributions | |
enhagen | -0.236 |
ighthouse | -0.207 |
�� | -0.199 |
ighth | -0.199 |
inately | -0.198 |
Token | izing |
Token ID | 2890 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
enhagen | +2.059 |
ighthouse | +1.531 |
inately | +1.376 |
ighth | +1.271 |
achus | +1.145 |
Neg logit contributions | |
Promotion | -7.805 |
Sao | -7.509 |
tolerance | -7.497 |
Chair | -7.443 |
Mania | -7.435 |
Token | and |
Token ID | 290 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
enhagen | +1.973 |
ighthouse | +1.713 |
inately | +1.652 |
ighth | +1.631 |
�� | +1.622 |
Neg logit contributions | |
Promotion | -1.715 |
Sao | -1.598 |
Chair | -1.596 |
tolerance | -1.594 |
Mania | -1.588 |
Token | insurers |
Token ID | 24668 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Promotion | +0.266 |
Sao | +0.250 |
tolerance | +0.249 |
Mania | +0.248 |
Chair | +0.248 |
Neg logit contributions | |
enhagen | -0.330 |
ighthouse | -0.290 |
ighth | -0.278 |
�� | -0.278 |
inately | -0.277 |
Token | in |
Token ID | 287 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
Promotion | +0.215 |
Sao | +0.202 |
tolerance | +0.201 |
Chair | +0.201 |
Mania | +0.198 |
Neg logit contributions | |
enhagen | -0.291 |
ighthouse | -0.256 |
ighth | -0.247 |
inately | -0.246 |
�� | -0.245 |
Token | this |
Token ID | 428 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
enhagen | +0.545 |
ighthouse | +0.478 |
ighth | +0.463 |
inately | +0.462 |
�� | +0.460 |
Neg logit contributions | |
Promotion | -0.445 |
tolerance | -0.420 |
Mania | -0.416 |
Sao | -0.414 |
Chair | -0.413 |
Token | - |
Token ID | 12 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Promotion | +0.076 |
tolerance | +0.072 |
Chair | +0.071 |
Sao | +0.071 |
Mania | +0.071 |
Neg logit contributions | |
enhagen | -0.082 |
ighthouse | -0.072 |
�� | -0.069 |
ighth | -0.069 |
inately | -0.068 |
Token | powered |
Token ID | 12293 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Promotion | +0.553 |
tolerance | +0.530 |
Chair | +0.526 |
Sao | +0.525 |
TABLE | +0.521 |
Neg logit contributions | |
enhagen | -0.416 |
ighthouse | -0.351 |
�� | -0.334 |
inately | -0.330 |
ighth | -0.329 |
Token | ships |
Token ID | 7937 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
enhagen | +0.184 |
ighthouse | +0.158 |
�� | +0.151 |
ighth | +0.150 |
inately | +0.150 |
Neg logit contributions | |
Promotion | -0.205 |
tolerance | -0.195 |
Chair | -0.193 |
Mania | -0.193 |
Sao | -0.192 |
Token | , |
Token ID | 11 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
enhagen | +1.493 |
ighthouse | +1.309 |
ighth | +1.255 |
�� | +1.246 |
inately | +1.246 |
Neg logit contributions | |
Promotion | -1.303 |
tolerance | -1.239 |
Chair | -1.221 |
Sao | -1.221 |
Mania | -1.215 |
Token | with |
Token ID | 351 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
enhagen | +0.473 |
ighthouse | +0.417 |
ighth | +0.400 |
�� | +0.399 |
inately | +0.397 |
Neg logit contributions | |
Promotion | -0.375 |
tolerance | -0.354 |
Mania | -0.350 |
Sao | -0.350 |
Chair | -0.350 |
Token | polar |
Token ID | 13559 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
enhagen | +1.992 |
ighthouse | +1.749 |
ighth | +1.686 |
inately | +1.667 |
�� | +1.646 |
Neg logit contributions | |
Promotion | -1.505 |
Mania | -1.425 |
tolerance | -1.408 |
TABLE | -1.398 |
Chair | -1.386 |
Token | vessels |
Token ID | 14891 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
enhagen | +5.244 |
ighthouse | +4.898 |
ighth | +4.651 |
�� | +4.432 |
inately | +4.376 |
Neg logit contributions | |
Promotion | -4.439 |
Mania | -4.168 |
Sao | -4.088 |
TABLE | -4.077 |
Oaks | -4.075 |
Token | being |
Token ID | 852 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
enhagen | +0.617 |
ighthouse | +0.544 |
ighth | +0.523 |
�� | +0.520 |
inately | +0.520 |
Neg logit contributions | |
Promotion | -0.486 |
tolerance | -0.459 |
Chair | -0.452 |
Sao | -0.451 |
Mania | -0.451 |
Token | mentioned |
Token ID | 4750 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
enhagen | +0.053 |
ighthouse | +0.046 |
�� | +0.044 |
ighth | +0.044 |
inately | +0.044 |
Neg logit contributions | |
Promotion | -0.041 |
tolerance | -0.039 |
Sao | -0.038 |
Chair | -0.038 |
Mania | -0.038 |
Token | but |
Token ID | 475 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
Promotion | +1.146 |
tolerance | +1.080 |
Sao | +1.067 |
Chair | +1.066 |
TABLE | +1.049 |
Neg logit contributions | |
enhagen | -1.748 |
ighthouse | -1.546 |
�� | -1.508 |
inately | -1.485 |
ighth | -1.481 |
Token | aircraft |
Token ID | 6215 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
enhagen | +0.686 |
ighthouse | +0.600 |
ighth | +0.574 |
inately | +0.573 |
�� | +0.572 |
Neg logit contributions | |
Promotion | -0.584 |
tolerance | -0.550 |
Mania | -0.545 |
Chair | -0.544 |
Sao | -0.541 |
Token | play |
Token ID | 711 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
enhagen | +0.106 |
ighthouse | +0.094 |
ighth | +0.090 |
inately | +0.090 |
�� | +0.090 |
Neg logit contributions | |
Promotion | -0.077 |
tolerance | -0.072 |
Chair | -0.072 |
Sao | -0.071 |
Mania | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
Promotion | +0.226 |
tolerance | +0.214 |
Chair | +0.212 |
Sao | +0.212 |
TABLE | +0.209 |
Neg logit contributions | |
enhagen | -0.282 |
ighthouse | -0.248 |
�� | -0.238 |
inately | -0.237 |
ighth | -0.237 |
Token | role |
Token ID | 2597 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
enhagen | +0.002 |
ighthouse | +0.002 |
ighth | +0.002 |
�� | +0.002 |
inately | +0.002 |
Neg logit contributions | |
Promotion | -0.002 |
tolerance | -0.002 |
Sao | -0.002 |
Chair | -0.002 |
Mania | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Promotion | +0.199 |
tolerance | +0.188 |
Chair | +0.186 |
Sao | +0.186 |
TABLE | +0.184 |
Neg logit contributions | |
enhagen | -0.259 |
ighthouse | -0.228 |
�� | -0.219 |
inately | -0.218 |
ighth | -0.218 |
Token | Kodi |
Token ID | 44129 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
enhagen | +0.184 |
ighthouse | +0.162 |
ighth | +0.155 |
inately | +0.155 |
�� | +0.155 |
Neg logit contributions | |
Promotion | -0.149 |
tolerance | -0.141 |
Sao | -0.139 |
Chair | -0.139 |
Mania | -0.138 |
Token | Leia |
Token ID | 41212 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
enhagen | +2.980 |
ighthouse | +2.710 |
ighth | +2.603 |
inately | +2.601 |
�� | +2.536 |
Neg logit contributions | |
Promotion | -1.698 |
tolerance | -1.593 |
Sao | -1.582 |
Chair | -1.573 |
TABLE | -1.563 |
Token | : |
Token ID | 25 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
enhagen | +5.382 |
ighthouse | +4.809 |
ighth | +4.580 |
inately | +4.576 |
achus | +4.445 |
Neg logit contributions | |
Promotion | -4.234 |
tolerance | -4.138 |
Sao | -4.029 |
TABLE | -3.982 |
Chair | -3.968 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
enhagen | +1.177 |
ighthouse | +1.046 |
inately | +1.000 |
ighth | +0.998 |
�� | +0.997 |
Neg logit contributions | |
Promotion | -0.886 |
tolerance | -0.841 |
Sao | -0.830 |
Chair | -0.830 |
Mania | -0.826 |
Token |
|
Token ID | 198 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
enhagen | +0.909 |
ighthouse | +0.811 |
ighth | +0.772 |
inately | +0.769 |
�� | +0.763 |
Neg logit contributions | |
Promotion | -0.769 |
tolerance | -0.732 |
Sao | -0.723 |
Chair | -0.716 |
TABLE | -0.713 |
Token | Update |
Token ID | 10260 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
enhagen | +0.268 |
ighthouse | +0.239 |
ighth | +0.229 |
inately | +0.227 |
�� | +0.227 |
Neg logit contributions | |
Promotion | -0.214 |
tolerance | -0.203 |
Sao | -0.202 |
Chair | -0.200 |
TABLE | -0.197 |
Token | your |
Token ID | 534 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
enhagen | +0.478 |
ighthouse | +0.423 |
ighth | +0.405 |
inately | +0.405 |
�� | +0.403 |
Neg logit contributions | |
Promotion | -0.337 |
tolerance | -0.320 |
Chair | -0.316 |
Sao | -0.316 |
Mania | -0.313 |
Token | ( |
Token ID | 357 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
enhagen | +0.261 |
ighthouse | +0.228 |
inately | +0.218 |
ighth | +0.217 |
�� | +0.217 |
Neg logit contributions | |
Promotion | -0.203 |
tolerance | -0.194 |
Mania | -0.190 |
Sao | -0.189 |
Chair | -0.189 |
Token | Photo |
Token ID | 6191 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Promotion | +1.501 |
tolerance | +1.418 |
Chair | +1.401 |
Sao | +1.400 |
TABLE | +1.385 |
Neg logit contributions | |
enhagen | -2.007 |
ighthouse | -1.768 |
�� | -1.708 |
inately | -1.694 |
ighth | -1.691 |
Token | : |
Token ID | 25 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
enhagen | +0.484 |
ighthouse | +0.427 |
�� | +0.413 |
inately | +0.409 |
ighth | +0.407 |
Neg logit contributions | |
Promotion | -0.304 |
tolerance | -0.286 |
Sao | -0.283 |
Chair | -0.281 |
TABLE | -0.279 |
Token | Mary |
Token ID | 5335 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
enhagen | +0.572 |
ighthouse | +0.502 |
�� | +0.480 |
inately | +0.480 |
ighth | +0.478 |
Neg logit contributions | |
Promotion | -0.418 |
tolerance | -0.401 |
Mania | -0.391 |
Chair | -0.390 |
Sao | -0.387 |
Token | Sch |
Token ID | 3059 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
enhagen | +0.351 |
ighthouse | +0.313 |
inately | +0.305 |
ighth | +0.304 |
�� | +0.299 |
Neg logit contributions | |
Promotion | -0.178 |
tolerance | -0.172 |
TABLE | -0.167 |
Chair | -0.165 |
_______ | -0.161 |
Token | wal |
Token ID | 16783 |
Feature activation | -7.02e+00 |
Pos logit contributions | |
enhagen | +1.718 |
ighthouse | +1.496 |
ighth | +1.436 |
inately | +1.422 |
�� | +1.384 |
Neg logit contributions | |
Promotion | -1.677 |
tolerance | -1.603 |
Sao | -1.570 |
TABLE | -1.564 |
Chair | -1.548 |
Token | m |
Token ID | 76 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
enhagen | +4.882 |
ighthouse | +4.085 |
ighth | +4.012 |
inately | +3.955 |
vre | +3.843 |
Neg logit contributions | |
Promotion | -4.934 |
tolerance | -4.883 |
Mania | -4.654 |
Sao | -4.622 |
_______ | -4.622 |
Token | / |
Token ID | 14 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
enhagen | +0.498 |
ighthouse | +0.436 |
inately | +0.421 |
�� | +0.421 |
ighth | +0.420 |
Neg logit contributions | |
Promotion | -0.319 |
tolerance | -0.304 |
Sao | -0.298 |
Chair | -0.296 |
Mania | -0.295 |
Token | AP |
Token ID | 2969 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
enhagen | +1.780 |
ighthouse | +1.553 |
�� | +1.487 |
inately | +1.485 |
ighth | +1.477 |
Neg logit contributions | |
Promotion | -1.235 |
tolerance | -1.191 |
Chair | -1.163 |
Sao | -1.152 |
TABLE | -1.148 |
Token | ) |
Token ID | 8 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
enhagen | +0.130 |
ighthouse | +0.115 |
�� | +0.111 |
inately | +0.110 |
ighth | +0.110 |
Neg logit contributions | |
Promotion | -0.088 |
tolerance | -0.083 |
Sao | -0.082 |
Chair | -0.082 |
TABLE | -0.081 |
Token |
|
Token ID | 198 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
enhagen | +1.287 |
ighthouse | +1.125 |
�� | +1.076 |
inately | +1.072 |
ighth | +1.070 |
Neg logit contributions | |
Promotion | -1.024 |
tolerance | -0.972 |
Sao | -0.963 |
Mania | -0.953 |
Chair | -0.953 |
Token |
|
Token ID | 198 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
Promotion | +0.378 |
tolerance | +0.357 |
Chair | +0.354 |
Sao | +0.352 |
TABLE | +0.348 |
Neg logit contributions | |
enhagen | -0.516 |
ighthouse | -0.452 |
�� | -0.441 |
inately | -0.435 |
ighth | -0.433 |
Token | German |
Token ID | 16010 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Promotion | +0.461 |
tolerance | +0.430 |
Sao | +0.425 |
Chair | +0.423 |
TABLE | +0.417 |
Neg logit contributions | |
enhagen | -0.848 |
ighthouse | -0.760 |
�� | -0.734 |
ighth | -0.734 |
inately | -0.731 |
Token | environment |
Token ID | 2858 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Promotion | +0.126 |
tolerance | +0.117 |
Sao | +0.117 |
Mania | +0.116 |
TABLE | +0.116 |
Neg logit contributions | |
enhagen | -0.181 |
ighthouse | -0.160 |
inately | -0.154 |
ighth | -0.153 |
�� | -0.153 |
Token | minister |
Token ID | 5342 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
Promotion | +0.454 |
tolerance | +0.421 |
Sao | +0.419 |
TABLE | +0.416 |
Mania | +0.413 |
Neg logit contributions | |
enhagen | -0.901 |
ighthouse | -0.812 |
�� | -0.786 |
ighth | -0.782 |
inately | -0.782 |
Token | Barbara |
Token ID | 16685 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
enhagen | +0.534 |
ighthouse | +0.465 |
inately | +0.446 |
�� | +0.443 |
ighth | +0.440 |
Neg logit contributions | |
Promotion | -0.414 |
tolerance | -0.387 |
Sao | -0.386 |
Mania | -0.383 |
Chair | -0.383 |
Token | Hendricks |
Token ID | 42476 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
Promotion | +0.891 |
tolerance | +0.855 |
Chair | +0.847 |
Sao | +0.847 |
TABLE | +0.840 |
Neg logit contributions | |
enhagen | -0.649 |
ighthouse | -0.544 |
�� | -0.517 |
inately | -0.511 |
ighth | -0.510 |
Token | said |
Token ID | 531 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
enhagen | +5.479 |
ighthouse | +4.572 |
ighth | +4.398 |
inately | +4.377 |
achus | +4.276 |
Neg logit contributions | |
Promotion | -4.349 |
tolerance | -4.079 |
TABLE | -4.065 |
Sao | -4.060 |
Mania | -4.026 |
Token | there |
Token ID | 612 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
enhagen | +0.378 |
ighthouse | +0.332 |
inately | +0.318 |
ighth | +0.317 |
�� | +0.316 |
Neg logit contributions | |
Promotion | -0.287 |
tolerance | -0.267 |
Sao | -0.265 |
Chair | -0.265 |
TABLE | -0.264 |
Token | was |
Token ID | 373 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
enhagen | +1.550 |
ighthouse | +1.387 |
inately | +1.331 |
ighth | +1.323 |
�� | +1.307 |
Neg logit contributions | |
Promotion | -1.040 |
tolerance | -0.961 |
Mania | -0.951 |
Sao | -0.949 |
Chair | -0.948 |
Token | a |
Token ID | 257 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
enhagen | +1.065 |
ighthouse | +0.929 |
inately | +0.884 |
ighth | +0.883 |
�� | +0.876 |
Neg logit contributions | |
Promotion | -0.979 |
Sao | -0.920 |
Mania | -0.919 |
tolerance | -0.913 |
Chair | -0.910 |
Token | � |
Token ID | 564 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
enhagen | +0.125 |
ighthouse | +0.109 |
�� | +0.105 |
inately | +0.105 |
ighth | +0.105 |
Neg logit contributions | |
Promotion | -0.097 |
Sao | -0.091 |
tolerance | -0.091 |
Mania | -0.091 |
Chair | -0.090 |
Token | At |
Token ID | 1629 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
Promotion | +0.350 |
tolerance | +0.330 |
Sao | +0.323 |
Chair | +0.322 |
TABLE | +0.319 |
Neg logit contributions | |
enhagen | -0.586 |
ighthouse | -0.523 |
�� | -0.506 |
inately | -0.503 |
ighth | -0.502 |
Token | first |
Token ID | 717 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Promotion | +0.668 |
tolerance | +0.635 |
Chair | +0.626 |
Sao | +0.626 |
TABLE | +0.620 |
Neg logit contributions | |
enhagen | -0.762 |
ighthouse | -0.665 |
�� | -0.639 |
inately | -0.635 |
ighth | -0.633 |
Token | we |
Token ID | 356 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
enhagen | +1.950 |
ighthouse | +1.707 |
inately | +1.644 |
�� | +1.624 |
ighth | +1.619 |
Neg logit contributions | |
Promotion | -1.588 |
tolerance | -1.487 |
Chair | -1.465 |
Mania | -1.464 |
Sao | -1.461 |
Token | imagined |
Token ID | 15758 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Promotion | +0.910 |
tolerance | +0.860 |
Chair | +0.850 |
Sao | +0.849 |
TABLE | +0.840 |
Neg logit contributions | |
enhagen | -1.192 |
ighthouse | -1.049 |
�� | -1.013 |
inately | -1.005 |
ighth | -1.003 |
Token | that |
Token ID | 326 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Promotion | +0.933 |
tolerance | +0.881 |
Chair | +0.871 |
Sao | +0.870 |
TABLE | +0.860 |
Neg logit contributions | |
enhagen | -1.245 |
ighthouse | -1.096 |
�� | -1.059 |
inately | -1.051 |
ighth | -1.049 |
Token | each |
Token ID | 1123 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
Promotion | +0.633 |
tolerance | +0.599 |
Sao | +0.590 |
Chair | +0.590 |
TABLE | +0.584 |
Neg logit contributions | |
enhagen | -0.826 |
ighthouse | -0.726 |
�� | -0.701 |
inately | -0.696 |
ighth | -0.694 |
Token | battle |
Token ID | 3344 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Promotion | +3.247 |
tolerance | +3.068 |
Chair | +3.054 |
Sao | +3.026 |
TABLE | +2.996 |
Neg logit contributions | |
enhagen | -4.411 |
ighthouse | -3.855 |
�� | -3.754 |
inately | -3.730 |
ighth | -3.685 |
Token | should |
Token ID | 815 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Promotion | +0.907 |
tolerance | +0.846 |
Sao | +0.833 |
Chair | +0.831 |
TABLE | +0.821 |
Neg logit contributions | |
enhagen | -1.641 |
ighthouse | -1.465 |
�� | -1.418 |
inately | -1.412 |
ighth | -1.409 |
Token | have |
Token ID | 423 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Promotion | +0.193 |
tolerance | +0.180 |
Sao | +0.179 |
Chair | +0.177 |
Mania | +0.177 |
Neg logit contributions | |
enhagen | -0.255 |
ighthouse | -0.224 |
inately | -0.216 |
�� | -0.215 |
ighth | -0.215 |
Token | happened |
Token ID | 3022 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Promotion | +1.062 |
tolerance | +1.001 |
Sao | +0.989 |
Chair | +0.989 |
Mania | +0.979 |
Neg logit contributions | |
enhagen | -1.413 |
ighthouse | -1.243 |
�� | -1.199 |
inately | -1.192 |
ighth | -1.190 |
Token | in |
Token ID | 287 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
enhagen | +0.236 |
ighthouse | +0.208 |
inately | +0.200 |
ighth | +0.199 |
�� | +0.199 |
Neg logit contributions | |
Promotion | -0.178 |
tolerance | -0.167 |
Chair | -0.165 |
Sao | -0.165 |
Mania | -0.163 |
Token | me |
Token ID | 502 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
enhagen | +1.136 |
ighthouse | +0.974 |
inately | +0.922 |
�� | +0.915 |
ighth | +0.913 |
Neg logit contributions | |
Promotion | -1.356 |
Mania | -1.283 |
tolerance | -1.279 |
Chair | -1.276 |
Sao | -1.275 |
Token | something |
Token ID | 1223 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
enhagen | +0.714 |
ighthouse | +0.623 |
inately | +0.599 |
�� | +0.596 |
ighth | +0.596 |
Neg logit contributions | |
Promotion | -0.569 |
tolerance | -0.532 |
Chair | -0.531 |
Mania | -0.529 |
Sao | -0.529 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
enhagen | +1.781 |
ighthouse | +1.574 |
inately | +1.502 |
ighth | +1.501 |
�� | +1.499 |
Neg logit contributions | |
Promotion | -1.367 |
Mania | -1.279 |
tolerance | -1.275 |
Chair | -1.263 |
TABLE | -1.258 |
Token | He |
Token ID | 679 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Promotion | +0.202 |
tolerance | +0.193 |
Sao | +0.187 |
Chair | +0.187 |
Mania | +0.186 |
Neg logit contributions | |
enhagen | -0.324 |
ighthouse | -0.290 |
�� | -0.278 |
ighth | -0.278 |
inately | -0.277 |
Token | holds |
Token ID | 6622 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
enhagen | +0.274 |
ighthouse | +0.239 |
inately | +0.228 |
�� | +0.228 |
ighth | +0.228 |
Neg logit contributions | |
Promotion | -0.241 |
tolerance | -0.227 |
Sao | -0.225 |
Chair | -0.225 |
Mania | -0.223 |
Token | up |
Token ID | 510 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
Promotion | +2.158 |
tolerance | +2.046 |
Chair | +2.028 |
Sao | +2.019 |
TABLE | +1.996 |
Neg logit contributions | |
enhagen | -3.021 |
ighthouse | -2.673 |
�� | -2.608 |
ighth | -2.559 |
inately | -2.555 |
Token | an |
Token ID | 281 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Promotion | +2.910 |
tolerance | +2.784 |
Chair | +2.741 |
Sao | +2.714 |
TABLE | +2.708 |
Neg logit contributions | |
enhagen | -4.111 |
ighthouse | -3.659 |
�� | -3.566 |
ighth | -3.508 |
inately | -3.479 |
Token | intricate |
Token ID | 28746 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Promotion | +0.730 |
tolerance | +0.688 |
Sao | +0.678 |
Chair | +0.678 |
Mania | +0.670 |
Neg logit contributions | |
enhagen | -1.077 |
ighthouse | -0.954 |
�� | -0.920 |
inately | -0.917 |
ighth | -0.914 |
Token | ring |
Token ID | 5858 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Promotion | +1.941 |
tolerance | +1.847 |
Chair | +1.824 |
Sao | +1.815 |
TABLE | +1.797 |
Neg logit contributions | |
enhagen | -2.452 |
ighthouse | -2.152 |
�� | -2.090 |
ighth | -2.054 |
inately | -2.054 |
Token | made |
Token ID | 925 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
Promotion | +1.700 |
tolerance | +1.613 |
Chair | +1.595 |
Sao | +1.591 |
TABLE | +1.575 |
Neg logit contributions | |
enhagen | -2.128 |
ighthouse | -1.868 |
�� | -1.806 |
inately | -1.788 |
ighth | -1.786 |
Token | of |
Token ID | 286 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Promotion | +0.354 |
tolerance | +0.338 |
Chair | +0.334 |
Sao | +0.334 |
TABLE | +0.330 |
Neg logit contributions | |
enhagen | -0.393 |
ighthouse | -0.342 |
�� | -0.330 |
ighth | -0.326 |
inately | -0.326 |
Token | aid |
Token ID | 1698 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
enhagen | +0.158 |
ighthouse | +0.138 |
�� | +0.136 |
inately | +0.134 |
ighth | +0.132 |
Neg logit contributions | |
Promotion | -0.108 |
Chair | -0.101 |
tolerance | -0.101 |
Sao | -0.101 |
TABLE | -0.099 |
Token | oa |
Token ID | 12162 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
enhagen | +0.207 |
ighthouse | +0.186 |
�� | +0.182 |
inately | +0.180 |
ighth | +0.179 |
Neg logit contributions | |
Promotion | -0.097 |
tolerance | -0.090 |
Sao | -0.088 |
Chair | -0.088 |
Mania | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
Promotion | +0.269 |
tolerance | +0.255 |
Chair | +0.252 |
Sao | +0.252 |
TABLE | +0.249 |
Neg logit contributions | |
enhagen | -0.325 |
ighthouse | -0.284 |
�� | -0.275 |
inately | -0.272 |
ighth | -0.272 |
Token | which |
Token ID | 543 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Promotion | +0.613 |
tolerance | +0.580 |
Chair | +0.574 |
Sao | +0.574 |
TABLE | +0.566 |
Neg logit contributions | |
enhagen | -0.776 |
ighthouse | -0.680 |
�� | -0.658 |
inately | -0.652 |
ighth | -0.651 |
Token | is |
Token ID | 318 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Promotion | +0.651 |
tolerance | +0.614 |
Chair | +0.604 |
Mania | +0.602 |
Sao | +0.602 |
Neg logit contributions | |
enhagen | -0.912 |
ighthouse | -0.804 |
�� | -0.774 |
inately | -0.771 |
ighth | -0.768 |
Token | held |
Token ID | 2714 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
Promotion | +0.804 |
tolerance | +0.755 |
Chair | +0.744 |
Sao | +0.743 |
Mania | +0.739 |
Neg logit contributions | |
enhagen | -1.132 |
ighthouse | -1.002 |
�� | -0.965 |
ighth | -0.961 |
inately | -0.960 |
Token | by |
Token ID | 416 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Promotion | +2.842 |
Sao | +2.740 |
tolerance | +2.736 |
Chair | +2.714 |
TABLE | +2.596 |
Neg logit contributions | |
enhagen | -5.381 |
ighthouse | -4.803 |
�� | -4.743 |
ighth | -4.617 |
inately | -4.583 |
Token | the |
Token ID | 262 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
Promotion | +2.406 |
tolerance | +2.288 |
Sao | +2.271 |
Chair | +2.267 |
TABLE | +2.214 |
Neg logit contributions | |
enhagen | -3.089 |
ighthouse | -2.729 |
�� | -2.664 |
inately | -2.607 |
ighth | -2.607 |
Token | Islamist |
Token ID | 17780 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
Promotion | +0.283 |
tolerance | +0.269 |
Chair | +0.266 |
Sao | +0.265 |
Mania | +0.265 |
Neg logit contributions | |
enhagen | -0.323 |
ighthouse | -0.281 |
�� | -0.270 |
inately | -0.269 |
ighth | -0.268 |
Token | group |
Token ID | 1448 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
enhagen | +0.670 |
ighthouse | +0.587 |
inately | +0.566 |
�� | +0.563 |
ighth | +0.561 |
Neg logit contributions | |
Promotion | -0.530 |
Mania | -0.506 |
tolerance | -0.504 |
TABLE | -0.498 |
Chair | -0.498 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Promotion | +0.558 |
tolerance | +0.529 |
Chair | +0.522 |
Sao | +0.522 |
TABLE | +0.516 |
Neg logit contributions | |
enhagen | -0.697 |
ighthouse | -0.611 |
�� | -0.590 |
inately | -0.585 |
ighth | -0.584 |
Token | the |
Token ID | 262 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
Promotion | +1.035 |
tolerance | +0.977 |
Chair | +0.967 |
Sao | +0.967 |
TABLE | +0.957 |
Neg logit contributions | |
enhagen | -1.354 |
ighthouse | -1.191 |
�� | -1.149 |
inately | -1.141 |
ighth | -1.139 |
Token | UN |
Token ID | 4725 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Promotion | +0.579 |
tolerance | +0.549 |
Chair | +0.542 |
Sao | +0.542 |
TABLE | +0.536 |
Neg logit contributions | |
enhagen | -0.718 |
ighthouse | -0.630 |
�� | -0.607 |
inately | -0.602 |
ighth | -0.601 |
Token | commission |
Token ID | 5810 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
enhagen | +1.891 |
ighthouse | +1.676 |
inately | +1.615 |
ighth | +1.615 |
�� | +1.611 |
Neg logit contributions | |
Promotion | -1.206 |
tolerance | -1.129 |
Sao | -1.127 |
TABLE | -1.124 |
Mania | -1.121 |
Token | of |
Token ID | 286 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
enhagen | +1.704 |
ighthouse | +1.491 |
ighth | +1.445 |
inately | +1.444 |
�� | +1.416 |
Neg logit contributions | |
Promotion | -1.197 |
tolerance | -1.117 |
TABLE | -1.104 |
Mania | -1.101 |
Sao | -1.096 |
Token | inquiry |
Token ID | 12069 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
Promotion | +0.060 |
tolerance | +0.056 |
Sao | +0.055 |
Chair | +0.055 |
Mania | +0.055 |
Neg logit contributions | |
enhagen | -0.119 |
ighthouse | -0.107 |
�� | -0.104 |
ighth | -0.103 |
inately | -0.103 |
Token | held |
Token ID | 2714 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Promotion | +0.468 |
tolerance | +0.437 |
Sao | +0.431 |
Chair | +0.431 |
TABLE | +0.428 |
Neg logit contributions | |
enhagen | -0.740 |
ighthouse | -0.656 |
inately | -0.634 |
�� | -0.632 |
ighth | -0.632 |
Token | Hamas |
Token ID | 15767 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
Promotion | +3.513 |
tolerance | +3.396 |
Chair | +3.343 |
Sao | +3.315 |
TABLE | +3.222 |
Neg logit contributions | |
enhagen | -4.624 |
ighthouse | -4.087 |
�� | -4.020 |
ighth | -3.912 |
inately | -3.902 |
Token | accountable |
Token ID | 16689 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Promotion | +0.033 |
tolerance | +0.031 |
Sao | +0.030 |
TABLE | +0.030 |
Chair | +0.030 |
Neg logit contributions | |
enhagen | -0.057 |
ighthouse | -0.051 |
inately | -0.049 |
ighth | -0.049 |
�� | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
enhagen | +1.102 |
ighthouse | +0.962 |
inately | +0.924 |
�� | +0.920 |
ighth | +0.920 |
Neg logit contributions | |
Promotion | -0.928 |
tolerance | -0.871 |
Sao | -0.866 |
Chair | -0.864 |
TABLE | -0.857 |
Token | international |
Token ID | 3230 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
enhagen | +0.597 |
ighthouse | +0.518 |
�� | +0.499 |
ighth | +0.497 |
inately | +0.495 |
Neg logit contributions | |
Promotion | -0.504 |
tolerance | -0.475 |
Sao | -0.473 |
Mania | -0.472 |
Chair | -0.470 |
Token | human |
Token ID | 1692 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
enhagen | +0.117 |
ighthouse | +0.104 |
�� | +0.101 |
ighth | +0.100 |
inately | +0.100 |
Neg logit contributions | |
Promotion | -0.076 |
tolerance | -0.070 |
Chair | -0.070 |
Sao | -0.070 |
Mania | -0.070 |
Token | points |
Token ID | 2173 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
enhagen | +0.784 |
ighthouse | +0.688 |
ighth | +0.661 |
inately | +0.657 |
�� | +0.655 |
Neg logit contributions | |
Promotion | -0.588 |
tolerance | -0.549 |
Sao | -0.542 |
Chair | -0.542 |
Mania | -0.540 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
enhagen | +0.885 |
ighthouse | +0.777 |
�� | +0.749 |
inately | +0.744 |
ighth | +0.741 |
Neg logit contributions | |
Promotion | -0.684 |
tolerance | -0.644 |
Chair | -0.639 |
Sao | -0.638 |
TABLE | -0.632 |
Token | the |
Token ID | 262 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
Promotion | +0.074 |
tolerance | +0.070 |
Chair | +0.070 |
Sao | +0.069 |
Mania | +0.069 |
Neg logit contributions | |
enhagen | -0.091 |
ighthouse | -0.080 |
�� | -0.077 |
inately | -0.076 |
ighth | -0.076 |
Token | case |
Token ID | 1339 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Promotion | +0.044 |
tolerance | +0.042 |
Chair | +0.041 |
Sao | +0.041 |
TABLE | +0.041 |
Neg logit contributions | |
enhagen | -0.055 |
ighthouse | -0.048 |
�� | -0.047 |
inately | -0.046 |
ighth | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
enhagen | +1.153 |
ighthouse | +1.001 |
�� | +0.964 |
inately | +0.952 |
ighth | +0.951 |
Neg logit contributions | |
Promotion | -1.073 |
tolerance | -1.017 |
Chair | -1.007 |
Sao | -1.006 |
TABLE | -0.998 |
Token | Tad |
Token ID | 50077 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
enhagen | +0.408 |
ighthouse | +0.356 |
�� | +0.343 |
inately | +0.342 |
ighth | +0.342 |
Neg logit contributions | |
Promotion | -0.317 |
tolerance | -0.300 |
Mania | -0.296 |
Chair | -0.296 |
TABLE | -0.295 |
Token | am |
Token ID | 321 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Promotion | +4.878 |
Chair | +4.628 |
Sao | +4.616 |
tolerance | +4.616 |
Mania | +4.572 |
Neg logit contributions | |
enhagen | -5.109 |
ighthouse | -4.457 |
�� | -4.330 |
inately | -4.268 |
ighth | -4.213 |
Token | asa |
Token ID | 15462 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
Promotion | +2.092 |
tolerance | +1.973 |
Chair | +1.953 |
Sao | +1.948 |
Mania | +1.922 |
Neg logit contributions | |
enhagen | -2.895 |
ighthouse | -2.552 |
�� | -2.466 |
inately | -2.450 |
ighth | -2.443 |
Token | G |
Token ID | 402 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Promotion | +2.687 |
tolerance | +2.528 |
Chair | +2.524 |
Sao | +2.520 |
TABLE | +2.465 |
Neg logit contributions | |
enhagen | -3.289 |
ighthouse | -2.874 |
�� | -2.764 |
inately | -2.764 |
ighth | -2.747 |
Token | oto |
Token ID | 2069 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Promotion | +0.746 |
tolerance | +0.709 |
Chair | +0.701 |
Sao | +0.700 |
Mania | +0.692 |
Neg logit contributions | |
enhagen | -0.824 |
ighthouse | -0.716 |
�� | -0.692 |
inately | -0.685 |
ighth | -0.681 |
Token | , |
Token ID | 11 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
Promotion | +0.100 |
tolerance | +0.094 |
Chair | +0.093 |
Sao | +0.093 |
TABLE | +0.092 |
Neg logit contributions | |
enhagen | -0.128 |
ighthouse | -0.112 |
�� | -0.108 |
inately | -0.108 |
ighth | -0.108 |
Token | all |
Token ID | 477 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
enhagen | +0.992 |
ighthouse | +0.873 |
�� | +0.837 |
inately | +0.836 |
ighth | +0.833 |
Neg logit contributions | |
Promotion | -0.792 |
tolerance | -0.746 |
Sao | -0.742 |
Chair | -0.740 |
Mania | -0.733 |
Token | of |
Token ID | 286 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
enhagen | +0.499 |
ighthouse | +0.438 |
�� | +0.421 |
ighth | +0.420 |
inately | +0.418 |
Neg logit contributions | |
Promotion | -0.396 |
tolerance | -0.374 |
Sao | -0.371 |
Chair | -0.371 |
Mania | -0.367 |
Token | this |
Token ID | 428 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Promotion | +0.366 |
tolerance | +0.346 |
Chair | +0.343 |
Sao | +0.342 |
Mania | +0.339 |
Neg logit contributions | |
enhagen | -0.433 |
ighthouse | -0.377 |
�� | -0.363 |
ighth | -0.361 |
inately | -0.361 |
Token | would |
Token ID | 561 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Promotion | +1.121 |
tolerance | +1.057 |
Chair | +1.041 |
Sao | +1.040 |
TABLE | +1.028 |
Neg logit contributions | |
enhagen | -1.676 |
ighthouse | -1.486 |
�� | -1.439 |
inately | -1.426 |
ighth | -1.425 |
Token | have |
Token ID | 423 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
enhagen | +0.868 |
ighthouse | +0.761 |
inately | +0.735 |
�� | +0.729 |
ighth | +0.726 |
Neg logit contributions | |
Promotion | -0.729 |
tolerance | -0.681 |
Chair | -0.677 |
Sao | -0.676 |
Mania | -0.671 |
Token | been |
Token ID | 587 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Promotion | +1.134 |
tolerance | +1.077 |
Sao | +1.063 |
Chair | +1.061 |
TABLE | +1.051 |
Neg logit contributions | |
enhagen | -1.447 |
ighthouse | -1.271 |
�� | -1.228 |
inately | -1.215 |
ighth | -1.214 |
Token | for |
Token ID | 329 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Promotion | +0.999 |
tolerance | +0.941 |
Chair | +0.934 |
Sao | +0.933 |
Mania | +0.923 |
Neg logit contributions | |
enhagen | -1.209 |
ighthouse | -1.059 |
�� | -1.019 |
inately | -1.015 |
ighth | -1.012 |
Token | nothing |
Token ID | 2147 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Promotion | +0.677 |
tolerance | +0.640 |
Chair | +0.634 |
Sao | +0.633 |
Mania | +0.625 |
Neg logit contributions | |
enhagen | -0.862 |
ighthouse | -0.757 |
�� | -0.731 |
inately | -0.726 |
ighth | -0.724 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Promotion | +0.086 |
tolerance | +0.081 |
Chair | +0.081 |
Sao | +0.080 |
Mania | +0.079 |
Neg logit contributions | |
enhagen | -0.094 |
ighthouse | -0.082 |
�� | -0.079 |
inately | -0.079 |
ighth | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Promotion | +0.704 |
tolerance | +0.667 |
Sao | +0.655 |
Chair | +0.654 |
Mania | +0.648 |
Neg logit contributions | |
enhagen | -1.006 |
ighthouse | -0.892 |
�� | -0.860 |
ighth | -0.855 |
inately | -0.855 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Promotion | +0.699 |
tolerance | +0.659 |
Chair | +0.655 |
Sao | +0.650 |
Mania | +0.644 |
Neg logit contributions | |
enhagen | -0.977 |
ighthouse | -0.852 |
�� | -0.835 |
inately | -0.822 |
ighth | -0.817 |
Token | of |
Token ID | 286 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Promotion | +0.043 |
tolerance | +0.041 |
Chair | +0.041 |
Sao | +0.041 |
TABLE | +0.040 |
Neg logit contributions | |
enhagen | -0.049 |
ighthouse | -0.043 |
�� | -0.041 |
inately | -0.041 |
ighth | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
enhagen | +1.026 |
ighthouse | +0.892 |
�� | +0.856 |
ighth | +0.852 |
inately | +0.847 |
Neg logit contributions | |
Promotion | -0.902 |
TABLE | -0.839 |
tolerance | -0.836 |
Mania | -0.835 |
Sao | -0.831 |
Token | problem |
Token ID | 1917 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Promotion | +0.010 |
tolerance | +0.009 |
Chair | +0.009 |
Sao | +0.009 |
TABLE | +0.009 |
Neg logit contributions | |
enhagen | -0.013 |
ighthouse | -0.012 |
�� | -0.011 |
ighth | -0.011 |
inately | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Promotion | +0.235 |
tolerance | +0.223 |
Sao | +0.220 |
Chair | +0.220 |
TABLE | +0.218 |
Neg logit contributions | |
enhagen | -0.308 |
ighthouse | -0.270 |
�� | -0.262 |
inately | -0.259 |
ighth | -0.259 |
Token | those |
Token ID | 883 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Promotion | +0.163 |
tolerance | +0.155 |
Sao | +0.153 |
Chair | +0.153 |
Mania | +0.152 |
Neg logit contributions | |
enhagen | -0.185 |
ighthouse | -0.162 |
�� | -0.155 |
inately | -0.154 |
ighth | -0.154 |
Token | who |
Token ID | 508 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
enhagen | +1.322 |
ighthouse | +1.159 |
ighth | +1.104 |
inately | +1.099 |
�� | +1.088 |
Neg logit contributions | |
Promotion | -1.364 |
tolerance | -1.292 |
Sao | -1.288 |
Mania | -1.288 |
TABLE | -1.279 |
Token | paid |
Token ID | 3432 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Promotion | +1.036 |
tolerance | +0.978 |
Chair | +0.966 |
Sao | +0.964 |
TABLE | +0.952 |
Neg logit contributions | |
enhagen | -1.520 |
ighthouse | -1.342 |
�� | -1.303 |
inately | -1.289 |
ighth | -1.285 |
Token | extra |
Token ID | 3131 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
enhagen | +1.109 |
ighthouse | +0.976 |
inately | +0.937 |
�� | +0.935 |
ighth | +0.935 |
Neg logit contributions | |
Promotion | -0.882 |
tolerance | -0.835 |
Sao | -0.828 |
Chair | -0.825 |
Mania | -0.822 |
Token | for |
Token ID | 329 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Promotion | +1.275 |
tolerance | +1.213 |
Sao | +1.190 |
Chair | +1.190 |
TABLE | +1.174 |
Neg logit contributions | |
enhagen | -1.735 |
ighthouse | -1.532 |
�� | -1.500 |
ighth | -1.462 |
inately | -1.457 |
Token | other |
Token ID | 584 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Promotion | +0.111 |
tolerance | +0.105 |
Sao | +0.104 |
Chair | +0.104 |
Mania | +0.103 |
Neg logit contributions | |
enhagen | -0.135 |
ighthouse | -0.118 |
�� | -0.114 |
inately | -0.113 |
ighth | -0.113 |
Token | rewards |
Token ID | 11530 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Promotion | +0.968 |
tolerance | +0.917 |
Chair | +0.906 |
Sao | +0.906 |
TABLE | +0.896 |
Neg logit contributions | |
enhagen | -1.190 |
ighthouse | -1.043 |
�� | -1.006 |
inately | -0.998 |
ighth | -0.996 |
Token | cycles |
Token ID | 16006 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Promotion | +0.728 |
tolerance | +0.689 |
Sao | +0.682 |
Chair | +0.682 |
TABLE | +0.673 |
Neg logit contributions | |
enhagen | -0.895 |
ighthouse | -0.785 |
�� | -0.756 |
inately | -0.751 |
ighth | -0.750 |
Token | of |
Token ID | 286 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
enhagen | +0.187 |
ighthouse | +0.164 |
�� | +0.158 |
inately | +0.157 |
ighth | +0.157 |
Neg logit contributions | |
Promotion | -0.150 |
tolerance | -0.141 |
Sao | -0.140 |
Chair | -0.140 |
TABLE | -0.138 |
Token | cards |
Token ID | 4116 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
Promotion | +0.242 |
tolerance | +0.229 |
Sao | +0.228 |
Chair | +0.227 |
Mania | +0.225 |
Neg logit contributions | |
enhagen | -0.303 |
ighthouse | -0.265 |
�� | -0.255 |
inately | -0.255 |
ighth | -0.254 |
Token | , |
Token ID | 11 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
enhagen | +0.587 |
ighthouse | +0.512 |
inately | +0.493 |
ighth | +0.491 |
�� | +0.489 |
Neg logit contributions | |
Promotion | -0.460 |
tolerance | -0.433 |
Chair | -0.431 |
Sao | -0.429 |
Mania | -0.425 |
Token | we |
Token ID | 356 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Promotion | +0.180 |
tolerance | +0.170 |
Sao | +0.168 |
Chair | +0.168 |
TABLE | +0.166 |
Neg logit contributions | |
enhagen | -0.238 |
ighthouse | -0.209 |
�� | -0.201 |
inately | -0.201 |
ighth | -0.200 |
Token | have |
Token ID | 423 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
Promotion | +0.698 |
tolerance | +0.656 |
Sao | +0.649 |
Chair | +0.648 |
Mania | +0.640 |
Neg logit contributions | |
enhagen | -0.982 |
ighthouse | -0.869 |
�� | -0.835 |
inately | -0.834 |
ighth | -0.833 |
Token | to |
Token ID | 284 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Promotion | +0.552 |
tolerance | +0.520 |
Chair | +0.515 |
Sao | +0.515 |
Mania | +0.509 |
Neg logit contributions | |
enhagen | -0.708 |
ighthouse | -0.621 |
�� | -0.598 |
inately | -0.596 |
ighth | -0.595 |
Token | decide |
Token ID | 5409 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Promotion | +0.851 |
tolerance | +0.802 |
Chair | +0.792 |
Sao | +0.792 |
TABLE | +0.782 |
Neg logit contributions | |
enhagen | -1.200 |
ighthouse | -1.060 |
�� | -1.024 |
inately | -1.017 |
ighth | -1.016 |
Token | whether |
Token ID | 1771 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
enhagen | +1.977 |
ighthouse | +1.732 |
inately | +1.675 |
ighth | +1.660 |
�� | +1.629 |
Neg logit contributions | |
Promotion | -1.733 |
Sao | -1.611 |
Chair | -1.609 |
tolerance | -1.606 |
Mania | -1.605 |
Token | we |
Token ID | 356 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Promotion | +0.378 |
tolerance | +0.356 |
Sao | +0.353 |
Chair | +0.353 |
TABLE | +0.349 |
Neg logit contributions | |
enhagen | -0.489 |
ighthouse | -0.429 |
�� | -0.413 |
inately | -0.412 |
ighth | -0.411 |
Token | 're |
Token ID | 821 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Promotion | +1.093 |
tolerance | +1.031 |
Chair | +1.019 |
Sao | +1.018 |
TABLE | +1.006 |
Neg logit contributions | |
enhagen | -1.506 |
ighthouse | -1.329 |
�� | -1.284 |
inately | -1.274 |
ighth | -1.272 |
Token | needed |
Token ID | 2622 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
enhagen | +1.787 |
ighthouse | +1.584 |
ighth | +1.489 |
�� | +1.472 |
inately | +1.470 |
Neg logit contributions | |
Promotion | -1.334 |
Mania | -1.250 |
tolerance | -1.240 |
Sao | -1.236 |
TABLE | -1.214 |
Token | to |
Token ID | 284 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
enhagen | +0.784 |
ighthouse | +0.689 |
inately | +0.661 |
ighth | +0.657 |
�� | +0.653 |
Neg logit contributions | |
Promotion | -0.579 |
tolerance | -0.543 |
Sao | -0.540 |
Mania | -0.536 |
Chair | -0.535 |
Token | make |
Token ID | 787 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Promotion | +0.325 |
tolerance | +0.301 |
Sao | +0.299 |
Mania | +0.298 |
Chair | +0.297 |
Neg logit contributions | |
enhagen | -0.492 |
ighthouse | -0.441 |
inately | -0.424 |
ighth | -0.423 |
�� | -0.418 |
Token | sure |
Token ID | 1654 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
enhagen | +1.558 |
ighthouse | +1.367 |
ighth | +1.292 |
inately | +1.282 |
�� | +1.270 |
Neg logit contributions | |
Promotion | -1.541 |
Mania | -1.472 |
_______ | -1.442 |
Sao | -1.442 |
tolerance | -1.437 |
Token | future |
Token ID | 2003 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
Promotion | +0.822 |
tolerance | +0.775 |
Sao | +0.767 |
Chair | +0.766 |
TABLE | +0.758 |
Neg logit contributions | |
enhagen | -1.078 |
ighthouse | -0.949 |
�� | -0.915 |
inately | -0.908 |
ighth | -0.907 |
Token | expenses |
Token ID | 9307 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Promotion | +0.362 |
tolerance | +0.338 |
Sao | +0.336 |
Chair | +0.333 |
Mania | +0.333 |
Neg logit contributions | |
enhagen | -0.523 |
ighthouse | -0.465 |
�� | -0.447 |
inately | -0.446 |
ighth | -0.445 |
Token | are |
Token ID | 389 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
Promotion | +0.942 |
tolerance | +0.886 |
Sao | +0.877 |
Chair | +0.876 |
TABLE | +0.866 |
Neg logit contributions | |
enhagen | -1.334 |
ighthouse | -1.178 |
�� | -1.137 |
inately | -1.130 |
ighth | -1.130 |
Token | fully |
Token ID | 3938 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
Promotion | +0.572 |
tolerance | +0.539 |
Chair | +0.534 |
Sao | +0.533 |
TABLE | +0.529 |
Neg logit contributions | |
enhagen | -0.721 |
ighthouse | -0.634 |
�� | -0.611 |
ighth | -0.608 |
inately | -0.607 |
Token | compliant |
Token ID | 31332 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
enhagen | +0.659 |
ighthouse | +0.585 |
ighth | +0.567 |
�� | +0.562 |
inately | +0.560 |
Neg logit contributions | |
Promotion | -0.456 |
tolerance | -0.421 |
Chair | -0.419 |
TABLE | -0.418 |
Sao | -0.417 |
Token | with |
Token ID | 351 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
enhagen | +2.737 |
ighthouse | +2.386 |
inately | +2.298 |
ighth | +2.263 |
�� | +2.247 |
Neg logit contributions | |
Promotion | -2.269 |
tolerance | -2.146 |
Mania | -2.135 |
Sao | -2.128 |
Chair | -2.122 |
Token | a |
Token ID | 257 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
enhagen | +2.793 |
ighthouse | +2.521 |
ighth | +2.365 |
inately | +2.336 |
�� | +2.332 |
Neg logit contributions | |
Promotion | -2.258 |
Mania | -2.215 |
Sao | -2.150 |
_______ | -2.148 |
tolerance | -2.107 |
Token | you |
Token ID | 345 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Promotion | +0.619 |
tolerance | +0.585 |
Sao | +0.579 |
Chair | +0.578 |
Mania | +0.573 |
Neg logit contributions | |
enhagen | -0.750 |
ighthouse | -0.657 |
�� | -0.633 |
inately | -0.628 |
ighth | -0.627 |
Token | can |
Token ID | 460 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Promotion | +0.072 |
tolerance | +0.066 |
Sao | +0.066 |
Chair | +0.066 |
Mania | +0.065 |
Neg logit contributions | |
enhagen | -0.125 |
ighthouse | -0.111 |
ighth | -0.108 |
inately | -0.108 |
�� | -0.107 |
Token | defend |
Token ID | 4404 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
enhagen | +0.918 |
ighthouse | +0.818 |
inately | +0.798 |
ighth | +0.790 |
�� | +0.781 |
Neg logit contributions | |
Promotion | -0.631 |
Sao | -0.586 |
tolerance | -0.584 |
Mania | -0.582 |
Chair | -0.577 |
Token | your |
Token ID | 534 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Promotion | +1.723 |
tolerance | +1.648 |
Chair | +1.622 |
Sao | +1.614 |
TABLE | +1.593 |
Neg logit contributions | |
enhagen | -2.117 |
ighthouse | -1.854 |
�� | -1.795 |
inately | -1.768 |
ighth | -1.765 |
Token | running |
Token ID | 2491 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Promotion | +0.229 |
Sao | +0.214 |
tolerance | +0.214 |
Mania | +0.213 |
Chair | +0.212 |
Neg logit contributions | |
enhagen | -0.317 |
ighthouse | -0.279 |
inately | -0.271 |
�� | -0.270 |
ighth | -0.269 |
Token | mate |
Token ID | 16133 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
enhagen | +0.244 |
ighthouse | +0.212 |
inately | +0.203 |
�� | +0.203 |
ighth | +0.202 |
Neg logit contributions | |
Promotion | -0.231 |
tolerance | -0.218 |
Sao | -0.216 |
Chair | -0.215 |
TABLE | -0.215 |
Token | � |
Token ID | 447 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Promotion | +0.352 |
tolerance | +0.333 |
Chair | +0.329 |
Sao | +0.329 |
TABLE | +0.325 |
Neg logit contributions | |
enhagen | -0.484 |
ighthouse | -0.427 |
�� | -0.413 |
inately | -0.409 |
ighth | -0.409 |
Token | � |
Token ID | 247 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Promotion | +0.177 |
tolerance | +0.169 |
Chair | +0.168 |
Sao | +0.168 |
TABLE | +0.166 |
Neg logit contributions | |
enhagen | -0.145 |
ighthouse | -0.123 |
�� | -0.117 |
inately | -0.116 |
ighth | -0.116 |
Token | s |
Token ID | 82 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
Promotion | +0.249 |
tolerance | +0.236 |
Chair | +0.234 |
Sao | +0.234 |
TABLE | +0.231 |
Neg logit contributions | |
enhagen | -0.296 |
ighthouse | -0.259 |
�� | -0.250 |
inately | -0.248 |
ighth | -0.247 |
Token | position |
Token ID | 2292 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
Promotion | +0.487 |
Sao | +0.454 |
tolerance | +0.453 |
Chair | +0.450 |
Mania | +0.449 |
Neg logit contributions | |
enhagen | -0.691 |
ighthouse | -0.610 |
inately | -0.590 |
ighth | -0.588 |
�� | -0.588 |
Token | . |
Token ID | 13 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
enhagen | +0.758 |
ighthouse | +0.665 |
�� | +0.639 |
inately | +0.636 |
ighth | +0.635 |
Neg logit contributions | |
Promotion | -0.619 |
tolerance | -0.582 |
Sao | -0.578 |
Chair | -0.577 |
TABLE | -0.572 |
Token | and |
Token ID | 392 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Promotion | +0.862 |
tolerance | +0.820 |
Chair | +0.811 |
Sao | +0.811 |
TABLE | +0.802 |
Neg logit contributions | |
enhagen | -0.941 |
ighthouse | -0.818 |
�� | -0.787 |
inately | -0.780 |
ighth | -0.779 |
Token | - |
Token ID | 12 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
Promotion | +0.905 |
tolerance | +0.847 |
Chair | +0.835 |
Sao | +0.834 |
TABLE | +0.823 |
Neg logit contributions | |
enhagen | -1.548 |
ighthouse | -1.381 |
�� | -1.339 |
inately | -1.329 |
ighth | -1.327 |
Token | out |
Token ID | 448 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Promotion | +0.641 |
tolerance | +0.612 |
Sao | +0.607 |
Chair | +0.606 |
TABLE | +0.601 |
Neg logit contributions | |
enhagen | -0.554 |
ighthouse | -0.474 |
�� | -0.452 |
inately | -0.450 |
ighth | -0.449 |
Token | wing |
Token ID | 8539 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
Promotion | +0.296 |
tolerance | +0.279 |
Chair | +0.277 |
Sao | +0.275 |
TABLE | +0.274 |
Neg logit contributions | |
enhagen | -0.376 |
ighthouse | -0.330 |
�� | -0.319 |
inately | -0.318 |
ighth | -0.317 |
Token | ers |
Token ID | 364 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Promotion | +0.420 |
tolerance | +0.394 |
Chair | +0.389 |
Sao | +0.388 |
TABLE | +0.384 |
Neg logit contributions | |
enhagen | -0.635 |
ighthouse | -0.562 |
�� | -0.545 |
ighth | -0.541 |
inately | -0.540 |
Token | , |
Token ID | 11 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
enhagen | +0.223 |
ighthouse | +0.195 |
�� | +0.188 |
inately | +0.187 |
ighth | +0.187 |
Neg logit contributions | |
Promotion | -0.181 |
tolerance | -0.171 |
Chair | -0.169 |
Sao | -0.168 |
TABLE | -0.167 |
Token | and |
Token ID | 290 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Promotion | +0.187 |
tolerance | +0.177 |
Chair | +0.175 |
Sao | +0.175 |
TABLE | +0.174 |
Neg logit contributions | |
enhagen | -0.232 |
ighthouse | -0.204 |
�� | -0.196 |
inately | -0.195 |
ighth | -0.195 |
Token | formed |
Token ID | 7042 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Promotion | +0.615 |
tolerance | +0.581 |
Chair | +0.574 |
Sao | +0.572 |
TABLE | +0.568 |
Neg logit contributions | |
enhagen | -0.779 |
ighthouse | -0.684 |
�� | -0.660 |
inately | -0.656 |
ighth | -0.655 |
Token | a |
Token ID | 257 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Promotion | +1.050 |
tolerance | +0.992 |
Chair | +0.981 |
Sao | +0.980 |
TABLE | +0.970 |
Neg logit contributions | |
enhagen | -1.343 |
ighthouse | -1.180 |
�� | -1.138 |
inately | -1.130 |
ighth | -1.128 |
Token | five |
Token ID | 1936 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
Promotion | +0.734 |
tolerance | +0.694 |
Chair | +0.686 |
Sao | +0.686 |
TABLE | +0.678 |
Neg logit contributions | |
enhagen | -0.932 |
ighthouse | -0.818 |
�� | -0.789 |
inately | -0.783 |
ighth | -0.782 |
Token | - |
Token ID | 12 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
enhagen | +0.769 |
ighthouse | +0.689 |
ighth | +0.664 |
�� | +0.655 |
inately | +0.654 |
Neg logit contributions | |
Promotion | -0.539 |
tolerance | -0.497 |
Chair | -0.495 |
Sao | -0.494 |
TABLE | -0.493 |
Token | part |
Token ID | 636 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
Promotion | +1.528 |
tolerance | +1.436 |
Chair | +1.417 |
Sao | +1.416 |
TABLE | +1.398 |
Neg logit contributions | |
enhagen | -2.371 |
ighthouse | -2.105 |
�� | -2.038 |
inately | -2.023 |
ighth | -2.020 |
Token | of |
Token ID | 286 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
enhagen | +0.353 |
ighthouse | +0.307 |
�� | +0.293 |
ighth | +0.292 |
inately | +0.291 |
Neg logit contributions | |
Promotion | -0.338 |
tolerance | -0.321 |
Sao | -0.318 |
Chair | -0.318 |
TABLE | -0.315 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Promotion | +0.284 |
tolerance | +0.269 |
Chair | +0.266 |
Sao | +0.266 |
Mania | +0.264 |
Neg logit contributions | |
enhagen | -0.391 |
ighthouse | -0.345 |
�� | -0.332 |
ighth | -0.330 |
inately | -0.329 |
Token | original |
Token ID | 2656 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Promotion | +0.621 |
tolerance | +0.585 |
Chair | +0.577 |
Sao | +0.577 |
Mania | +0.572 |
Neg logit contributions | |
enhagen | -0.951 |
ighthouse | -0.843 |
�� | -0.814 |
inately | -0.809 |
ighth | -0.809 |
Token | 802 |
Token ID | 33121 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
enhagen | +0.994 |
ighthouse | +0.880 |
�� | +0.847 |
ighth | +0.844 |
inately | +0.842 |
Neg logit contributions | |
Promotion | -0.666 |
tolerance | -0.631 |
Mania | -0.627 |
Sao | -0.623 |
Chair | -0.622 |
Token | . |
Token ID | 13 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
Promotion | +2.241 |
tolerance | +2.122 |
Chair | +2.102 |
Sao | +2.096 |
TABLE | +2.073 |
Neg logit contributions | |
enhagen | -2.661 |
ighthouse | -2.321 |
�� | -2.249 |
inately | -2.226 |
ighth | -2.212 |
Token | 11 |
Token ID | 1157 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
enhagen | +0.044 |
ighthouse | +0.039 |
�� | +0.038 |
ighth | +0.038 |
inately | +0.037 |
Neg logit contributions | |
Promotion | -0.034 |
tolerance | -0.033 |
Sao | -0.032 |
Chair | -0.032 |
Mania | -0.032 |
Token | standard |
Token ID | 3210 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Promotion | +0.417 |
tolerance | +0.392 |
Sao | +0.388 |
Chair | +0.383 |
Mania | +0.382 |
Neg logit contributions | |
enhagen | -0.780 |
ighthouse | -0.700 |
�� | -0.675 |
ighth | -0.674 |
inately | -0.671 |
Token | ratified |
Token ID | 39067 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Promotion | +1.166 |
tolerance | +1.102 |
Sao | +1.089 |
Chair | +1.089 |
TABLE | +1.075 |
Neg logit contributions | |
enhagen | -1.626 |
ighthouse | -1.434 |
�� | -1.382 |
inately | -1.374 |
ighth | -1.372 |
Token | in |
Token ID | 287 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
Promotion | +1.060 |
tolerance | +0.997 |
Sao | +0.983 |
Chair | +0.983 |
TABLE | +0.974 |
Neg logit contributions | |
enhagen | -1.588 |
ighthouse | -1.409 |
�� | -1.358 |
inately | -1.352 |
ighth | -1.350 |
Token | 1997 |
Token ID | 8309 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
Promotion | +0.459 |
tolerance | +0.436 |
Mania | +0.430 |
TABLE | +0.427 |
Chair | +0.426 |
Neg logit contributions | |
enhagen | -0.593 |
ighthouse | -0.520 |
ighth | -0.500 |
inately | -0.500 |
�� | -0.499 |
Token | flights |
Token ID | 13956 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Promotion | +0.794 |
tolerance | +0.746 |
Chair | +0.729 |
Sao | +0.727 |
TABLE | +0.726 |
Neg logit contributions | |
enhagen | -1.128 |
ighthouse | -0.993 |
�� | -0.958 |
ighth | -0.956 |
inately | -0.950 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Promotion | +0.200 |
tolerance | +0.191 |
Chair | +0.188 |
Sao | +0.187 |
Mania | +0.182 |
Neg logit contributions | |
enhagen | -0.303 |
ighthouse | -0.266 |
�� | -0.263 |
ighth | -0.259 |
inately | -0.258 |
Token | US |
Token ID | 1294 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Promotion | +0.120 |
tolerance | +0.114 |
Mania | +0.112 |
Sao | +0.111 |
Chair | +0.111 |
Neg logit contributions | |
enhagen | -0.146 |
ighthouse | -0.129 |
ighth | -0.125 |
�� | -0.124 |
inately | -0.123 |
Token | on |
Token ID | 319 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Promotion | +0.652 |
tolerance | +0.638 |
Sao | +0.625 |
Chair | +0.619 |
TABLE | +0.616 |
Neg logit contributions | |
enhagen | -0.848 |
ighthouse | -0.734 |
�� | -0.719 |
inately | -0.712 |
ighth | -0.703 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
Promotion | +0.193 |
tolerance | +0.182 |
Chair | +0.179 |
Sao | +0.179 |
TABLE | +0.177 |
Neg logit contributions | |
enhagen | -0.262 |
ighthouse | -0.232 |
�� | -0.224 |
inately | -0.222 |
ighth | -0.222 |
Token | of |
Token ID | 286 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
enhagen | +0.059 |
ighthouse | +0.051 |
�� | +0.049 |
ighth | +0.049 |
inately | +0.048 |
Neg logit contributions | |
Promotion | -0.057 |
tolerance | -0.054 |
Sao | -0.054 |
Chair | -0.054 |
TABLE | -0.053 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
Promotion | +0.250 |
tolerance | +0.237 |
Sao | +0.236 |
Chair | +0.232 |
TABLE | +0.232 |
Neg logit contributions | |
enhagen | -0.418 |
ighthouse | -0.368 |
inately | -0.361 |
�� | -0.357 |
ighth | -0.350 |
Token | - |
Token ID | 12 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
enhagen | +0.048 |
ighthouse | +0.043 |
ighth | +0.042 |
�� | +0.041 |
inately | +0.041 |
Neg logit contributions | |
Promotion | -0.032 |
tolerance | -0.030 |
Sao | -0.030 |
Chair | -0.029 |
Mania | -0.029 |
Token | Kim |
Token ID | 26374 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Promotion | +0.094 |
tolerance | +0.089 |
Sao | +0.089 |
TABLE | +0.089 |
Chair | +0.089 |
Neg logit contributions | |
enhagen | -0.110 |
ighthouse | -0.098 |
ighth | -0.094 |
�� | -0.093 |
inately | -0.092 |
Token | summit |
Token ID | 14237 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
enhagen | +2.085 |
ighthouse | +1.871 |
ighth | +1.805 |
�� | +1.780 |
vre | +1.755 |
Neg logit contributions | |
Promotion | -1.372 |
Oaks | -1.317 |
_______ | -1.282 |
Sao | -1.278 |
tolerance | -1.273 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Promotion | +0.149 |
tolerance | +0.142 |
Sao | +0.140 |
Mania | +0.139 |
Chair | +0.139 |
Neg logit contributions | |
enhagen | -0.199 |
ighthouse | -0.177 |
�� | -0.171 |
ighth | -0.170 |
inately | -0.167 |
Token | * |
Token ID | 9 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
enhagen | +0.363 |
ighthouse | +0.329 |
�� | +0.318 |
ighth | +0.317 |
inately | +0.317 |
Neg logit contributions | |
Promotion | -0.167 |
tolerance | -0.154 |
Sao | -0.151 |
Chair | -0.151 |
TABLE | -0.149 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Promotion | +0.096 |
tolerance | +0.089 |
Chair | +0.088 |
Sao | +0.088 |
TABLE | +0.087 |
Neg logit contributions | |
enhagen | -0.192 |
ighthouse | -0.173 |
�� | -0.168 |
inately | -0.167 |
ighth | -0.166 |
Token | * |
Token ID | 9 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
enhagen | +0.260 |
ighthouse | +0.235 |
�� | +0.228 |
ighth | +0.227 |
inately | +0.227 |
Neg logit contributions | |
Promotion | -0.117 |
tolerance | -0.109 |
Chair | -0.107 |
Sao | -0.107 |
TABLE | -0.105 |
Token | B |
Token ID | 347 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
Promotion | +0.187 |
tolerance | +0.177 |
Chair | +0.174 |
Sao | +0.173 |
Mania | +0.173 |
Neg logit contributions | |
enhagen | -0.246 |
ighthouse | -0.217 |
�� | -0.208 |
ighth | -0.207 |
inately | -0.207 |
Token | ama |
Token ID | 1689 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
enhagen | +0.423 |
ighthouse | +0.366 |
�� | +0.349 |
ighth | +0.348 |
inately | +0.346 |
Neg logit contributions | |
Promotion | -0.434 |
tolerance | -0.414 |
Chair | -0.410 |
Sao | -0.409 |
TABLE | -0.408 |
Token | / |
Token ID | 14 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
enhagen | +1.478 |
ighthouse | +1.299 |
�� | +1.245 |
ighth | +1.245 |
inately | +1.236 |
Neg logit contributions | |
Promotion | -1.108 |
tolerance | -1.059 |
Mania | -1.033 |
Sao | -1.030 |
Chair | -1.029 |
Token | UF |
Token ID | 36820 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
Promotion | +0.097 |
tolerance | +0.091 |
Chair | +0.090 |
Sao | +0.090 |
TABLE | +0.089 |
Neg logit contributions | |
enhagen | -0.141 |
ighthouse | -0.125 |
�� | -0.120 |
ighth | -0.120 |
inately | -0.119 |
Token | Leonard |
Token ID | 20131 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Promotion | +0.041 |
tolerance | +0.039 |
Chair | +0.038 |
Sao | +0.038 |
TABLE | +0.038 |
Neg logit contributions | |
enhagen | -0.053 |
ighthouse | -0.046 |
�� | -0.045 |
ighth | -0.044 |
inately | -0.044 |
Token | Warner |
Token ID | 14469 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
enhagen | +2.701 |
ighthouse | +2.382 |
ighth | +2.293 |
�� | +2.256 |
inately | +2.255 |
Neg logit contributions | |
Promotion | -2.103 |
tolerance | -1.997 |
TABLE | -1.945 |
Chair | -1.923 |
Sao | -1.918 |
Token | LB |
Token ID | 22199 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
enhagen | +0.807 |
ighthouse | +0.713 |
ighth | +0.691 |
�� | +0.688 |
inately | +0.686 |
Neg logit contributions | |
Promotion | -0.558 |
tolerance | -0.527 |
Sao | -0.513 |
Mania | -0.512 |
Chair | -0.512 |
Token | 6 |
Token ID | 718 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
enhagen | +0.871 |
ighthouse | +0.777 |
�� | +0.750 |
ighth | +0.750 |
inately | +0.748 |
Neg logit contributions | |
Promotion | -0.532 |
tolerance | -0.505 |
Mania | -0.492 |
Sao | -0.491 |
Chair | -0.488 |
Token | narrative |
Token ID | 8689 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Promotion | +0.108 |
Sao | +0.100 |
tolerance | +0.100 |
Chair | +0.099 |
Mania | +0.099 |
Neg logit contributions | |
enhagen | -0.191 |
ighthouse | -0.171 |
�� | -0.165 |
ighth | -0.165 |
inately | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
enhagen | +0.451 |
ighthouse | +0.399 |
�� | +0.383 |
ighth | +0.382 |
inately | +0.381 |
Neg logit contributions | |
Promotion | -0.359 |
Sao | -0.335 |
tolerance | -0.334 |
Chair | -0.333 |
Mania | -0.333 |
Token | It |
Token ID | 632 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
enhagen | +0.296 |
ighthouse | +0.263 |
�� | +0.255 |
ighth | +0.254 |
inately | +0.253 |
Neg logit contributions | |
Promotion | -0.180 |
tolerance | -0.174 |
Sao | -0.169 |
Chair | -0.168 |
Mania | -0.167 |
Token | is |
Token ID | 318 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
enhagen | +1.216 |
ighthouse | +1.067 |
�� | +1.025 |
ighth | +1.022 |
inately | +1.018 |
Neg logit contributions | |
Promotion | -0.988 |
Sao | -0.922 |
tolerance | -0.919 |
Chair | -0.919 |
Mania | -0.906 |
Token | a |
Token ID | 257 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
enhagen | +0.494 |
ighthouse | +0.429 |
�� | +0.415 |
ighth | +0.414 |
inately | +0.412 |
Neg logit contributions | |
Promotion | -0.393 |
Sao | -0.370 |
Chair | -0.368 |
tolerance | -0.366 |
TABLE | -0.366 |
Token | rank |
Token ID | 4279 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
enhagen | +0.969 |
ighthouse | +0.848 |
�� | +0.821 |
ighth | +0.820 |
inately | +0.817 |
Neg logit contributions | |
Promotion | -0.736 |
Sao | -0.693 |
Chair | -0.687 |
Mania | -0.685 |
TABLE | -0.684 |
Token | - |
Token ID | 12 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
enhagen | +1.241 |
ighthouse | +1.091 |
inately | +1.064 |
�� | +1.056 |
ighth | +1.052 |
Neg logit contributions | |
Promotion | -0.915 |
Sao | -0.863 |
Chair | -0.859 |
TABLE | -0.859 |
Mania | -0.846 |
Token | ordering |
Token ID | 34555 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Promotion | +0.082 |
tolerance | +0.077 |
Sao | +0.077 |
Chair | +0.077 |
TABLE | +0.076 |
Neg logit contributions | |
enhagen | -0.101 |
ighthouse | -0.089 |
inately | -0.086 |
�� | -0.086 |
ighth | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
enhagen | +1.430 |
ighthouse | +1.246 |
inately | +1.203 |
�� | +1.189 |
ighth | +1.187 |
Neg logit contributions | |
Promotion | -1.270 |
Sao | -1.201 |
Mania | -1.188 |
Chair | -1.187 |
TABLE | -1.185 |
Token | If |
Token ID | 1002 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
enhagen | +0.376 |
ighthouse | +0.335 |
�� | +0.324 |
ighth | +0.324 |
inately | +0.322 |
Neg logit contributions | |
Promotion | -0.221 |
tolerance | -0.213 |
Sao | -0.208 |
Chair | -0.206 |
Mania | -0.204 |
Token | a |
Token ID | 257 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
enhagen | +1.847 |
ighthouse | +1.592 |
inately | +1.547 |
�� | +1.544 |
ighth | +1.535 |
Neg logit contributions | |
Promotion | -1.448 |
Sao | -1.364 |
TABLE | -1.350 |
Chair | -1.345 |
tolerance | -1.342 |
Token | ] |
Token ID | 60 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
Promotion | +0.581 |
tolerance | +0.550 |
Sao | +0.547 |
Chair | +0.545 |
Mania | +0.539 |
Neg logit contributions | |
enhagen | -0.651 |
ighthouse | -0.566 |
�� | -0.544 |
ighth | -0.541 |
inately | -0.540 |
Token | { |
Token ID | 90 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
enhagen | +0.479 |
ighthouse | +0.422 |
ighth | +0.406 |
�� | +0.406 |
inately | +0.405 |
Neg logit contributions | |
Promotion | -0.334 |
tolerance | -0.315 |
Sao | -0.311 |
Chair | -0.310 |
Mania | -0.306 |
Token | options |
Token ID | 25811 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Promotion | +2.282 |
tolerance | +2.184 |
Chair | +2.155 |
Sao | +2.151 |
TABLE | +2.145 |
Neg logit contributions | |
enhagen | -2.256 |
ighthouse | -1.954 |
�� | -1.880 |
inately | -1.859 |
ighth | -1.841 |
Token | } |
Token ID | 92 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
enhagen | +1.317 |
ighthouse | +1.149 |
ighth | +1.105 |
inately | +1.103 |
�� | +1.095 |
Neg logit contributions | |
Promotion | -1.040 |
Sao | -0.977 |
tolerance | -0.969 |
Chair | -0.963 |
Mania | -0.948 |
Token | [ |
Token ID | 685 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
enhagen | +0.125 |
ighthouse | +0.110 |
ighth | +0.106 |
inately | +0.106 |
�� | +0.106 |
Neg logit contributions | |
Promotion | -0.082 |
tolerance | -0.077 |
Sao | -0.076 |
Chair | -0.076 |
Mania | -0.075 |
Token | text |
Token ID | 5239 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Promotion | +1.099 |
tolerance | +1.046 |
Sao | +1.037 |
Chair | +1.036 |
TABLE | +1.023 |
Neg logit contributions | |
enhagen | -1.090 |
ighthouse | -0.941 |
�� | -0.902 |
ighth | -0.895 |
inately | -0.894 |
Token | ] |
Token ID | 60 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
enhagen | +3.034 |
ighthouse | +2.558 |
ighth | +2.495 |
inately | +2.463 |
�� | +2.413 |
Neg logit contributions | |
Promotion | -3.094 |
Sao | -2.936 |
Chair | -2.905 |
tolerance | -2.887 |
Mania | -2.843 |
Token | any |
Token ID | 597 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
enhagen | +0.737 |
ighthouse | +0.647 |
ighth | +0.623 |
�� | +0.623 |
inately | +0.620 |
Neg logit contributions | |
Promotion | -0.538 |
tolerance | -0.506 |
Sao | -0.503 |
Chair | -0.502 |
Mania | -0.491 |
Token | text |
Token ID | 2420 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
Promotion | +0.630 |
tolerance | +0.593 |
Sao | +0.587 |
Chair | +0.587 |
Mania | +0.578 |
Neg logit contributions | |
enhagen | -0.880 |
ighthouse | -0.776 |
�� | -0.750 |
ighth | -0.746 |
inately | -0.745 |
Token | or |
Token ID | 393 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
enhagen | +3.414 |
ighthouse | +2.914 |
ighth | +2.884 |
inately | +2.834 |
achus | +2.822 |
Neg logit contributions | |
Promotion | -2.648 |
Chair | -2.497 |
Sao | -2.496 |
tolerance | -2.454 |
Mania | -2.450 |
Token | empty |
Token ID | 6565 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
enhagen | +1.140 |
ighthouse | +0.997 |
ighth | +0.963 |
inately | +0.961 |
�� | +0.956 |
Neg logit contributions | |
Promotion | -0.851 |
Sao | -0.802 |
Chair | -0.797 |
tolerance | -0.795 |
Mania | -0.787 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
enhagen | +0.538 |
ighthouse | +0.475 |
inately | +0.459 |
ighth | +0.454 |
�� | +0.453 |
Neg logit contributions | |
Promotion | -0.404 |
tolerance | -0.383 |
Mania | -0.377 |
Chair | -0.376 |
TABLE | -0.375 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Promotion | +0.646 |
tolerance | +0.612 |
Chair | +0.604 |
Sao | +0.602 |
TABLE | +0.597 |
Neg logit contributions | |
enhagen | -0.859 |
ighthouse | -0.756 |
�� | -0.726 |
inately | -0.724 |
ighth | -0.721 |
Token | we |
Token ID | 356 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
enhagen | +0.155 |
ighthouse | +0.139 |
�� | +0.134 |
inately | +0.133 |
ighth | +0.133 |
Neg logit contributions | |
Promotion | -0.090 |
tolerance | -0.083 |
Sao | -0.082 |
Chair | -0.082 |
Mania | -0.082 |
Token | had |
Token ID | 550 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
Promotion | +0.822 |
tolerance | +0.777 |
Chair | +0.767 |
Sao | +0.766 |
TABLE | +0.758 |
Neg logit contributions | |
enhagen | -1.125 |
ighthouse | -0.992 |
�� | -0.960 |
inately | -0.951 |
ighth | -0.950 |
Token | begun |
Token ID | 9258 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
enhagen | +0.553 |
ighthouse | +0.487 |
inately | +0.469 |
ighth | +0.466 |
�� | +0.465 |
Neg logit contributions | |
Promotion | -0.416 |
tolerance | -0.390 |
Chair | -0.387 |
Sao | -0.386 |
Mania | -0.385 |
Token | transitioning |
Token ID | 37005 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
Promotion | +0.821 |
tolerance | +0.769 |
Chair | +0.761 |
Sao | +0.760 |
TABLE | +0.751 |
Neg logit contributions | |
enhagen | -1.314 |
ighthouse | -1.170 |
�� | -1.130 |
inately | -1.124 |
ighth | -1.121 |
Token | from |
Token ID | 422 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
enhagen | +3.213 |
ighthouse | +2.856 |
inately | +2.733 |
ighth | +2.681 |
�� | +2.674 |
Neg logit contributions | |
Promotion | -2.751 |
_______ | -2.570 |
Mania | -2.569 |
Chair | -2.564 |
Sao | -2.554 |
Token | PV |
Token ID | 31392 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Promotion | +0.711 |
tolerance | +0.665 |
Chair | +0.659 |
Sao | +0.658 |
Mania | +0.650 |
Neg logit contributions | |
enhagen | -1.113 |
ighthouse | -0.990 |
�� | -0.957 |
inately | -0.952 |
ighth | -0.948 |
Token | to |
Token ID | 284 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Promotion | +0.263 |
tolerance | +0.247 |
Sao | +0.246 |
Chair | +0.245 |
TABLE | +0.242 |
Neg logit contributions | |
enhagen | -0.351 |
ighthouse | -0.311 |
inately | -0.297 |
�� | -0.296 |
ighth | -0.296 |
Token | H |
Token ID | 367 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
enhagen | +0.426 |
ighthouse | +0.383 |
inately | +0.369 |
�� | +0.368 |
ighth | +0.367 |
Neg logit contributions | |
Promotion | -0.238 |
tolerance | -0.221 |
Sao | -0.220 |
Chair | -0.220 |
Mania | -0.219 |
Token | VM |
Token ID | 15996 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
enhagen | +1.037 |
ighthouse | +0.926 |
ighth | +0.881 |
inately | +0.874 |
�� | +0.873 |
Neg logit contributions | |
Promotion | -0.940 |
tolerance | -0.890 |
Sao | -0.880 |
Chair | -0.878 |
TABLE | -0.871 |
Token | The |
Token ID | 464 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
enhagen | +0.405 |
ighthouse | +0.363 |
ighth | +0.348 |
�� | +0.348 |
inately | +0.344 |
Neg logit contributions | |
Promotion | -0.335 |
tolerance | -0.319 |
Sao | -0.316 |
Chair | -0.311 |
TABLE | -0.308 |
Token | visceral |
Token ID | 38259 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
enhagen | +0.973 |
ighthouse | +0.858 |
�� | +0.829 |
inately | +0.827 |
ighth | +0.825 |
Neg logit contributions | |
Promotion | -0.705 |
tolerance | -0.661 |
Mania | -0.660 |
Sao | -0.656 |
TABLE | -0.648 |
Token | phrase |
Token ID | 9546 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
enhagen | +0.886 |
ighthouse | +0.786 |
�� | +0.759 |
ighth | +0.757 |
inately | +0.755 |
Neg logit contributions | |
Promotion | -0.632 |
Sao | -0.582 |
Chair | -0.582 |
tolerance | -0.581 |
Mania | -0.578 |
Token | � |
Token ID | 564 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Promotion | +2.247 |
tolerance | +2.123 |
Chair | +2.093 |
Sao | +2.092 |
TABLE | +2.067 |
Neg logit contributions | |
enhagen | -3.238 |
ighthouse | -2.863 |
�� | -2.766 |
inately | -2.745 |
ighth | -2.742 |
Token | � |
Token ID | 250 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
enhagen | +1.074 |
ighthouse | +0.923 |
�� | +0.909 |
ighth | +0.875 |
inately | +0.867 |
Neg logit contributions | |
Promotion | -1.408 |
tolerance | -1.343 |
Chair | -1.333 |
Sao | -1.332 |
TABLE | -1.322 |
Token | skin |
Token ID | 20407 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
enhagen | +0.855 |
ighthouse | +0.756 |
�� | +0.731 |
ighth | +0.730 |
inately | +0.723 |
Neg logit contributions | |
Promotion | -0.680 |
tolerance | -0.637 |
Chair | -0.634 |
Sao | -0.633 |
TABLE | -0.624 |
Token | in |
Token ID | 287 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
enhagen | +3.032 |
ighthouse | +2.697 |
ighth | +2.632 |
inately | +2.570 |
�� | +2.540 |
Neg logit contributions | |
Promotion | -3.025 |
Sao | -2.866 |
tolerance | -2.836 |
TABLE | -2.830 |
Chair | -2.819 |
Token | the |
Token ID | 262 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
enhagen | +0.596 |
ighthouse | +0.523 |
�� | +0.506 |
ighth | +0.505 |
inately | +0.504 |
Neg logit contributions | |
Promotion | -0.467 |
tolerance | -0.436 |
Sao | -0.432 |
Chair | -0.430 |
Mania | -0.429 |
Token | game |
Token ID | 983 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Promotion | +0.037 |
tolerance | +0.034 |
Sao | +0.034 |
Chair | +0.034 |
Mania | +0.034 |
Neg logit contributions | |
enhagen | -0.059 |
ighthouse | -0.052 |
�� | -0.050 |
inately | -0.050 |
ighth | -0.050 |
Token | � |
Token ID | 447 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
enhagen | +0.355 |
ighthouse | +0.321 |
�� | +0.311 |
inately | +0.310 |
ighth | +0.309 |
Neg logit contributions | |
Promotion | -0.155 |
tolerance | -0.141 |
Sao | -0.140 |
Chair | -0.139 |
Mania | -0.137 |
Token | � |
Token ID | 251 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Promotion | +0.187 |
tolerance | +0.179 |
Sao | +0.177 |
Chair | +0.177 |
TABLE | +0.176 |
Neg logit contributions | |
enhagen | -0.158 |
ighthouse | -0.135 |
�� | -0.130 |
inately | -0.127 |
ighth | -0.127 |
Token | of |
Token ID | 286 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
enhagen | +1.459 |
ighthouse | +1.283 |
�� | +1.220 |
ighth | +1.213 |
inately | +1.209 |
Neg logit contributions | |
Promotion | -1.171 |
Chair | -1.103 |
tolerance | -1.100 |
Sao | -1.095 |
Mania | -1.092 |
Token | his |
Token ID | 465 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
enhagen | +0.340 |
ighthouse | +0.298 |
�� | +0.286 |
inately | +0.284 |
ighth | +0.284 |
Neg logit contributions | |
Promotion | -0.260 |
tolerance | -0.245 |
Chair | -0.243 |
Sao | -0.242 |
Mania | -0.241 |
Token | pedigree |
Token ID | 46895 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
enhagen | +0.827 |
ighthouse | +0.724 |
�� | +0.698 |
inately | +0.693 |
ighth | +0.692 |
Neg logit contributions | |
Promotion | -0.651 |
Chair | -0.612 |
tolerance | -0.610 |
Sao | -0.608 |
TABLE | -0.605 |
Token | as |
Token ID | 355 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
enhagen | +1.021 |
ighthouse | +0.894 |
�� | +0.855 |
ighth | +0.851 |
inately | +0.847 |
Neg logit contributions | |
Promotion | -0.801 |
Chair | -0.760 |
TABLE | -0.751 |
tolerance | -0.749 |
Sao | -0.748 |
Token | an |
Token ID | 281 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Promotion | +1.111 |
tolerance | +1.055 |
Chair | +1.037 |
Sao | +1.036 |
TABLE | +1.024 |
Neg logit contributions | |
enhagen | -1.494 |
ighthouse | -1.315 |
�� | -1.275 |
inately | -1.269 |
ighth | -1.262 |
Token | offensive |
Token ID | 5859 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
Promotion | +0.437 |
tolerance | +0.416 |
Sao | +0.412 |
Chair | +0.412 |
TABLE | +0.407 |
Neg logit contributions | |
enhagen | -0.457 |
ighthouse | -0.396 |
�� | -0.381 |
inately | -0.377 |
ighth | -0.376 |
Token | coordinator |
Token ID | 16052 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
enhagen | +3.328 |
ighthouse | +2.917 |
�� | +2.807 |
ighth | +2.784 |
inately | +2.779 |
Neg logit contributions | |
Promotion | -3.164 |
Mania | -2.958 |
Sao | -2.955 |
TABLE | -2.953 |
Chair | -2.942 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
enhagen | +3.853 |
ighthouse | +3.291 |
�� | +3.156 |
ighth | +3.144 |
inately | +3.125 |
Neg logit contributions | |
Promotion | -3.418 |
Mania | -3.248 |
Chair | -3.231 |
_______ | -3.210 |
Sao | -3.195 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Promotion | +0.068 |
tolerance | +0.064 |
Sao | +0.063 |
Chair | +0.063 |
Mania | +0.063 |
Neg logit contributions | |
enhagen | -0.098 |
ighthouse | -0.087 |
�� | -0.084 |
inately | -0.083 |
ighth | -0.083 |
Token | � |
Token ID | 447 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
enhagen | +1.124 |
ighthouse | +1.031 |
ighth | +0.998 |
inately | +0.996 |
�� | +0.992 |
Neg logit contributions | |
Promotion | -0.381 |
tolerance | -0.346 |
Sao | -0.339 |
Chair | -0.337 |
TABLE | -0.329 |
Token | � |
Token ID | 247 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
enhagen | +0.340 |
ighthouse | +0.291 |
�� | +0.277 |
ighth | +0.273 |
inately | +0.272 |
Neg logit contributions | |
Promotion | -0.453 |
tolerance | -0.433 |
Sao | -0.428 |
Chair | -0.427 |
TABLE | -0.425 |
Token | Chancellor |
Token ID | 19477 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
Promotion | +0.141 |
tolerance | +0.132 |
Sao | +0.131 |
Chair | +0.130 |
TABLE | +0.130 |
Neg logit contributions | |
enhagen | -0.200 |
ighthouse | -0.177 |
�� | -0.171 |
inately | -0.170 |
ighth | -0.169 |
Token | Angela |
Token ID | 17799 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
enhagen | +4.243 |
ighthouse | +3.682 |
inately | +3.570 |
achus | +3.530 |
ighth | +3.508 |
Neg logit contributions | |
Promotion | -3.043 |
tolerance | -2.825 |
TABLE | -2.819 |
Sao | -2.802 |
Chair | -2.758 |
Token | Merkel |
Token ID | 18263 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
enhagen | +0.496 |
ighthouse | +0.440 |
�� | +0.421 |
inately | +0.420 |
ighth | +0.419 |
Neg logit contributions | |
Promotion | -0.351 |
tolerance | -0.330 |
Sao | -0.326 |
Chair | -0.326 |
TABLE | -0.325 |
Token | over |
Token ID | 625 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
enhagen | +1.891 |
ighthouse | +1.657 |
inately | +1.586 |
ighth | +1.572 |
�� | +1.570 |
Neg logit contributions | |
Promotion | -1.532 |
tolerance | -1.428 |
Sao | -1.423 |
Chair | -1.419 |
TABLE | -1.414 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
enhagen | +0.826 |
ighthouse | +0.725 |
�� | +0.697 |
ighth | +0.693 |
inately | +0.692 |
Neg logit contributions | |
Promotion | -0.634 |
tolerance | -0.591 |
Mania | -0.591 |
Sao | -0.590 |
Chair | -0.589 |
Token | " |
Token ID | 366 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
enhagen | +2.315 |
ighthouse | +2.022 |
�� | +1.949 |
ighth | +1.940 |
inately | +1.939 |
Neg logit contributions | |
Promotion | -1.707 |
Mania | -1.628 |
TABLE | -1.612 |
_______ | -1.595 |
Sao | -1.592 |
Token | crazy |
Token ID | 50112 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
enhagen | +3.248 |
ighthouse | +2.882 |
�� | +2.757 |
ighth | +2.728 |
inately | +2.685 |
Neg logit contributions | |
Promotion | -3.023 |
Sao | -2.913 |
Chair | -2.876 |
TABLE | -2.872 |
tolerance | -2.844 |
Token | " |
Token ID | 1 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Promotion | +0.366 |
Sao | +0.343 |
tolerance | +0.340 |
Chair | +0.339 |
Mania | +0.338 |
Neg logit contributions | |
enhagen | -0.516 |
ighthouse | -0.455 |
�� | -0.436 |
ighth | -0.436 |
inately | -0.435 |
Token | Russian |
Token ID | 3394 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
enhagen | +1.913 |
ighthouse | +1.671 |
inately | +1.605 |
ighth | +1.603 |
�� | +1.590 |
Neg logit contributions | |
Promotion | -1.397 |
Mania | -1.326 |
TABLE | -1.314 |
Sao | -1.305 |
_______ | -1.304 |
Token | leader |
Token ID | 3554 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
Promotion | +1.027 |
tolerance | +0.963 |
Sao | +0.957 |
Chair | +0.953 |
Mania | +0.948 |
Neg logit contributions | |
enhagen | -1.427 |
ighthouse | -1.259 |
�� | -1.214 |
inately | -1.209 |
ighth | -1.206 |
Token | who |
Token ID | 508 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
enhagen | +0.634 |
ighthouse | +0.558 |
inately | +0.538 |
�� | +0.536 |
ighth | +0.532 |
Neg logit contributions | |
Promotion | -0.480 |
tolerance | -0.448 |
Chair | -0.446 |
Sao | -0.445 |
TABLE | -0.442 |