Token | related |
Token ID | 3519 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
margins | +0.554 |
rig | +0.519 |
agy | +0.469 |
hetical | +0.464 |
spiders | +0.443 |
Neg logit contributions | |
henko | -0.641 |
ramid | -0.573 |
� | -0.547 |
��� | -0.527 |
LV | -0.526 |
Token | cases |
Token ID | 2663 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
margins | +0.242 |
rig | +0.227 |
agy | +0.206 |
hetical | +0.204 |
spiders | +0.193 |
Neg logit contributions | |
henko | -0.302 |
ramid | -0.271 |
� | -0.259 |
LV | -0.249 |
��� | -0.247 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
henko | +0.293 |
ramid | +0.260 |
� | +0.249 |
��� | +0.239 |
LV | +0.239 |
Neg logit contributions | |
margins | -0.268 |
rig | -0.252 |
agy | -0.228 |
hetical | -0.226 |
spiders | -0.216 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-03 |
Pos logit contributions | |
margins | +0.337 |
rig | +0.316 |
agy | +0.286 |
hetical | +0.283 |
spiders | +0.270 |
Neg logit contributions | |
henko | -0.398 |
ramid | -0.356 |
� | -0.340 |
LV | -0.327 |
��� | -0.327 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
henko | +0.004 |
ramid | +0.003 |
� | +0.003 |
LV | +0.003 |
��� | +0.003 |
Neg logit contributions | |
margins | -0.003 |
rig | -0.003 |
agy | -0.003 |
hetical | -0.003 |
spiders | -0.003 |
Token | Court |
Token ID | 3078 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
margins | +3.191 |
rig | +3.030 |
agy | +2.776 |
hetical | +2.759 |
spiders | +2.678 |
Neg logit contributions | |
henko | -2.265 |
ramid | -1.988 |
� | -1.873 |
��� | -1.852 |
LV | -1.751 |
Token | found |
Token ID | 1043 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
margins | +4.727 |
rig | +4.426 |
agy | +3.942 |
hetical | +3.882 |
spiders | +3.748 |
Neg logit contributions | |
henko | -5.318 |
ramid | -4.853 |
� | -4.588 |
��� | -4.423 |
LV | -4.360 |
Token | that |
Token ID | 326 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
margins | +1.960 |
rig | +1.840 |
agy | +1.662 |
hetical | +1.649 |
spiders | +1.583 |
Neg logit contributions | |
henko | -2.065 |
ramid | -1.845 |
� | -1.753 |
��� | -1.687 |
LV | -1.683 |
Token | while |
Token ID | 981 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
margins | +0.548 |
rig | +0.518 |
agy | +0.476 |
hetical | +0.470 |
spiders | +0.451 |
Neg logit contributions | |
henko | -0.512 |
ramid | -0.451 |
� | -0.428 |
LV | -0.410 |
��� | -0.409 |
Token | the |
Token ID | 262 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
margins | +0.478 |
rig | +0.449 |
agy | +0.408 |
hetical | +0.403 |
spiders | +0.386 |
Neg logit contributions | |
henko | -0.522 |
ramid | -0.465 |
� | -0.444 |
LV | -0.426 |
��� | -0.426 |
Token | Canadian |
Token ID | 5398 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
margins | +0.169 |
rig | +0.159 |
agy | +0.144 |
hetical | +0.142 |
spiders | +0.136 |
Neg logit contributions | |
henko | -0.190 |
ramid | -0.170 |
� | -0.162 |
LV | -0.156 |
��� | -0.155 |
Token | cases |
Token ID | 2663 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
margins | +1.321 |
rig | +1.217 |
agy | +1.077 |
hetical | +1.059 |
spiders | +1.027 |
Neg logit contributions | |
henko | -1.822 |
ramid | -1.649 |
� | -1.569 |
��� | -1.536 |
LV | -1.521 |
Token | are |
Token ID | 389 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
margins | +0.938 |
rig | +0.880 |
agy | +0.792 |
hetical | +0.783 |
spiders | +0.750 |
Neg logit contributions | |
henko | -1.086 |
ramid | -0.973 |
� | -0.927 |
��� | -0.896 |
LV | -0.893 |
Token | filed |
Token ID | 5717 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
henko | +0.431 |
ramid | +0.389 |
� | +0.372 |
LV | +0.359 |
��� | +0.358 |
Neg logit contributions | |
margins | -0.323 |
rig | -0.300 |
agy | -0.271 |
hetical | -0.267 |
spiders | -0.253 |
Token | . |
Token ID | 13 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
margins | +0.567 |
rig | +0.532 |
agy | +0.481 |
hetical | +0.476 |
spiders | +0.456 |
Neg logit contributions | |
henko | -0.630 |
ramid | -0.563 |
� | -0.535 |
��� | -0.516 |
LV | -0.515 |
Token | Whatever |
Token ID | 15935 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
henko | +0.084 |
ramid | +0.075 |
� | +0.071 |
��� | +0.068 |
LV | +0.068 |
Neg logit contributions | |
margins | -0.077 |
rig | -0.073 |
agy | -0.066 |
hetical | -0.065 |
spiders | -0.062 |
Token | recon |
Token ID | 8195 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
margins | +0.996 |
rig | +0.927 |
agy | +0.820 |
hetical | +0.809 |
spiders | +0.779 |
Neg logit contributions | |
henko | -1.314 |
ramid | -1.187 |
� | -1.131 |
��� | -1.099 |
LV | -1.091 |
Token | figured |
Token ID | 46296 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
margins | +4.612 |
rig | +4.365 |
agy | +3.901 |
hetical | +3.835 |
spiders | +3.690 |
Neg logit contributions | |
henko | -5.210 |
ramid | -4.713 |
��� | -4.406 |
� | -4.400 |
LV | -4.284 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
margins | +1.205 |
rig | +1.121 |
agy | +1.001 |
hetical | +0.990 |
spiders | +0.949 |
Neg logit contributions | |
henko | -1.509 |
ramid | -1.359 |
� | -1.297 |
��� | -1.253 |
LV | -1.248 |
Token | Court |
Token ID | 3078 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
margins | +2.408 |
rig | +2.289 |
agy | +2.115 |
hetical | +2.100 |
spiders | +2.035 |
Neg logit contributions | |
henko | -1.595 |
ramid | -1.384 |
� | -1.288 |
��� | -1.236 |
LV | -1.212 |
Token | emerges |
Token ID | 25457 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
margins | +3.643 |
rig | +3.343 |
agy | +2.884 |
hetical | +2.781 |
spiders | +2.722 |
Neg logit contributions | |
henko | -5.585 |
ramid | -5.096 |
� | -4.824 |
��� | -4.711 |
LV | -4.652 |
Token | after |
Token ID | 706 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
margins | +1.248 |
rig | +1.174 |
agy | +1.068 |
hetical | +1.057 |
spiders | +1.015 |
Neg logit contributions | |
henko | -1.260 |
ramid | -1.123 |
� | -1.064 |
��� | -1.025 |
LV | -1.021 |
Token | ) |
Token ID | 8 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
margins | +0.456 |
rig | +0.428 |
agy | +0.385 |
hetical | +0.381 |
spiders | +0.363 |
Neg logit contributions | |
henko | -0.547 |
ramid | -0.492 |
� | -0.469 |
��� | -0.457 |
LV | -0.451 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
margins | +0.101 |
rig | +0.094 |
agy | +0.085 |
hetical | +0.084 |
spiders | +0.080 |
Neg logit contributions | |
henko | -0.118 |
ramid | -0.106 |
� | -0.101 |
��� | -0.097 |
LV | -0.097 |
Token | United |
Token ID | 17013 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
henko | +0.129 |
ramid | +0.113 |
� | +0.106 |
��� | +0.102 |
LV | +0.101 |
Neg logit contributions | |
margins | -0.159 |
rig | -0.151 |
agy | -0.139 |
hetical | -0.138 |
spiders | -0.133 |
Token | States |
Token ID | 1829 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
henko | +0.359 |
ramid | +0.316 |
� | +0.300 |
LV | +0.286 |
��� | +0.285 |
Neg logit contributions | |
margins | -0.411 |
rig | -0.389 |
agy | -0.356 |
hetical | -0.354 |
spiders | -0.339 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
margins | +1.289 |
rig | +1.214 |
agy | +1.100 |
hetical | +1.091 |
spiders | +1.056 |
Neg logit contributions | |
henko | -1.283 |
ramid | -1.142 |
� | -1.080 |
��� | -1.040 |
LV | -1.033 |
Token | Court |
Token ID | 3078 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
margins | +2.508 |
rig | +2.387 |
agy | +2.193 |
hetical | +2.184 |
spiders | +2.124 |
Neg logit contributions | |
henko | -1.706 |
ramid | -1.492 |
� | -1.390 |
��� | -1.343 |
LV | -1.304 |
Token | case |
Token ID | 1339 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
margins | +4.380 |
rig | +4.139 |
agy | +3.704 |
hetical | +3.602 |
spiders | +3.506 |
Neg logit contributions | |
henko | -5.361 |
ramid | -4.812 |
� | -4.600 |
��� | -4.442 |
LV | -4.367 |
Token |
|
Token ID | 198 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
margins | +3.293 |
rig | +3.063 |
agy | +2.759 |
hetical | +2.732 |
spiders | +2.646 |
Neg logit contributions | |
henko | -3.634 |
ramid | -3.291 |
� | -3.107 |
��� | -3.015 |
LV | -2.964 |
Token |
|
Token ID | 198 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
margins | +1.106 |
rig | +1.039 |
agy | +0.930 |
hetical | +0.917 |
spiders | +0.873 |
Neg logit contributions | |
henko | -1.386 |
ramid | -1.247 |
� | -1.182 |
��� | -1.180 |
LV | -1.135 |
Token | Santa |
Token ID | 42694 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
margins | +1.175 |
rig | +1.126 |
agy | +1.028 |
hetical | +1.019 |
spiders | +0.978 |
Neg logit contributions | |
henko | -0.936 |
ramid | -0.815 |
� | -0.763 |
��� | -0.744 |
LV | -0.720 |
Token | Clara |
Token ID | 27443 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
margins | +1.322 |
rig | +1.228 |
agy | +1.091 |
hetical | +1.078 |
spiders | +1.024 |
Neg logit contributions | |
henko | -1.911 |
ramid | -1.734 |
� | -1.662 |
��� | -1.607 |
LV | -1.602 |
Token | not |
Token ID | 407 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
henko | +0.214 |
ramid | +0.192 |
� | +0.183 |
��� | +0.177 |
LV | +0.176 |
Neg logit contributions | |
margins | -0.179 |
rig | -0.168 |
agy | -0.151 |
hetical | -0.150 |
spiders | -0.143 |
Token | only |
Token ID | 691 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
henko | +0.735 |
ramid | +0.657 |
� | +0.628 |
LV | +0.604 |
��� | +0.603 |
Neg logit contributions | |
margins | -0.616 |
rig | -0.581 |
agy | -0.524 |
hetical | -0.518 |
spiders | -0.491 |
Token | through |
Token ID | 832 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
margins | +0.250 |
rig | +0.235 |
agy | +0.213 |
hetical | +0.212 |
spiders | +0.203 |
Neg logit contributions | |
henko | -0.260 |
ramid | -0.231 |
� | -0.220 |
��� | -0.211 |
LV | -0.211 |
Token | numerous |
Token ID | 6409 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
margins | +0.416 |
rig | +0.389 |
agy | +0.351 |
hetical | +0.347 |
spiders | +0.330 |
Neg logit contributions | |
henko | -0.506 |
ramid | -0.454 |
� | -0.434 |
��� | -0.418 |
LV | -0.418 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
margins | +0.041 |
rig | +0.038 |
agy | +0.035 |
hetical | +0.034 |
spiders | +0.032 |
Neg logit contributions | |
henko | -0.049 |
ramid | -0.044 |
� | -0.042 |
LV | -0.041 |
��� | -0.041 |
Token | Court |
Token ID | 3078 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
margins | +3.579 |
rig | +3.377 |
hetical | +3.085 |
agy | +3.077 |
spiders | +2.993 |
Neg logit contributions | |
henko | -2.513 |
ramid | -2.234 |
� | -2.070 |
��� | -2.012 |
LV | -1.949 |
Token | and |
Token ID | 290 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
margins | +3.912 |
rig | +3.601 |
agy | +3.140 |
hetical | +3.097 |
spiders | +2.953 |
Neg logit contributions | |
henko | -5.890 |
ramid | -5.410 |
� | -5.101 |
��� | -4.994 |
LV | -4.963 |
Token | other |
Token ID | 584 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
margins | +0.451 |
rig | +0.424 |
agy | +0.386 |
hetical | +0.382 |
spiders | +0.365 |
Neg logit contributions | |
henko | -0.477 |
ramid | -0.425 |
� | -0.405 |
��� | -0.390 |
LV | -0.389 |
Token | court |
Token ID | 2184 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
henko | +0.115 |
ramid | +0.103 |
� | +0.099 |
LV | +0.096 |
��� | +0.095 |
Neg logit contributions | |
margins | -0.087 |
rig | -0.081 |
agy | -0.074 |
hetical | -0.073 |
spiders | -0.069 |
Token | decisions |
Token ID | 5370 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
margins | +2.999 |
rig | +2.763 |
agy | +2.398 |
hetical | +2.375 |
spiders | +2.247 |
Neg logit contributions | |
henko | -4.800 |
ramid | -4.404 |
� | -4.171 |
��� | -4.078 |
LV | -4.062 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
margins | +2.740 |
rig | +2.552 |
agy | +2.290 |
hetical | +2.269 |
spiders | +2.171 |
Neg logit contributions | |
henko | -3.248 |
ramid | -2.946 |
� | -2.756 |
��� | -2.704 |
LV | -2.677 |
Token | rick |
Token ID | 5557 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
henko | +0.008 |
ramid | +0.007 |
� | +0.007 |
LV | +0.007 |
��� | +0.007 |
Neg logit contributions | |
margins | -0.007 |
rig | -0.007 |
agy | -0.006 |
hetical | -0.006 |
spiders | -0.006 |
Token | Garland |
Token ID | 35466 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
margins | +0.300 |
rig | +0.282 |
agy | +0.262 |
hetical | +0.261 |
spiders | +0.249 |
Neg logit contributions | |
henko | -0.246 |
ramid | -0.211 |
� | -0.204 |
LV | -0.194 |
��� | -0.191 |
Token | to |
Token ID | 284 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
margins | +0.206 |
rig | +0.193 |
agy | +0.174 |
hetical | +0.172 |
spiders | +0.164 |
Neg logit contributions | |
henko | -0.249 |
ramid | -0.225 |
� | -0.214 |
��� | -0.206 |
LV | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
henko | +0.030 |
ramid | +0.027 |
� | +0.026 |
LV | +0.025 |
��� | +0.025 |
Neg logit contributions | |
margins | -0.026 |
rig | -0.024 |
agy | -0.022 |
hetical | -0.022 |
spiders | -0.021 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
henko | +0.037 |
ramid | +0.033 |
� | +0.031 |
LV | +0.030 |
��� | +0.030 |
Neg logit contributions | |
margins | -0.039 |
rig | -0.036 |
agy | -0.033 |
hetical | -0.033 |
spiders | -0.032 |
Token | Court |
Token ID | 3078 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
margins | +3.183 |
rig | +3.039 |
agy | +2.781 |
hetical | +2.766 |
spiders | +2.683 |
Neg logit contributions | |
henko | -2.276 |
ramid | -1.998 |
� | -1.875 |
��� | -1.851 |
LV | -1.748 |
Token | . |
Token ID | 13 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
margins | +4.151 |
rig | +3.950 |
agy | +3.547 |
hetical | +3.392 |
spiders | +3.305 |
Neg logit contributions | |
henko | -5.392 |
ramid | -4.924 |
� | -4.580 |
��� | -4.521 |
LV | -4.375 |
Token | In |
Token ID | 554 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
margins | +0.159 |
rig | +0.150 |
agy | +0.136 |
hetical | +0.135 |
spiders | +0.130 |
Neg logit contributions | |
henko | -0.158 |
ramid | -0.141 |
� | -0.132 |
��� | -0.130 |
LV | -0.126 |
Token | March |
Token ID | 2805 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
henko | +0.046 |
ramid | +0.041 |
� | +0.039 |
��� | +0.038 |
LV | +0.038 |
Neg logit contributions | |
margins | -0.039 |
rig | -0.036 |
agy | -0.033 |
hetical | -0.032 |
spiders | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
margins | +0.151 |
rig | +0.142 |
agy | +0.129 |
hetical | +0.127 |
spiders | +0.122 |
Neg logit contributions | |
henko | -0.167 |
ramid | -0.150 |
� | -0.142 |
��� | -0.137 |
LV | -0.137 |
Token | according |
Token ID | 1864 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
henko | +0.448 |
ramid | +0.398 |
� | +0.379 |
LV | +0.364 |
��� | +0.364 |
Neg logit contributions | |
margins | -0.432 |
rig | -0.407 |
agy | -0.370 |
hetical | -0.366 |
spiders | -0.351 |
Token | while |
Token ID | 981 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
henko | +0.415 |
ramid | +0.367 |
� | +0.353 |
LV | +0.340 |
��� | +0.336 |
Neg logit contributions | |
margins | -0.369 |
rig | -0.346 |
agy | -0.314 |
hetical | -0.312 |
spiders | -0.298 |
Token | it |
Token ID | 340 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
margins | +0.510 |
rig | +0.479 |
agy | +0.432 |
hetical | +0.428 |
spiders | +0.408 |
Neg logit contributions | |
henko | -0.604 |
ramid | -0.540 |
� | -0.517 |
��� | -0.497 |
LV | -0.496 |
Token | asks |
Token ID | 7893 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
margins | +0.365 |
rig | +0.342 |
agy | +0.307 |
hetical | +0.305 |
spiders | +0.289 |
Neg logit contributions | |
henko | -0.447 |
ramid | -0.399 |
� | -0.383 |
��� | -0.369 |
LV | -0.367 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
margins | +0.325 |
rig | +0.306 |
agy | +0.276 |
hetical | +0.274 |
spiders | +0.260 |
Neg logit contributions | |
henko | -0.387 |
ramid | -0.345 |
� | -0.332 |
LV | -0.319 |
��� | -0.317 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
margins | +0.482 |
rig | +0.452 |
agy | +0.408 |
hetical | +0.404 |
spiders | +0.387 |
Neg logit contributions | |
henko | -0.537 |
ramid | -0.480 |
� | -0.458 |
��� | -0.440 |
LV | -0.440 |
Token | Court |
Token ID | 3078 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
margins | +2.696 |
rig | +2.562 |
agy | +2.359 |
hetical | +2.343 |
spiders | +2.270 |
Neg logit contributions | |
henko | -1.843 |
ramid | -1.603 |
� | -1.509 |
��� | -1.470 |
LV | -1.418 |
Token | to |
Token ID | 284 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
margins | +4.185 |
rig | +3.928 |
agy | +3.487 |
hetical | +3.386 |
spiders | +3.266 |
Neg logit contributions | |
henko | -5.393 |
ramid | -4.859 |
� | -4.571 |
LV | -4.458 |
��� | -4.455 |
Token | hear |
Token ID | 3285 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
margins | +0.457 |
rig | +0.431 |
agy | +0.387 |
hetical | +0.387 |
spiders | +0.366 |
Neg logit contributions | |
henko | -0.558 |
ramid | -0.499 |
� | -0.478 |
LV | -0.461 |
��� | -0.460 |
Token | its |
Token ID | 663 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
margins | +0.432 |
rig | +0.405 |
agy | +0.365 |
hetical | +0.361 |
spiders | +0.343 |
Neg logit contributions | |
henko | -0.551 |
ramid | -0.495 |
� | -0.475 |
LV | -0.457 |
��� | -0.456 |
Token | appeal |
Token ID | 5198 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
margins | +0.347 |
rig | +0.325 |
agy | +0.293 |
hetical | +0.290 |
spiders | +0.274 |
Neg logit contributions | |
henko | -0.468 |
ramid | -0.421 |
� | -0.404 |
LV | -0.390 |
��� | -0.388 |
Token | of |
Token ID | 286 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
margins | +1.457 |
rig | +1.367 |
agy | +1.232 |
hetical | +1.218 |
spiders | +1.166 |
Neg logit contributions | |
henko | -1.676 |
ramid | -1.504 |
� | -1.433 |
��� | -1.382 |
LV | -1.377 |
Token | working |
Token ID | 1762 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
henko | +0.337 |
ramid | +0.307 |
� | +0.294 |
��� | +0.285 |
LV | +0.285 |
Neg logit contributions | |
margins | -0.213 |
rig | -0.197 |
agy | -0.174 |
hetical | -0.172 |
spiders | -0.163 |
Token | on |
Token ID | 319 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
margins | +0.360 |
rig | +0.336 |
agy | +0.302 |
hetical | +0.298 |
spiders | +0.285 |
Neg logit contributions | |
henko | -0.449 |
ramid | -0.404 |
� | -0.386 |
��� | -0.372 |
LV | -0.371 |
Token | , |
Token ID | 11 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
margins | +0.457 |
rig | +0.428 |
agy | +0.386 |
hetical | +0.382 |
spiders | +0.365 |
Neg logit contributions | |
henko | -0.532 |
ramid | -0.477 |
� | -0.455 |
��� | -0.439 |
LV | -0.438 |
Token | we |
Token ID | 356 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
margins | +0.501 |
rig | +0.467 |
agy | +0.416 |
hetical | +0.411 |
spiders | +0.390 |
Neg logit contributions | |
henko | -0.695 |
ramid | -0.627 |
� | -0.601 |
LV | -0.580 |
��� | -0.580 |
Token | can |
Token ID | 460 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
margins | +0.595 |
rig | +0.559 |
agy | +0.507 |
hetical | +0.504 |
spiders | +0.483 |
Neg logit contributions | |
henko | -0.632 |
ramid | -0.563 |
� | -0.537 |
��� | -0.519 |
LV | -0.515 |
Token | recon |
Token ID | 8195 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
margins | +0.866 |
rig | +0.804 |
agy | +0.718 |
hetical | +0.712 |
spiders | +0.677 |
Neg logit contributions | |
henko | -1.197 |
ramid | -1.082 |
� | -1.038 |
��� | -1.009 |
LV | -1.003 |
Token | f |
Token ID | 69 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
margins | +4.798 |
rig | +4.587 |
agy | +4.137 |
hetical | +4.079 |
spiders | +3.943 |
Neg logit contributions | |
henko | -4.650 |
ramid | -4.121 |
� | -3.863 |
��� | -3.860 |
LV | -3.751 |
Token | irm |
Token ID | 2533 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
henko | +1.019 |
ramid | +0.914 |
� | +0.871 |
LV | +0.842 |
��� | +0.828 |
Neg logit contributions | |
margins | -0.898 |
rig | -0.834 |
agy | -0.757 |
hetical | -0.750 |
spiders | -0.720 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
margins | +0.817 |
rig | +0.767 |
agy | +0.694 |
hetical | +0.687 |
spiders | +0.658 |
Neg logit contributions | |
henko | -0.901 |
ramid | -0.805 |
� | -0.767 |
��� | -0.738 |
LV | -0.736 |
Token | we |
Token ID | 356 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
margins | +0.233 |
rig | +0.218 |
agy | +0.197 |
hetical | +0.194 |
spiders | +0.185 |
Neg logit contributions | |
henko | -0.285 |
ramid | -0.256 |
� | -0.245 |
LV | -0.236 |
��� | -0.236 |
Token | are |
Token ID | 389 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
margins | +0.599 |
rig | +0.565 |
agy | +0.513 |
hetical | +0.509 |
spiders | +0.489 |
Neg logit contributions | |
henko | -0.608 |
ramid | -0.540 |
� | -0.515 |
��� | -0.494 |
LV | -0.492 |
Token |
|
Token ID | 198 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
margins | +0.572 |
rig | +0.538 |
agy | +0.484 |
hetical | +0.479 |
spiders | +0.458 |
Neg logit contributions | |
henko | -0.647 |
ramid | -0.580 |
� | -0.550 |
��� | -0.534 |
LV | -0.527 |
Token |
|
Token ID | 198 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
margins | +0.729 |
rig | +0.683 |
agy | +0.615 |
hetical | +0.609 |
spiders | +0.581 |
Neg logit contributions | |
henko | -0.864 |
ramid | -0.775 |
� | -0.740 |
��� | -0.713 |
LV | -0.712 |
Token | The |
Token ID | 464 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
margins | +0.726 |
rig | +0.694 |
agy | +0.633 |
hetical | +0.628 |
spiders | +0.602 |
Neg logit contributions | |
henko | -0.589 |
ramid | -0.515 |
� | -0.481 |
��� | -0.472 |
LV | -0.454 |
Token | state |
Token ID | 1181 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
margins | +0.077 |
rig | +0.072 |
agy | +0.065 |
hetical | +0.064 |
spiders | +0.061 |
Neg logit contributions | |
henko | -0.094 |
ramid | -0.084 |
� | -0.080 |
LV | -0.077 |
��� | -0.077 |
Token | supreme |
Token ID | 17700 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
margins | +0.454 |
rig | +0.426 |
agy | +0.384 |
hetical | +0.381 |
spiders | +0.366 |
Neg logit contributions | |
henko | -0.497 |
ramid | -0.443 |
� | -0.422 |
��� | -0.405 |
LV | -0.404 |
Token | court |
Token ID | 2184 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
margins | +1.198 |
rig | +1.118 |
agy | +1.010 |
hetical | +1.006 |
spiders | +0.979 |
Neg logit contributions | |
henko | -1.179 |
ramid | -1.056 |
� | -0.996 |
��� | -0.963 |
LV | -0.953 |
Token | rejected |
Token ID | 8606 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
margins | +4.097 |
rig | +3.790 |
agy | +3.359 |
hetical | +3.268 |
spiders | +3.207 |
Neg logit contributions | |
henko | -5.269 |
ramid | -4.802 |
� | -4.530 |
��� | -4.409 |
LV | -4.326 |
Token | allegations |
Token ID | 7636 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
margins | +1.230 |
rig | +1.148 |
agy | +1.031 |
hetical | +1.019 |
spiders | +0.975 |
Neg logit contributions | |
henko | -1.502 |
ramid | -1.350 |
� | -1.290 |
��� | -1.242 |
LV | -1.240 |
Token | that |
Token ID | 326 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
margins | +0.810 |
rig | +0.763 |
agy | +0.687 |
hetical | +0.682 |
spiders | +0.654 |
Neg logit contributions | |
henko | -0.864 |
ramid | -0.774 |
� | -0.734 |
��� | -0.710 |
LV | -0.704 |
Token | secretive |
Token ID | 32654 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
margins | +0.697 |
rig | +0.653 |
agy | +0.588 |
hetical | +0.582 |
spiders | +0.556 |
Neg logit contributions | |
henko | -0.823 |
ramid | -0.738 |
� | -0.704 |
��� | -0.678 |
LV | -0.678 |
Token | tax |
Token ID | 1687 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
margins | +1.269 |
rig | +1.188 |
agy | +1.069 |
hetical | +1.057 |
spiders | +1.010 |
Neg logit contributions | |
henko | -1.520 |
ramid | -1.364 |
� | -1.303 |
��� | -1.255 |
LV | -1.253 |
Token | . |
Token ID | 13 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
margins | +0.567 |
rig | +0.532 |
agy | +0.481 |
hetical | +0.476 |
spiders | +0.456 |
Neg logit contributions | |
henko | -0.630 |
ramid | -0.563 |
� | -0.535 |
��� | -0.516 |
LV | -0.515 |
Token | Whatever |
Token ID | 15935 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
henko | +0.084 |
ramid | +0.075 |
� | +0.071 |
��� | +0.068 |
LV | +0.068 |
Neg logit contributions | |
margins | -0.077 |
rig | -0.073 |
agy | -0.066 |
hetical | -0.065 |
spiders | -0.062 |
Token | recon |
Token ID | 8195 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
margins | +0.996 |
rig | +0.927 |
agy | +0.820 |
hetical | +0.809 |
spiders | +0.779 |
Neg logit contributions | |
henko | -1.314 |
ramid | -1.187 |
� | -1.131 |
��� | -1.099 |
LV | -1.091 |
Token | figured |
Token ID | 46296 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
margins | +4.612 |
rig | +4.365 |
agy | +3.901 |
hetical | +3.835 |
spiders | +3.690 |
Neg logit contributions | |
henko | -5.210 |
ramid | -4.713 |
��� | -4.406 |
� | -4.400 |
LV | -4.284 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
margins | +1.205 |
rig | +1.121 |
agy | +1.001 |
hetical | +0.990 |
spiders | +0.949 |
Neg logit contributions | |
henko | -1.509 |
ramid | -1.359 |
� | -1.297 |
��� | -1.253 |
LV | -1.248 |
Token | Court |
Token ID | 3078 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
margins | +2.408 |
rig | +2.289 |
agy | +2.115 |
hetical | +2.100 |
spiders | +2.035 |
Neg logit contributions | |
henko | -1.595 |
ramid | -1.384 |
� | -1.288 |
��� | -1.236 |
LV | -1.212 |
Token | emerges |
Token ID | 25457 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
margins | +3.643 |
rig | +3.343 |
agy | +2.884 |
hetical | +2.781 |
spiders | +2.722 |
Neg logit contributions | |
henko | -5.585 |
ramid | -5.096 |
� | -4.824 |
��� | -4.711 |
LV | -4.652 |
Token | after |
Token ID | 706 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
margins | +1.248 |
rig | +1.174 |
agy | +1.068 |
hetical | +1.057 |
spiders | +1.015 |
Neg logit contributions | |
henko | -1.260 |
ramid | -1.123 |
� | -1.064 |
��� | -1.025 |
LV | -1.021 |
Token | the |
Token ID | 262 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
henko | +0.408 |
ramid | +0.364 |
� | +0.348 |
LV | +0.335 |
��� | +0.335 |
Neg logit contributions | |
margins | -0.357 |
rig | -0.335 |
agy | -0.304 |
hetical | -0.301 |
spiders | -0.287 |
Token | November |
Token ID | 3389 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
margins | +0.135 |
rig | +0.127 |
agy | +0.116 |
hetical | +0.115 |
spiders | +0.110 |
Neg logit contributions | |
henko | -0.140 |
ramid | -0.124 |
� | -0.118 |
LV | -0.113 |
��� | -0.113 |
Token | election |
Token ID | 3071 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
margins | +0.700 |
rig | +0.662 |
agy | +0.606 |
hetical | +0.600 |
spiders | +0.575 |
Neg logit contributions | |
henko | -0.662 |
ramid | -0.585 |
� | -0.555 |
LV | -0.531 |
��� | -0.530 |
Token | role |
Token ID | 2597 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
margins | +0.334 |
rig | +0.312 |
agy | +0.281 |
hetical | +0.278 |
spiders | +0.265 |
Neg logit contributions | |
henko | -0.408 |
ramid | -0.366 |
� | -0.350 |
��� | -0.337 |
LV | -0.337 |
Token | played |
Token ID | 2826 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
henko | +0.286 |
ramid | +0.256 |
� | +0.245 |
LV | +0.236 |
��� | +0.235 |
Neg logit contributions | |
margins | -0.252 |
rig | -0.236 |
agy | -0.215 |
hetical | -0.212 |
spiders | -0.202 |
Token | by |
Token ID | 416 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
margins | +0.486 |
rig | +0.459 |
agy | +0.421 |
hetical | +0.417 |
spiders | +0.402 |
Neg logit contributions | |
henko | -0.411 |
ramid | -0.361 |
� | -0.341 |
��� | -0.326 |
LV | -0.325 |
Token | state |
Token ID | 1181 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
henko | +0.562 |
ramid | +0.504 |
� | +0.481 |
LV | +0.463 |
��� | +0.462 |
Neg logit contributions | |
margins | -0.487 |
rig | -0.458 |
agy | -0.415 |
hetical | -0.410 |
spiders | -0.390 |
Token | supreme |
Token ID | 17700 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
margins | +0.881 |
rig | +0.826 |
agy | +0.737 |
hetical | +0.731 |
spiders | +0.705 |
Neg logit contributions | |
henko | -1.040 |
ramid | -0.931 |
� | -0.887 |
��� | -0.859 |
LV | -0.850 |
Token | court |
Token ID | 2184 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
margins | +1.255 |
rig | +1.174 |
agy | +1.067 |
hetical | +1.056 |
spiders | +1.026 |
Neg logit contributions | |
henko | -1.223 |
ramid | -1.094 |
� | -1.032 |
��� | -1.000 |
LV | -0.988 |
Token | justices |
Token ID | 27818 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
margins | +4.000 |
rig | +3.740 |
agy | +3.324 |
hetical | +3.197 |
spiders | +3.185 |
Neg logit contributions | |
henko | -5.147 |
ramid | -4.709 |
� | -4.415 |
��� | -4.292 |
LV | -4.219 |
Token | in |
Token ID | 287 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
margins | +2.944 |
rig | +2.754 |
agy | +2.475 |
hetical | +2.427 |
spiders | +2.347 |
Neg logit contributions | |
henko | -3.538 |
ramid | -3.226 |
� | -3.005 |
��� | -2.952 |
LV | -2.901 |
Token | the |
Token ID | 262 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
margins | +0.566 |
rig | +0.529 |
agy | +0.474 |
hetical | +0.468 |
spiders | +0.447 |
Neg logit contributions | |
henko | -0.712 |
ramid | -0.640 |
� | -0.612 |
��� | -0.590 |
LV | -0.590 |
Token | case |
Token ID | 1339 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
margins | +0.644 |
rig | +0.600 |
agy | +0.537 |
hetical | +0.529 |
spiders | +0.507 |
Neg logit contributions | |
henko | -0.805 |
ramid | -0.725 |
� | -0.693 |
��� | -0.670 |
LV | -0.667 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
margins | +1.382 |
rig | +1.299 |
agy | +1.172 |
hetical | +1.158 |
spiders | +1.109 |
Neg logit contributions | |
henko | -1.545 |
ramid | -1.382 |
� | -1.314 |
��� | -1.269 |
LV | -1.263 |
Token | in |
Token ID | 287 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
margins | +0.045 |
rig | +0.042 |
agy | +0.038 |
hetical | +0.037 |
spiders | +0.036 |
Neg logit contributions | |
henko | -0.054 |
ramid | -0.048 |
� | -0.046 |
LV | -0.044 |
��� | -0.044 |
Token | Seoul |
Token ID | 22372 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
margins | +0.681 |
rig | +0.640 |
agy | +0.580 |
hetical | +0.574 |
spiders | +0.549 |
Neg logit contributions | |
henko | -0.747 |
ramid | -0.667 |
� | -0.636 |
LV | -0.611 |
��� | -0.611 |
Token | today |
Token ID | 1909 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
henko | +0.191 |
ramid | +0.172 |
� | +0.164 |
LV | +0.159 |
��� | +0.157 |
Neg logit contributions | |
margins | -0.153 |
rig | -0.143 |
agy | -0.129 |
hetical | -0.128 |
spiders | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
henko | +0.775 |
ramid | +0.691 |
� | +0.661 |
LV | +0.633 |
��� | +0.627 |
Neg logit contributions | |
margins | -0.711 |
rig | -0.667 |
agy | -0.605 |
hetical | -0.601 |
spiders | -0.571 |
Token | C |
Token ID | 327 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
margins | +0.371 |
rig | +0.348 |
agy | +0.314 |
hetical | +0.312 |
spiders | +0.297 |
Neg logit contributions | |
henko | -0.421 |
ramid | -0.377 |
� | -0.360 |
LV | -0.346 |
��� | -0.345 |
Token | NET |
Token ID | 12884 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
margins | +0.488 |
rig | +0.468 |
agy | +0.428 |
hetical | +0.424 |
spiders | +0.408 |
Neg logit contributions | |
henko | -0.387 |
ramid | -0.337 |
� | -0.317 |
��� | -0.308 |
LV | -0.303 |
Token | has |
Token ID | 468 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
margins | +3.526 |
rig | +3.299 |
hetical | +2.830 |
agy | +2.821 |
spiders | +2.696 |
Neg logit contributions | |
henko | -5.417 |
ramid | -4.934 |
��� | -4.704 |
� | -4.701 |
LV | -4.429 |
Token | learned |
Token ID | 4499 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
margins | +0.720 |
rig | +0.677 |
agy | +0.610 |
hetical | +0.603 |
spiders | +0.580 |
Neg logit contributions | |
henko | -0.763 |
ramid | -0.679 |
� | -0.651 |
��� | -0.629 |
LV | -0.621 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
margins | +0.480 |
rig | +0.451 |
agy | +0.406 |
hetical | +0.402 |
spiders | +0.385 |
Neg logit contributions | |
henko | -0.543 |
ramid | -0.486 |
� | -0.463 |
��� | -0.450 |
LV | -0.445 |
Token |
|
Token ID | 198 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
margins | +0.234 |
rig | +0.220 |
agy | +0.199 |
hetical | +0.197 |
spiders | +0.189 |
Neg logit contributions | |
henko | -0.249 |
ramid | -0.222 |
� | -0.212 |
LV | -0.203 |
��� | -0.203 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
margins | +0.653 |
rig | +0.612 |
agy | +0.550 |
hetical | +0.545 |
spiders | +0.520 |
Neg logit contributions | |
henko | -0.781 |
ramid | -0.701 |
� | -0.669 |
��� | -0.648 |
LV | -0.643 |
Token | Stephen |
Token ID | 24920 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
margins | +0.807 |
rig | +0.768 |
agy | +0.704 |
hetical | +0.699 |
spiders | +0.671 |
Neg logit contributions | |
henko | -0.653 |
ramid | -0.570 |
� | -0.536 |
��� | -0.522 |
LV | -0.508 |
Token | Shank |
Token ID | 41595 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
margins | +0.949 |
rig | +0.892 |
agy | +0.809 |
hetical | +0.800 |
spiders | +0.768 |
Neg logit contributions | |
henko | -1.015 |
ramid | -0.908 |
� | -0.864 |
��� | -0.830 |
LV | -0.829 |
Token | land |
Token ID | 1044 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
margins | +1.654 |
rig | +1.574 |
agy | +1.398 |
hetical | +1.386 |
spiders | +1.330 |
Neg logit contributions | |
henko | -1.747 |
ramid | -1.560 |
� | -1.493 |
��� | -1.431 |
LV | -1.414 |
Token | / |
Token ID | 14 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
henko | +0.531 |
ramid | +0.472 |
� | +0.450 |
LV | +0.434 |
��� | +0.432 |
Neg logit contributions | |
margins | -0.490 |
rig | -0.461 |
agy | -0.418 |
hetical | -0.414 |
spiders | -0.396 |
Token | C |
Token ID | 34 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
henko | +0.136 |
ramid | +0.119 |
� | +0.113 |
LV | +0.108 |
��� | +0.108 |
Neg logit contributions | |
margins | -0.154 |
rig | -0.146 |
agy | -0.134 |
hetical | -0.132 |
spiders | -0.127 |
Token | NET |
Token ID | 12884 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
margins | +0.132 |
rig | +0.125 |
agy | +0.115 |
hetical | +0.114 |
spiders | +0.109 |
Neg logit contributions | |
henko | -0.111 |
ramid | -0.097 |
� | -0.092 |
��� | -0.088 |
LV | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
margins | +3.803 |
rig | +3.521 |
agy | +3.157 |
hetical | +3.117 |
spiders | +2.977 |
Neg logit contributions | |
henko | -5.116 |
ramid | -4.603 |
� | -4.441 |
��� | -4.292 |
LV | -4.218 |
Token |
|
Token ID | 198 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
margins | +0.201 |
rig | +0.188 |
agy | +0.170 |
hetical | +0.168 |
spiders | +0.161 |
Neg logit contributions | |
henko | -0.234 |
ramid | -0.209 |
� | -0.200 |
LV | -0.193 |
��� | -0.190 |
Token | Most |
Token ID | 6943 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
margins | +0.237 |
rig | +0.225 |
agy | +0.207 |
hetical | +0.205 |
spiders | +0.198 |
Neg logit contributions | |
henko | -0.188 |
ramid | -0.164 |
� | -0.154 |
��� | -0.149 |
LV | -0.146 |
Token | of |
Token ID | 286 |
Feature activation | -8.95e-03 |
Pos logit contributions | |
margins | +1.118 |
rig | +1.044 |
agy | +0.937 |
hetical | +0.927 |
spiders | +0.885 |
Neg logit contributions | |
henko | -1.398 |
ramid | -1.257 |
� | -1.202 |
��� | -1.159 |
LV | -1.157 |
Token | Mozilla |
Token ID | 29258 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
henko | +0.022 |
ramid | +0.019 |
� | +0.019 |
LV | +0.018 |
��� | +0.018 |
Neg logit contributions | |
margins | -0.019 |
rig | -0.018 |
agy | -0.016 |
hetical | -0.016 |
spiders | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
margins | +0.328 |
rig | +0.309 |
agy | +0.281 |
hetical | +0.278 |
spiders | +0.266 |
Neg logit contributions | |
henko | -0.343 |
ramid | -0.305 |
� | -0.290 |
��� | -0.279 |
LV | -0.278 |
Token | adding |
Token ID | 4375 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
henko | +0.085 |
ramid | +0.076 |
� | +0.072 |
LV | +0.069 |
��� | +0.069 |
Neg logit contributions | |
margins | -0.083 |
rig | -0.078 |
agy | -0.071 |
hetical | -0.070 |
spiders | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
henko | +1.000 |
ramid | +0.887 |
� | +0.851 |
LV | +0.815 |
��� | +0.813 |
Neg logit contributions | |
margins | -0.931 |
rig | -0.876 |
agy | -0.793 |
hetical | -0.785 |
spiders | -0.752 |
Token | " |
Token ID | 366 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
henko | +0.063 |
ramid | +0.055 |
� | +0.052 |
��� | +0.050 |
LV | +0.050 |
Neg logit contributions | |
margins | -0.070 |
rig | -0.066 |
agy | -0.061 |
hetical | -0.060 |
spiders | -0.058 |
Token | O |
Token ID | 46 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
henko | +0.448 |
ramid | +0.392 |
� | +0.373 |
LV | +0.356 |
��� | +0.352 |
Neg logit contributions | |
margins | -0.537 |
rig | -0.507 |
agy | -0.467 |
hetical | -0.463 |
spiders | -0.446 |
Token | oooo |
Token ID | 13321 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
henko | +0.218 |
ramid | +0.194 |
� | +0.185 |
LV | +0.178 |
��� | +0.178 |
Neg logit contributions | |
margins | -0.200 |
rig | -0.187 |
agy | -0.170 |
hetical | -0.168 |
spiders | -0.161 |
Token | oh |
Token ID | 1219 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
margins | +3.767 |
rig | +3.526 |
agy | +3.187 |
hetical | +3.069 |
spiders | +2.951 |
Neg logit contributions | |
henko | -5.115 |
ramid | -4.648 |
��� | -4.404 |
� | -4.396 |
LV | -4.259 |
Token | ! |
Token ID | 0 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
margins | +0.459 |
rig | +0.431 |
agy | +0.390 |
hetical | +0.386 |
spiders | +0.369 |
Neg logit contributions | |
henko | -0.511 |
ramid | -0.457 |
� | -0.436 |
LV | -0.419 |
��� | -0.419 |
Token | The |
Token ID | 383 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
margins | +1.920 |
rig | +1.801 |
agy | +1.632 |
hetical | +1.611 |
spiders | +1.552 |
Neg logit contributions | |
henko | -2.064 |
ramid | -1.851 |
� | -1.745 |
��� | -1.711 |
LV | -1.676 |
Token | plot |
Token ID | 7110 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
henko | +0.177 |
ramid | +0.158 |
� | +0.151 |
LV | +0.145 |
��� | +0.145 |
Neg logit contributions | |
margins | -0.155 |
rig | -0.146 |
agy | -0.132 |
hetical | -0.130 |
spiders | -0.125 |
Token | thick |
Token ID | 6546 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
margins | +1.147 |
rig | +1.074 |
agy | +0.966 |
hetical | +0.956 |
spiders | +0.913 |
Neg logit contributions | |
henko | -1.371 |
ramid | -1.232 |
� | -1.175 |
��� | -1.134 |
LV | -1.131 |
Token | of |
Token ID | 286 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
margins | +1.255 |
rig | +1.179 |
agy | +1.059 |
hetical | +1.054 |
spiders | +1.006 |
Neg logit contributions | |
henko | -1.458 |
ramid | -1.309 |
� | -1.242 |
��� | -1.209 |
LV | -1.200 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
margins | +0.698 |
rig | +0.653 |
agy | +0.586 |
hetical | +0.582 |
spiders | +0.557 |
Neg logit contributions | |
henko | -0.834 |
ramid | -0.748 |
� | -0.713 |
��� | -0.688 |
LV | -0.687 |
Token | United |
Token ID | 1578 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
margins | +0.064 |
rig | +0.060 |
agy | +0.055 |
hetical | +0.054 |
spiders | +0.052 |
Neg logit contributions | |
henko | -0.062 |
ramid | -0.055 |
� | -0.052 |
��� | -0.050 |
LV | -0.050 |
Token | States |
Token ID | 1829 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
henko | +0.317 |
ramid | +0.278 |
� | +0.264 |
LV | +0.252 |
��� | +0.247 |
Neg logit contributions | |
margins | -0.363 |
rig | -0.344 |
agy | -0.315 |
hetical | -0.312 |
spiders | -0.300 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
margins | +0.867 |
rig | +0.819 |
agy | +0.741 |
hetical | +0.738 |
spiders | +0.710 |
Neg logit contributions | |
henko | -0.807 |
ramid | -0.711 |
� | -0.671 |
��� | -0.651 |
LV | -0.643 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
margins | +2.994 |
rig | +2.842 |
hetical | +2.596 |
agy | +2.592 |
spiders | +2.514 |
Neg logit contributions | |
henko | -2.147 |
ramid | -1.886 |
� | -1.769 |
��� | -1.757 |
LV | -1.660 |
Token | on |
Token ID | 319 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
margins | +3.998 |
rig | +3.761 |
hetical | +3.322 |
agy | +3.313 |
spiders | +3.146 |
Neg logit contributions | |
henko | -4.958 |
ramid | -4.410 |
� | -4.186 |
��� | -4.116 |
LV | -4.036 |
Token | taxation |
Token ID | 21843 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
margins | +0.878 |
rig | +0.825 |
agy | +0.745 |
hetical | +0.739 |
spiders | +0.710 |
Neg logit contributions | |
henko | -0.917 |
ramid | -0.814 |
� | -0.776 |
��� | -0.748 |
LV | -0.744 |
Token | of |
Token ID | 286 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
henko | +0.566 |
ramid | +0.507 |
� | +0.484 |
LV | +0.465 |
��� | +0.464 |
Neg logit contributions | |
margins | -0.494 |
rig | -0.463 |
agy | -0.419 |
hetical | -0.414 |
spiders | -0.396 |
Token | railroad |
Token ID | 24337 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
henko | +0.179 |
ramid | +0.161 |
� | +0.154 |
LV | +0.148 |
��� | +0.148 |
Neg logit contributions | |
margins | -0.150 |
rig | -0.141 |
agy | -0.128 |
hetical | -0.126 |
spiders | -0.120 |
Token | properties |
Token ID | 6608 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
margins | +1.273 |
rig | +1.179 |
agy | +1.048 |
hetical | +1.041 |
spiders | +1.000 |
Neg logit contributions | |
henko | -1.625 |
ramid | -1.460 |
� | -1.391 |
��� | -1.368 |
LV | -1.346 |
Token | . |
Token ID | 13 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
henko | +0.507 |
ramid | +0.451 |
� | +0.432 |
LV | +0.414 |
��� | +0.412 |
Neg logit contributions | |
margins | -0.469 |
rig | -0.441 |
agy | -0.400 |
hetical | -0.396 |
spiders | -0.379 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
margins | +0.158 |
rig | +0.148 |
agy | +0.134 |
hetical | +0.132 |
spiders | +0.127 |
Neg logit contributions | |
henko | -0.177 |
ramid | -0.159 |
� | -0.151 |
��� | -0.146 |
LV | -0.144 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
margins | +0.308 |
rig | +0.288 |
agy | +0.261 |
hetical | +0.258 |
spiders | +0.246 |
Neg logit contributions | |
henko | -0.358 |
ramid | -0.320 |
� | -0.306 |
LV | -0.295 |
��� | -0.291 |
Token | The |
Token ID | 464 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
margins | +0.279 |
rig | +0.265 |
agy | +0.243 |
hetical | +0.241 |
spiders | +0.231 |
Neg logit contributions | |
henko | -0.231 |
ramid | -0.202 |
� | -0.190 |
��� | -0.184 |
LV | -0.180 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
henko | +0.175 |
ramid | +0.157 |
� | +0.150 |
LV | +0.145 |
��� | +0.145 |
Neg logit contributions | |
margins | -0.138 |
rig | -0.130 |
agy | -0.117 |
hetical | -0.115 |
spiders | -0.109 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
margins | +2.251 |
rig | +2.139 |
agy | +1.971 |
hetical | +1.958 |
spiders | +1.902 |
Neg logit contributions | |
henko | -1.523 |
ramid | -1.327 |
� | -1.239 |
��� | -1.201 |
LV | -1.161 |
Token | � |
Token ID | 447 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
margins | +3.884 |
rig | +3.599 |
agy | +3.186 |
hetical | +3.128 |
spiders | +3.024 |
Neg logit contributions | |
henko | -5.069 |
ramid | -4.613 |
� | -4.361 |
��� | -4.231 |
LV | -4.158 |
Token | � |
Token ID | 247 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
margins | +0.828 |
rig | +0.778 |
agy | +0.705 |
hetical | +0.698 |
spiders | +0.668 |
Neg logit contributions | |
henko | -0.903 |
ramid | -0.807 |
� | -0.768 |
��� | -0.740 |
LV | -0.737 |
Token | s |
Token ID | 82 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
margins | +0.363 |
rig | +0.337 |
agy | +0.298 |
hetical | +0.294 |
spiders | +0.278 |
Neg logit contributions | |
henko | -0.549 |
ramid | -0.499 |
� | -0.478 |
��� | -0.463 |
LV | -0.462 |
Token | erroneous |
Token ID | 35366 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
margins | +0.313 |
rig | +0.292 |
agy | +0.262 |
hetical | +0.259 |
spiders | +0.246 |
Neg logit contributions | |
henko | -0.409 |
ramid | -0.368 |
� | -0.352 |
LV | -0.340 |
��� | -0.339 |
Token | campaign |
Token ID | 1923 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
margins | +1.275 |
rig | +1.187 |
agy | +1.060 |
hetical | +1.047 |
spiders | +0.998 |
Neg logit contributions | |
henko | -1.698 |
ramid | -1.533 |
� | -1.467 |
��� | -1.416 |
LV | -1.414 |
Token | the |
Token ID | 262 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
henko | +1.100 |
ramid | +0.978 |
� | +0.933 |
LV | +0.899 |
��� | +0.894 |
Neg logit contributions | |
margins | -0.908 |
rig | -0.865 |
agy | -0.783 |
hetical | -0.768 |
spiders | -0.735 |
Token | level |
Token ID | 1241 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
margins | +0.223 |
rig | +0.210 |
agy | +0.191 |
hetical | +0.189 |
spiders | +0.181 |
Neg logit contributions | |
henko | -0.234 |
ramid | -0.209 |
� | -0.198 |
LV | -0.191 |
��� | -0.190 |
Token | at |
Token ID | 379 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
henko | +2.223 |
ramid | +1.954 |
� | +1.866 |
LV | +1.807 |
��� | +1.779 |
Neg logit contributions | |
margins | -1.975 |
rig | -1.879 |
agy | -1.730 |
hetical | -1.678 |
spiders | -1.614 |
Token | which |
Token ID | 543 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
margins | +0.529 |
rig | +0.492 |
agy | +0.439 |
hetical | +0.433 |
spiders | +0.410 |
Neg logit contributions | |
henko | -0.759 |
ramid | -0.687 |
� | -0.659 |
LV | -0.636 |
��� | -0.636 |
Token | Yahoo |
Token ID | 16551 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
margins | +0.346 |
rig | +0.324 |
agy | +0.292 |
hetical | +0.288 |
spiders | +0.273 |
Neg logit contributions | |
henko | -0.452 |
ramid | -0.406 |
� | -0.389 |
LV | -0.375 |
��� | -0.374 |
Token | stock |
Token ID | 4283 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
margins | +1.923 |
rig | +1.791 |
agy | +1.597 |
hetical | +1.583 |
spiders | +1.520 |
Neg logit contributions | |
henko | -2.408 |
ramid | -2.172 |
� | -2.079 |
��� | -2.003 |
LV | -1.988 |
Token | was |
Token ID | 373 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
margins | +3.543 |
rig | +3.284 |
agy | +2.837 |
hetical | +2.835 |
spiders | +2.714 |
Neg logit contributions | |
henko | -5.307 |
ramid | -4.897 |
� | -4.665 |
��� | -4.562 |
LV | -4.408 |
Token | trading |
Token ID | 7313 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
henko | +0.348 |
ramid | +0.309 |
� | +0.294 |
LV | +0.284 |
��� | +0.283 |
Neg logit contributions | |
margins | -0.327 |
rig | -0.307 |
agy | -0.280 |
hetical | -0.276 |
spiders | -0.264 |
Token | when |
Token ID | 618 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
margins | +3.007 |
rig | +2.766 |
agy | +2.461 |
hetical | +2.434 |
spiders | +2.349 |
Neg logit contributions | |
henko | -3.732 |
ramid | -3.409 |
� | -3.258 |
��� | -3.197 |
LV | -3.102 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
henko | +0.885 |
ramid | +0.785 |
� | +0.752 |
LV | +0.726 |
��� | +0.717 |
Neg logit contributions | |
margins | -0.740 |
rig | -0.696 |
agy | -0.640 |
hetical | -0.626 |
spiders | -0.594 |
Token | bid |
Token ID | 8406 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
margins | +0.310 |
rig | +0.291 |
agy | +0.264 |
hetical | +0.260 |
spiders | +0.246 |
Neg logit contributions | |
henko | -0.379 |
ramid | -0.339 |
� | -0.324 |
LV | -0.313 |
��� | -0.311 |
Token | justices |
Token ID | 27818 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
henko | +0.394 |
ramid | +0.352 |
� | +0.336 |
LV | +0.324 |
��� | +0.323 |
Neg logit contributions | |
margins | -0.349 |
rig | -0.329 |
agy | -0.298 |
hetical | -0.295 |
spiders | -0.281 |
Token | on |
Token ID | 319 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
margins | +2.135 |
rig | +2.002 |
agy | +1.798 |
hetical | +1.769 |
spiders | +1.694 |
Neg logit contributions | |
henko | -2.586 |
ramid | -2.348 |
� | -2.208 |
��� | -2.153 |
LV | -2.129 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
margins | +0.515 |
rig | +0.480 |
agy | +0.431 |
hetical | +0.426 |
spiders | +0.409 |
Neg logit contributions | |
henko | -0.611 |
ramid | -0.546 |
� | -0.523 |
��� | -0.503 |
LV | -0.502 |
Token | Wisconsin |
Token ID | 9279 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
margins | +0.349 |
rig | +0.324 |
agy | +0.292 |
hetical | +0.291 |
spiders | +0.279 |
Neg logit contributions | |
henko | -0.371 |
ramid | -0.330 |
� | -0.315 |
��� | -0.303 |
LV | -0.301 |
Token | supreme |
Token ID | 17700 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
henko | +0.548 |
ramid | +0.484 |
� | +0.459 |
LV | +0.439 |
��� | +0.438 |
Neg logit contributions | |
margins | -0.601 |
rig | -0.568 |
agy | -0.521 |
hetical | -0.516 |
spiders | -0.495 |
Token | court |
Token ID | 2184 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
margins | +0.863 |
rig | +0.807 |
agy | +0.730 |
hetical | +0.728 |
spiders | +0.705 |
Neg logit contributions | |
henko | -0.826 |
ramid | -0.737 |
� | -0.697 |
��� | -0.681 |
LV | -0.665 |
Token | majority |
Token ID | 3741 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
margins | +3.945 |
rig | +3.647 |
agy | +3.241 |
hetical | +3.143 |
spiders | +3.076 |
Neg logit contributions | |
henko | -4.925 |
ramid | -4.434 |
� | -4.140 |
��� | -4.081 |
LV | -3.978 |
Token | that |
Token ID | 326 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
margins | +2.047 |
rig | +1.890 |
agy | +1.705 |
hetical | +1.692 |
spiders | +1.620 |
Neg logit contributions | |
henko | -2.343 |
ramid | -2.104 |
� | -1.985 |
��� | -1.939 |
LV | -1.917 |
Token | not |
Token ID | 407 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
margins | +0.346 |
rig | +0.324 |
agy | +0.293 |
hetical | +0.290 |
spiders | +0.277 |
Neg logit contributions | |
henko | -0.398 |
ramid | -0.357 |
� | -0.340 |
��� | -0.327 |
LV | -0.327 |
Token | only |
Token ID | 691 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
henko | +0.140 |
ramid | +0.124 |
� | +0.118 |
LV | +0.113 |
��� | +0.113 |
Neg logit contributions | |
margins | -0.144 |
rig | -0.136 |
agy | -0.124 |
hetical | -0.123 |
spiders | -0.118 |
Token | shut |
Token ID | 4423 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
margins | +0.300 |
rig | +0.282 |
agy | +0.255 |
hetical | +0.252 |
spiders | +0.241 |
Neg logit contributions | |
henko | -0.339 |
ramid | -0.302 |
� | -0.289 |
��� | -0.278 |
LV | -0.278 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
margins | +0.125 |
rig | +0.117 |
agy | +0.105 |
hetical | +0.104 |
spiders | +0.101 |
Neg logit contributions | |
henko | -0.141 |
ramid | -0.126 |
� | -0.120 |
��� | -0.116 |
LV | -0.116 |
Token | garlic |
Token ID | 17644 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
henko | +0.285 |
ramid | +0.254 |
� | +0.243 |
��� | +0.233 |
LV | +0.233 |
Neg logit contributions | |
margins | -0.259 |
rig | -0.243 |
agy | -0.220 |
hetical | -0.218 |
spiders | -0.209 |
Token | cloves |
Token ID | 45025 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
margins | +1.631 |
rig | +1.489 |
agy | +1.273 |
hetical | +1.261 |
spiders | +1.202 |
Neg logit contributions | |
henko | -3.018 |
ramid | -2.766 |
� | -2.668 |
��� | -2.593 |
LV | -2.586 |
Token | and |
Token ID | 290 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
margins | +2.749 |
rig | +2.579 |
agy | +2.299 |
hetical | +2.280 |
spiders | +2.214 |
Neg logit contributions | |
henko | -3.157 |
ramid | -2.853 |
� | -2.717 |
��� | -2.642 |
LV | -2.619 |
Token | the |
Token ID | 262 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
margins | +0.297 |
rig | +0.278 |
agy | +0.253 |
hetical | +0.250 |
spiders | +0.237 |
Neg logit contributions | |
henko | -0.348 |
ramid | -0.311 |
� | -0.297 |
LV | -0.286 |
��� | -0.286 |
Token | ginger |
Token ID | 25072 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
margins | +0.147 |
rig | +0.139 |
agy | +0.126 |
hetical | +0.125 |
spiders | +0.120 |
Neg logit contributions | |
henko | -0.153 |
ramid | -0.136 |
� | -0.130 |
��� | -0.124 |
LV | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
margins | +4.040 |
rig | +3.772 |
agy | +3.306 |
hetical | +3.277 |
spiders | +3.223 |
Neg logit contributions | |
henko | -4.763 |
ramid | -4.298 |
� | -4.081 |
��� | -4.022 |
LV | -3.909 |
Token | Cut |
Token ID | 9712 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
henko | +0.114 |
ramid | +0.102 |
� | +0.097 |
LV | +0.094 |
��� | +0.093 |
Neg logit contributions | |
margins | -0.106 |
rig | -0.099 |
agy | -0.090 |
hetical | -0.089 |
spiders | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
margins | +0.916 |
rig | +0.857 |
agy | +0.769 |
hetical | +0.761 |
spiders | +0.728 |
Neg logit contributions | |
henko | -1.119 |
ramid | -1.005 |
� | -0.961 |
��� | -0.926 |
LV | -0.926 |
Token | white |
Token ID | 2330 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
margins | +0.037 |
rig | +0.035 |
agy | +0.031 |
hetical | +0.031 |
spiders | +0.030 |
Neg logit contributions | |
henko | -0.045 |
ramid | -0.040 |
� | -0.038 |
��� | -0.037 |
LV | -0.037 |
Token | onion |
Token ID | 21670 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
margins | +0.249 |
rig | +0.233 |
agy | +0.210 |
hetical | +0.208 |
spiders | +0.200 |
Neg logit contributions | |
henko | -0.280 |
ramid | -0.251 |
� | -0.239 |
��� | -0.231 |
LV | -0.230 |
Token | U |
Token ID | 471 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
margins | +0.309 |
rig | +0.290 |
agy | +0.262 |
hetical | +0.260 |
spiders | +0.251 |
Neg logit contributions | |
henko | -0.315 |
ramid | -0.281 |
� | -0.267 |
��� | -0.257 |
LV | -0.255 |
Token | . |
Token ID | 13 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
margins | +0.211 |
rig | +0.198 |
agy | +0.180 |
hetical | +0.179 |
spiders | +0.171 |
Neg logit contributions | |
henko | -0.226 |
ramid | -0.202 |
� | -0.192 |
LV | -0.185 |
��� | -0.183 |
Token | S |
Token ID | 50 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
margins | +0.788 |
rig | +0.744 |
agy | +0.678 |
hetical | +0.671 |
spiders | +0.645 |
Neg logit contributions | |
henko | -0.764 |
ramid | -0.678 |
� | -0.643 |
��� | -0.617 |
LV | -0.615 |
Token | . |
Token ID | 13 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
henko | +0.320 |
ramid | +0.285 |
� | +0.272 |
LV | +0.261 |
��� | +0.259 |
Neg logit contributions | |
margins | -0.299 |
rig | -0.280 |
agy | -0.254 |
hetical | -0.252 |
spiders | -0.241 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
margins | +0.215 |
rig | +0.204 |
agy | +0.186 |
hetical | +0.184 |
spiders | +0.178 |
Neg logit contributions | |
henko | -0.189 |
ramid | -0.167 |
� | -0.158 |
��� | -0.151 |
LV | -0.150 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
margins | +2.568 |
rig | +2.444 |
agy | +2.249 |
hetical | +2.234 |
spiders | +2.171 |
Neg logit contributions | |
henko | -1.740 |
ramid | -1.512 |
� | -1.412 |
��� | -1.369 |
LV | -1.325 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
margins | +3.890 |
rig | +3.682 |
agy | +3.272 |
hetical | +3.170 |
spiders | +3.089 |
Neg logit contributions | |
henko | -4.771 |
ramid | -4.274 |
� | -4.021 |
��� | -3.948 |
LV | -3.856 |
Token | The |
Token ID | 383 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
margins | +0.505 |
rig | +0.474 |
agy | +0.427 |
hetical | +0.423 |
spiders | +0.404 |
Neg logit contributions | |
henko | -0.580 |
ramid | -0.520 |
� | -0.494 |
��� | -0.479 |
LV | -0.474 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
henko | +0.087 |
ramid | +0.078 |
� | +0.074 |
LV | +0.071 |
��� | +0.071 |
Neg logit contributions | |
margins | -0.077 |
rig | -0.072 |
agy | -0.065 |
hetical | -0.065 |
spiders | -0.062 |
Token | will |
Token ID | 481 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
margins | +3.246 |
rig | +3.039 |
agy | +2.729 |
hetical | +2.674 |
spiders | +2.577 |
Neg logit contributions | |
henko | -3.797 |
ramid | -3.430 |
� | -3.237 |
��� | -3.134 |
LV | -3.097 |
Token | decide |
Token ID | 5409 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
henko | +0.250 |
ramid | +0.219 |
� | +0.209 |
��� | +0.199 |
LV | +0.198 |
Neg logit contributions | |
margins | -0.285 |
rig | -0.270 |
agy | -0.249 |
hetical | -0.247 |
spiders | -0.236 |
Token | now |
Token ID | 783 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
margins | +0.701 |
rig | +0.656 |
agy | +0.591 |
hetical | +0.585 |
spiders | +0.557 |
Neg logit contributions | |
henko | -0.856 |
ramid | -0.769 |
� | -0.736 |
LV | -0.708 |
��� | -0.707 |
Token | pouring |
Token ID | 23147 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
henko | +0.168 |
ramid | +0.150 |
� | +0.144 |
LV | +0.138 |
��� | +0.137 |
Neg logit contributions | |
margins | -0.144 |
rig | -0.135 |
agy | -0.122 |
hetical | -0.121 |
spiders | -0.115 |
Token | into |
Token ID | 656 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
margins | +0.487 |
rig | +0.459 |
agy | +0.415 |
hetical | +0.410 |
spiders | +0.395 |
Neg logit contributions | |
henko | -0.509 |
ramid | -0.453 |
� | -0.431 |
��� | -0.416 |
LV | -0.413 |
Token | state |
Token ID | 1181 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
margins | +0.394 |
rig | +0.368 |
agy | +0.331 |
hetical | +0.327 |
spiders | +0.312 |
Neg logit contributions | |
henko | -0.490 |
ramid | -0.441 |
� | -0.422 |
��� | -0.406 |
LV | -0.406 |
Token | supreme |
Token ID | 17700 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
margins | +1.063 |
rig | +0.995 |
agy | +0.889 |
hetical | +0.881 |
spiders | +0.844 |
Neg logit contributions | |
henko | -1.272 |
ramid | -1.140 |
� | -1.088 |
��� | -1.051 |
LV | -1.044 |
Token | court |
Token ID | 2184 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
margins | +1.227 |
rig | +1.151 |
agy | +1.043 |
hetical | +1.035 |
spiders | +0.999 |
Neg logit contributions | |
henko | -1.249 |
ramid | -1.117 |
� | -1.057 |
��� | -1.023 |
LV | -1.013 |
Token | contests |
Token ID | 22830 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
margins | +3.794 |
rig | +3.524 |
agy | +3.129 |
hetical | +3.023 |
spiders | +2.977 |
Neg logit contributions | |
henko | -4.872 |
ramid | -4.427 |
� | -4.188 |
��� | -4.105 |
LV | -4.009 |
Token | in |
Token ID | 287 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
margins | +1.215 |
rig | +1.135 |
agy | +1.021 |
hetical | +1.009 |
spiders | +0.966 |
Neg logit contributions | |
henko | -1.458 |
ramid | -1.313 |
� | -1.250 |
��� | -1.211 |
LV | -1.204 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
margins | +0.448 |
rig | +0.418 |
agy | +0.375 |
hetical | +0.371 |
spiders | +0.353 |
Neg logit contributions | |
henko | -0.573 |
ramid | -0.516 |
� | -0.494 |
��� | -0.476 |
LV | -0.476 |
Token | sets |
Token ID | 5621 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
margins | +0.116 |
rig | +0.108 |
agy | +0.098 |
hetical | +0.097 |
spiders | +0.092 |
Neg logit contributions | |
henko | -0.138 |
ramid | -0.124 |
� | -0.119 |
LV | -0.114 |
��� | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
margins | +1.396 |
rig | +1.301 |
agy | +1.162 |
hetical | +1.150 |
spiders | +1.098 |
Neg logit contributions | |
henko | -1.811 |
ramid | -1.639 |
� | -1.563 |
��� | -1.508 |
LV | -1.508 |
Token | came |
Token ID | 1625 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
henko | +0.376 |
ramid | +0.337 |
� | +0.323 |
LV | +0.311 |
��� | +0.310 |
Neg logit contributions | |
margins | -0.303 |
rig | -0.283 |
agy | -0.255 |
hetical | -0.252 |
spiders | -0.240 |
Token | from |
Token ID | 422 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
margins | +0.334 |
rig | +0.314 |
agy | +0.286 |
hetical | +0.282 |
spiders | +0.273 |
Neg logit contributions | |
henko | -0.334 |
ramid | -0.299 |
� | -0.282 |
��� | -0.273 |
LV | -0.271 |
Token | the |
Token ID | 262 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
henko | +0.255 |
ramid | +0.229 |
� | +0.218 |
��� | +0.210 |
LV | +0.210 |
Neg logit contributions | |
margins | -0.222 |
rig | -0.208 |
agy | -0.187 |
hetical | -0.185 |
spiders | -0.177 |
Token | W |
Token ID | 370 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
henko | +0.542 |
ramid | +0.484 |
� | +0.462 |
LV | +0.445 |
��� | +0.444 |
Neg logit contributions | |
margins | -0.471 |
rig | -0.443 |
agy | -0.400 |
hetical | -0.396 |
spiders | -0.378 |
Token | BC |
Token ID | 2749 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
henko | +1.014 |
ramid | +0.847 |
� | +0.785 |
LV | +0.748 |
��� | +0.726 |
Neg logit contributions | |
margins | -1.917 |
rig | -1.812 |
agy | -1.708 |
hetical | -1.705 |
spiders | -1.653 |
Token | cruiser |
Token ID | 35239 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
henko | +1.198 |
ramid | +1.066 |
� | +1.020 |
LV | +0.981 |
��� | +0.977 |
Neg logit contributions | |
margins | -1.066 |
rig | -1.001 |
agy | -0.907 |
hetical | -0.897 |
spiders | -0.856 |
Token | weight |
Token ID | 6551 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
henko | +5.292 |
ramid | +4.656 |
� | +4.582 |
LV | +4.385 |
��� | +4.240 |
Neg logit contributions | |
margins | -3.185 |
rig | -2.965 |
agy | -2.679 |
hetical | -2.652 |
raints | -2.461 |
Token | world |
Token ID | 995 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
margins | +0.659 |
rig | +0.621 |
agy | +0.567 |
hetical | +0.562 |
spiders | +0.546 |
Neg logit contributions | |
henko | -0.557 |
ramid | -0.495 |
� | -0.465 |
��� | -0.450 |
LV | -0.444 |
Token | champion |
Token ID | 8783 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
henko | +2.232 |
ramid | +1.918 |
� | +1.821 |
LV | +1.731 |
��� | +1.720 |
Neg logit contributions | |
margins | -2.768 |
rig | -2.622 |
agy | -2.426 |
hetical | -2.407 |
spiders | -2.303 |
Token | , |
Token ID | 11 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
henko | +1.383 |
ramid | +1.224 |
� | +1.181 |
LV | +1.130 |
��� | +1.122 |
Neg logit contributions | |
margins | -1.233 |
rig | -1.158 |
agy | -1.048 |
hetical | -1.037 |
spiders | -0.989 |
Token | Tony |
Token ID | 8832 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
henko | +0.235 |
ramid | +0.213 |
� | +0.202 |
��� | +0.195 |
LV | +0.194 |
Neg logit contributions | |
margins | -0.199 |
rig | -0.186 |
agy | -0.168 |
hetical | -0.166 |
spiders | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
margins | +0.278 |
rig | +0.261 |
agy | +0.235 |
hetical | +0.233 |
spiders | +0.222 |
Neg logit contributions | |
henko | -0.324 |
ramid | -0.290 |
� | -0.277 |
LV | -0.266 |
��� | -0.266 |
Token |
|
Token ID | 198 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
henko | +0.172 |
ramid | +0.154 |
� | +0.147 |
��� | +0.141 |
LV | +0.140 |
Neg logit contributions | |
margins | -0.158 |
rig | -0.149 |
agy | -0.135 |
hetical | -0.133 |
spiders | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
margins | +0.153 |
rig | +0.143 |
agy | +0.130 |
hetical | +0.128 |
spiders | +0.123 |
Neg logit contributions | |
henko | -0.176 |
ramid | -0.158 |
� | -0.151 |
LV | -0.145 |
��� | -0.142 |
Token | It |
Token ID | 1026 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
margins | +0.056 |
rig | +0.053 |
agy | +0.049 |
hetical | +0.048 |
spiders | +0.046 |
Neg logit contributions | |
henko | -0.044 |
ramid | -0.039 |
� | -0.036 |
��� | -0.035 |
LV | -0.034 |
Token | 's |
Token ID | 338 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
margins | +0.114 |
rig | +0.106 |
agy | +0.096 |
hetical | +0.095 |
spiders | +0.090 |
Neg logit contributions | |
henko | -0.140 |
ramid | -0.126 |
� | -0.120 |
LV | -0.116 |
��� | -0.116 |
Token | understandable |
Token ID | 21977 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
henko | +0.389 |
ramid | +0.350 |
� | +0.335 |
��� | +0.323 |
LV | +0.322 |
Neg logit contributions | |
margins | -0.320 |
rig | -0.299 |
agy | -0.268 |
hetical | -0.265 |
spiders | -0.253 |
Token | parents |
Token ID | 3397 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
henko | +4.007 |
ramid | +3.543 |
� | +3.384 |
LV | +3.257 |
��� | +3.135 |
Neg logit contributions | |
margins | -4.181 |
rig | -3.960 |
agy | -3.645 |
hetical | -3.628 |
spiders | -3.430 |
Token | would |
Token ID | 561 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
henko | +0.789 |
ramid | +0.709 |
� | +0.677 |
��� | +0.653 |
LV | +0.651 |
Neg logit contributions | |
margins | -0.658 |
rig | -0.615 |
agy | -0.554 |
hetical | -0.549 |
spiders | -0.524 |
Token | want |
Token ID | 765 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
henko | +1.757 |
ramid | +1.577 |
� | +1.509 |
LV | +1.447 |
��� | +1.438 |
Neg logit contributions | |
margins | -1.424 |
rig | -1.337 |
agy | -1.203 |
hetical | -1.188 |
spiders | -1.128 |
Token | to |
Token ID | 284 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
henko | +0.623 |
ramid | +0.557 |
� | +0.531 |
��� | +0.511 |
LV | +0.510 |
Neg logit contributions | |
margins | -0.551 |
rig | -0.517 |
agy | -0.467 |
hetical | -0.462 |
spiders | -0.442 |
Token | know |
Token ID | 760 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
henko | +0.385 |
ramid | +0.346 |
� | +0.330 |
LV | +0.318 |
��� | +0.317 |
Neg logit contributions | |
margins | -0.314 |
rig | -0.295 |
agy | -0.265 |
hetical | -0.262 |
spiders | -0.249 |
Token | dumb |
Token ID | 13526 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
henko | +0.226 |
ramid | +0.202 |
� | +0.193 |
��� | +0.186 |
LV | +0.186 |
Neg logit contributions | |
margins | -0.194 |
rig | -0.182 |
agy | -0.164 |
hetical | -0.162 |
spiders | -0.155 |
Token | law |
Token ID | 1099 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
henko | +2.052 |
ramid | +1.862 |
� | +1.784 |
LV | +1.704 |
��� | +1.687 |
Neg logit contributions | |
margins | -1.622 |
rig | -1.509 |
agy | -1.361 |
hetical | -1.350 |
spiders | -1.285 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
henko | +1.297 |
ramid | +1.159 |
� | +1.105 |
LV | +1.058 |
��� | +1.051 |
Neg logit contributions | |
margins | -1.200 |
rig | -1.125 |
agy | -1.024 |
hetical | -1.014 |
spiders | -0.969 |
Token | it |
Token ID | 340 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
margins | +0.227 |
rig | +0.212 |
agy | +0.190 |
hetical | +0.189 |
spiders | +0.181 |
Neg logit contributions | |
henko | -0.269 |
ramid | -0.242 |
� | -0.231 |
��� | -0.223 |
LV | -0.222 |
Token | is |
Token ID | 318 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
henko | +0.282 |
ramid | +0.252 |
� | +0.241 |
LV | +0.231 |
��� | +0.231 |
Neg logit contributions | |
margins | -0.241 |
rig | -0.226 |
agy | -0.204 |
hetical | -0.202 |
spiders | -0.192 |
Token | understandable |
Token ID | 21977 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
margins | +0.135 |
rig | +0.127 |
agy | +0.114 |
hetical | +0.113 |
spiders | +0.108 |
Neg logit contributions | |
henko | -0.160 |
ramid | -0.144 |
� | -0.137 |
��� | -0.133 |
LV | -0.132 |
Token | that |
Token ID | 326 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
henko | +3.824 |
ramid | +3.372 |
� | +3.252 |
LV | +3.113 |
��� | +2.982 |
Neg logit contributions | |
margins | -3.856 |
rig | -3.661 |
agy | -3.353 |
hetical | -3.325 |
aura | -3.142 |
Token | you |
Token ID | 345 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
henko | +0.435 |
ramid | +0.389 |
� | +0.371 |
��� | +0.356 |
LV | +0.356 |
Neg logit contributions | |
margins | -0.392 |
rig | -0.368 |
agy | -0.333 |
hetical | -0.330 |
spiders | -0.316 |
Token | broke |
Token ID | 6265 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
henko | +0.493 |
ramid | +0.442 |
� | +0.423 |
LV | +0.407 |
��� | +0.406 |
Neg logit contributions | |
margins | -0.406 |
rig | -0.380 |
agy | -0.342 |
hetical | -0.338 |
spiders | -0.323 |
Token | it |
Token ID | 340 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
margins | +0.340 |
rig | +0.317 |
agy | +0.284 |
hetical | +0.281 |
spiders | +0.268 |
Neg logit contributions | |
henko | -0.436 |
ramid | -0.393 |
� | -0.376 |
��� | -0.363 |
LV | -0.362 |
Token | — |
Token ID | 851 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
henko | +0.079 |
ramid | +0.070 |
� | +0.067 |
LV | +0.064 |
��� | +0.064 |
Neg logit contributions | |
margins | -0.072 |
rig | -0.068 |
agy | -0.061 |
hetical | -0.061 |
spiders | -0.058 |
Token | any |
Token ID | 597 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
margins | +0.155 |
rig | +0.145 |
agy | +0.131 |
hetical | +0.129 |
spiders | +0.123 |
Neg logit contributions | |
henko | -0.192 |
ramid | -0.173 |
� | -0.165 |
LV | -0.159 |
��� | -0.159 |
Token | danger |
Token ID | 3514 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
margins | +0.887 |
rig | +0.825 |
agy | +0.736 |
hetical | +0.728 |
spiders | +0.694 |
Neg logit contributions | |
henko | -1.207 |
ramid | -1.091 |
� | -1.044 |
��� | -1.010 |
LV | -1.007 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
margins | +1.833 |
rig | +1.692 |
agy | +1.517 |
hetical | +1.512 |
spiders | +1.455 |
Neg logit contributions | |
henko | -2.194 |
ramid | -1.988 |
� | -1.870 |
��� | -1.844 |
LV | -1.810 |
Token | it |
Token ID | 340 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
margins | +0.569 |
rig | +0.533 |
agy | +0.480 |
hetical | +0.475 |
spiders | +0.453 |
Neg logit contributions | |
henko | -0.677 |
ramid | -0.607 |
� | -0.581 |
LV | -0.559 |
��� | -0.558 |
Token | feels |
Token ID | 5300 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
margins | +0.468 |
rig | +0.440 |
agy | +0.397 |
hetical | +0.393 |
spiders | +0.376 |
Neg logit contributions | |
henko | -0.531 |
ramid | -0.475 |
� | -0.454 |
LV | -0.436 |
��� | -0.435 |
Token | hollow |
Token ID | 20596 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
margins | +0.785 |
rig | +0.734 |
agy | +0.659 |
hetical | +0.652 |
spiders | +0.622 |
Neg logit contributions | |
henko | -0.982 |
ramid | -0.884 |
� | -0.845 |
��� | -0.814 |
LV | -0.814 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
henko | +3.929 |
ramid | +3.460 |
� | +3.400 |
LV | +3.216 |
��� | +3.041 |
Neg logit contributions | |
margins | -3.709 |
rig | -3.559 |
agy | -3.222 |
hetical | -3.174 |
ipes | -3.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
henko | +0.264 |
ramid | +0.237 |
� | +0.226 |
��� | +0.218 |
LV | +0.217 |
Neg logit contributions | |
margins | -0.229 |
rig | -0.215 |
agy | -0.194 |
hetical | -0.192 |
spiders | -0.184 |
Token | will |
Token ID | 481 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
henko | +0.391 |
ramid | +0.351 |
� | +0.335 |
LV | +0.323 |
��� | +0.322 |
Neg logit contributions | |
margins | -0.324 |
rig | -0.303 |
agy | -0.273 |
hetical | -0.270 |
spiders | -0.257 |
Token | fall |
Token ID | 2121 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
henko | +0.480 |
ramid | +0.431 |
� | +0.414 |
LV | +0.398 |
��� | +0.394 |
Neg logit contributions | |
margins | -0.379 |
rig | -0.356 |
agy | -0.320 |
hetical | -0.316 |
spiders | -0.298 |
Token | apart |
Token ID | 5475 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
henko | +1.480 |
ramid | +1.312 |
� | +1.260 |
LV | +1.205 |
��� | +1.193 |
Neg logit contributions | |
margins | -1.400 |
rig | -1.318 |
agy | -1.196 |
hetical | -1.194 |
spiders | -1.132 |
Token | of |
Token ID | 286 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
margins | +0.374 |
rig | +0.352 |
agy | +0.320 |
hetical | +0.315 |
spiders | +0.302 |
Neg logit contributions | |
henko | -0.411 |
ramid | -0.366 |
� | -0.350 |
LV | -0.335 |
��� | -0.334 |
Token | mass |
Token ID | 2347 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
margins | +0.034 |
rig | +0.032 |
agy | +0.029 |
hetical | +0.029 |
spiders | +0.026 |
Neg logit contributions | |
henko | -0.052 |
ramid | -0.047 |
� | -0.045 |
LV | -0.043 |
��� | -0.043 |
Token | unemployment |
Token ID | 10681 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
margins | +1.045 |
rig | +0.964 |
agy | +0.843 |
hetical | +0.831 |
spiders | +0.780 |
Neg logit contributions | |
henko | -1.818 |
ramid | -1.657 |
� | -1.596 |
LV | -1.544 |
��� | -1.543 |
Token | - |
Token ID | 532 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
henko | +1.956 |
ramid | +1.702 |
� | +1.656 |
LV | +1.581 |
enza | +1.518 |
Neg logit contributions | |
margins | -1.838 |
rig | -1.766 |
agy | -1.616 |
hetical | -1.584 |
spiders | -1.496 |
Token | both |
Token ID | 1111 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
henko | +1.098 |
ramid | +0.979 |
� | +0.939 |
LV | +0.902 |
��� | +0.890 |
Neg logit contributions | |
margins | -0.934 |
rig | -0.883 |
agy | -0.799 |
hetical | -0.790 |
spiders | -0.746 |
Token | blue |
Token ID | 4171 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
henko | +0.881 |
ramid | +0.779 |
� | +0.745 |
LV | +0.715 |
��� | +0.705 |
Neg logit contributions | |
margins | -0.823 |
rig | -0.783 |
agy | -0.717 |
hetical | -0.700 |
spiders | -0.667 |
Token | and |
Token ID | 290 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
henko | +3.819 |
ramid | +3.371 |
� | +3.236 |
LV | +3.112 |
��� | +3.033 |
Neg logit contributions | |
margins | -3.383 |
rig | -3.255 |
agy | -3.042 |
hetical | -2.986 |
rac | -2.761 |
Token | white |
Token ID | 2330 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
henko | +0.118 |
ramid | +0.105 |
� | +0.100 |
LV | +0.096 |
��� | +0.096 |
Neg logit contributions | |
margins | -0.108 |
rig | -0.102 |
agy | -0.093 |
hetical | -0.091 |
spiders | -0.087 |
Token | collar |
Token ID | 19908 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
henko | +0.517 |
ramid | +0.460 |
� | +0.442 |
LV | +0.424 |
��� | +0.419 |
Neg logit contributions | |
margins | -0.451 |
rig | -0.427 |
agy | -0.388 |
hetical | -0.383 |
spiders | -0.363 |
Token | - |
Token ID | 532 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
henko | +0.229 |
ramid | +0.203 |
� | +0.195 |
LV | +0.187 |
��� | +0.185 |
Neg logit contributions | |
margins | -0.205 |
rig | -0.194 |
agy | -0.176 |
hetical | -0.174 |
spiders | -0.165 |
Token | resulting |
Token ID | 7186 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
henko | +0.627 |
ramid | +0.556 |
� | +0.535 |
LV | +0.511 |
��� | +0.503 |
Neg logit contributions | |
margins | -0.557 |
rig | -0.529 |
agy | -0.479 |
hetical | -0.472 |
spiders | -0.449 |
Token | be |
Token ID | 307 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
henko | +0.541 |
ramid | +0.484 |
� | +0.463 |
LV | +0.445 |
��� | +0.443 |
Neg logit contributions | |
margins | -0.443 |
rig | -0.415 |
agy | -0.376 |
hetical | -0.370 |
spiders | -0.349 |
Token | an |
Token ID | 281 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
margins | +0.425 |
rig | +0.399 |
agy | +0.361 |
hetical | +0.358 |
spiders | +0.343 |
Neg logit contributions | |
henko | -0.472 |
ramid | -0.422 |
� | -0.402 |
��� | -0.387 |
LV | -0.386 |
Token | issue |
Token ID | 2071 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
margins | +0.386 |
rig | +0.362 |
agy | +0.326 |
hetical | +0.321 |
spiders | +0.306 |
Neg logit contributions | |
henko | -0.464 |
ramid | -0.416 |
� | -0.397 |
LV | -0.384 |
��� | -0.382 |
Token | . |
Token ID | 13 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
margins | +0.175 |
rig | +0.165 |
agy | +0.149 |
hetical | +0.147 |
spiders | +0.141 |
Neg logit contributions | |
henko | -0.196 |
ramid | -0.176 |
� | -0.167 |
��� | -0.161 |
LV | -0.161 |
Token | For |
Token ID | 1114 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
henko | +0.093 |
ramid | +0.083 |
� | +0.079 |
LV | +0.076 |
��� | +0.076 |
Neg logit contributions | |
margins | -0.087 |
rig | -0.081 |
agy | -0.074 |
hetical | -0.073 |
spiders | -0.070 |
Token | Fi |
Token ID | 23238 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
henko | +0.294 |
ramid | +0.264 |
� | +0.252 |
LV | +0.243 |
��� | +0.242 |
Neg logit contributions | |
margins | -0.243 |
rig | -0.228 |
agy | -0.205 |
hetical | -0.203 |
spiders | -0.193 |
Token | OS |
Token ID | 2640 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
henko | +3.022 |
ramid | +2.608 |
LV | +2.397 |
� | +2.377 |
enza | +2.258 |
Neg logit contributions | |
margins | -4.313 |
rig | -4.122 |
hetical | -3.820 |
agy | -3.804 |
spiders | -3.646 |
Token | TV |
Token ID | 3195 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
henko | +0.174 |
ramid | +0.156 |
� | +0.149 |
��� | +0.144 |
LV | +0.143 |
Neg logit contributions | |
margins | -0.156 |
rig | -0.147 |
agy | -0.132 |
hetical | -0.131 |
spiders | -0.126 |
Token | customers |
Token ID | 4297 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
henko | +2.390 |
ramid | +2.139 |
� | +2.040 |
LV | +1.972 |
��� | +1.957 |
Neg logit contributions | |
margins | -2.104 |
rig | -1.969 |
agy | -1.788 |
hetical | -1.773 |
spiders | -1.674 |
Token | with |
Token ID | 351 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
henko | +1.168 |
ramid | +1.042 |
� | +0.994 |
LV | +0.955 |
��� | +0.952 |
Neg logit contributions | |
margins | -1.065 |
rig | -1.001 |
agy | -0.907 |
hetical | -0.896 |
spiders | -0.856 |
Token | a |
Token ID | 257 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
henko | +0.250 |
ramid | +0.224 |
� | +0.214 |
LV | +0.206 |
��� | +0.206 |
Neg logit contributions | |
margins | -0.214 |
rig | -0.201 |
agy | -0.182 |
hetical | -0.180 |
spiders | -0.171 |
Token | is |
Token ID | 318 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
henko | +0.497 |
ramid | +0.447 |
� | +0.428 |
LV | +0.411 |
��� | +0.411 |
Neg logit contributions | |
margins | -0.403 |
rig | -0.377 |
agy | -0.339 |
hetical | -0.335 |
spiders | -0.320 |
Token | a |
Token ID | 257 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
margins | +0.419 |
rig | +0.393 |
agy | +0.354 |
hetical | +0.351 |
spiders | +0.335 |
Neg logit contributions | |
henko | -0.486 |
ramid | -0.435 |
� | -0.415 |
��� | -0.400 |
LV | -0.399 |
Token | form |
Token ID | 1296 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
margins | +0.072 |
rig | +0.067 |
agy | +0.061 |
hetical | +0.060 |
spiders | +0.057 |
Neg logit contributions | |
henko | -0.084 |
ramid | -0.075 |
� | -0.072 |
LV | -0.069 |
��� | -0.069 |
Token | of |
Token ID | 286 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
henko | +1.697 |
ramid | +1.504 |
� | +1.469 |
LV | +1.388 |
��� | +1.378 |
Neg logit contributions | |
margins | -1.595 |
rig | -1.480 |
agy | -1.354 |
hetical | -1.330 |
spiders | -1.287 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
henko | +0.111 |
ramid | +0.100 |
� | +0.096 |
LV | +0.092 |
��� | +0.091 |
Neg logit contributions | |
margins | -0.094 |
rig | -0.088 |
agy | -0.080 |
hetical | -0.079 |
spiders | -0.075 |
Token | occupational |
Token ID | 34266 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
henko | +0.331 |
ramid | +0.297 |
� | +0.285 |
LV | +0.273 |
��� | +0.271 |
Neg logit contributions | |
margins | -0.283 |
rig | -0.266 |
agy | -0.241 |
hetical | -0.237 |
spiders | -0.226 |
Token | deriv |
Token ID | 16124 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
henko | +3.767 |
ramid | +3.341 |
� | +3.318 |
LV | +3.048 |
��� | +3.001 |
Neg logit contributions | |
margins | -3.476 |
rig | -3.272 |
agy | -2.985 |
hetical | -2.919 |
spiders | -2.771 |
Token | ational |
Token ID | 864 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
margins | +0.633 |
rig | +0.602 |
agy | +0.554 |
hetical | +0.550 |
spiders | +0.528 |
Neg logit contributions | |
henko | -0.503 |
ramid | -0.439 |
� | -0.414 |
��� | -0.396 |
LV | -0.395 |
Token | suffix |
Token ID | 35488 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
henko | +0.718 |
ramid | +0.636 |
� | +0.622 |
LV | +0.583 |
��� | +0.578 |
Neg logit contributions | |
margins | -0.664 |
rig | -0.624 |
agy | -0.570 |
hetical | -0.560 |
spiders | -0.535 |
Token | - |
Token ID | 532 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
margins | +0.817 |
rig | +0.766 |
agy | +0.693 |
hetical | +0.686 |
spiders | +0.655 |
Neg logit contributions | |
henko | -0.923 |
ramid | -0.825 |
� | -0.790 |
LV | -0.757 |
��� | -0.756 |
Token | cin |
Token ID | 17879 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
henko | +0.298 |
ramid | +0.266 |
� | +0.254 |
LV | +0.243 |
��� | +0.242 |
Neg logit contributions | |
margins | -0.278 |
rig | -0.260 |
agy | -0.236 |
hetical | -0.234 |
spiders | -0.225 |
Token | liter |
Token ID | 17201 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
henko | +0.902 |
ramid | +0.812 |
� | +0.778 |
LV | +0.750 |
��� | +0.749 |
Neg logit contributions | |
margins | -0.694 |
rig | -0.646 |
agy | -0.580 |
hetical | -0.573 |
spiders | -0.546 |
Token | Eco |
Token ID | 38719 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
henko | +1.052 |
ramid | +0.938 |
� | +0.894 |
LV | +0.861 |
��� | +0.856 |
Neg logit contributions | |
margins | -0.985 |
rig | -0.926 |
agy | -0.842 |
hetical | -0.833 |
spiders | -0.797 |
Token | Boost |
Token ID | 45686 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
henko | +0.538 |
ramid | +0.473 |
� | +0.448 |
��� | +0.429 |
LV | +0.427 |
Neg logit contributions | |
margins | -0.619 |
rig | -0.586 |
agy | -0.537 |
hetical | -0.532 |
spiders | -0.512 |
Token | proved |
Token ID | 8302 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
margins | +0.307 |
rig | +0.287 |
agy | +0.259 |
hetical | +0.256 |
spiders | +0.246 |
Neg logit contributions | |
henko | -0.348 |
ramid | -0.311 |
� | -0.297 |
��� | -0.287 |
LV | -0.283 |
Token | its |
Token ID | 663 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
margins | +0.212 |
rig | +0.198 |
agy | +0.179 |
hetical | +0.177 |
spiders | +0.169 |
Neg logit contributions | |
henko | -0.257 |
ramid | -0.231 |
� | -0.221 |
LV | -0.212 |
��� | -0.212 |
Token | met |
Token ID | 1138 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
henko | +0.494 |
ramid | +0.444 |
� | +0.426 |
LV | +0.411 |
��� | +0.408 |
Neg logit contributions | |
margins | -0.364 |
rig | -0.340 |
agy | -0.305 |
hetical | -0.302 |
spiders | -0.286 |
Token | tle |
Token ID | 7100 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
henko | +4.013 |
ramid | +3.601 |
� | +3.413 |
LV | +3.301 |
��� | +3.278 |
Neg logit contributions | |
margins | -3.295 |
rig | -3.029 |
agy | -2.732 |
hetical | -2.706 |
spiders | -2.636 |
Token | off |
Token ID | 572 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
henko | +0.887 |
ramid | +0.786 |
� | +0.751 |
LV | +0.721 |
��� | +0.712 |
Neg logit contributions | |
margins | -0.824 |
rig | -0.776 |
agy | -0.706 |
hetical | -0.702 |
spiders | -0.668 |
Token | - |
Token ID | 12 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
henko | +1.115 |
ramid | +0.981 |
� | +0.928 |
��� | +0.888 |
LV | +0.888 |
Neg logit contributions | |
margins | -1.259 |
rig | -1.189 |
agy | -1.092 |
hetical | -1.081 |
spiders | -1.041 |
Token | road |
Token ID | 6344 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
henko | +1.098 |
ramid | +0.985 |
� | +0.938 |
LV | +0.905 |
��� | +0.901 |
Neg logit contributions | |
margins | -0.914 |
rig | -0.851 |
agy | -0.772 |
hetical | -0.763 |
spiders | -0.731 |
Token | – |
Token ID | 784 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
henko | +1.663 |
ramid | +1.472 |
� | +1.415 |
LV | +1.359 |
��� | +1.343 |
Neg logit contributions | |
margins | -1.518 |
rig | -1.424 |
agy | -1.303 |
hetical | -1.298 |
spiders | -1.228 |
Token | who |
Token ID | 508 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
henko | +0.362 |
ramid | +0.325 |
� | +0.312 |
LV | +0.300 |
��� | +0.300 |
Neg logit contributions | |
margins | -0.286 |
rig | -0.268 |
agy | -0.240 |
hetical | -0.238 |
spiders | -0.226 |
Token | � |
Token ID | 447 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
henko | +0.376 |
ramid | +0.336 |
� | +0.322 |
LV | +0.310 |
��� | +0.309 |
Neg logit contributions | |
margins | -0.324 |
rig | -0.304 |
agy | -0.274 |
hetical | -0.271 |
spiders | -0.259 |
Token | � |
Token ID | 247 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
henko | +0.127 |
ramid | +0.112 |
� | +0.107 |
LV | +0.102 |
��� | +0.102 |
Neg logit contributions | |
margins | -0.137 |
rig | -0.129 |
agy | -0.118 |
hetical | -0.117 |
spiders | -0.113 |
Token | s |
Token ID | 82 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
margins | +0.114 |
rig | +0.106 |
agy | +0.094 |
hetical | +0.093 |
spiders | +0.088 |
Neg logit contributions | |
henko | -0.168 |
ramid | -0.152 |
� | -0.146 |
��� | -0.141 |
LV | -0.141 |
Token | never |
Token ID | 1239 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
margins | +0.111 |
rig | +0.104 |
agy | +0.094 |
hetical | +0.093 |
spiders | +0.089 |
Neg logit contributions | |
henko | -0.126 |
ramid | -0.112 |
� | -0.107 |
��� | -0.103 |
LV | -0.103 |
Token | met |
Token ID | 1138 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
margins | +0.314 |
rig | +0.294 |
agy | +0.266 |
hetical | +0.262 |
spiders | +0.252 |
Neg logit contributions | |
henko | -0.369 |
ramid | -0.332 |
� | -0.315 |
��� | -0.305 |
LV | -0.305 |
Token | a |
Token ID | 257 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
henko | +3.758 |
ramid | +3.304 |
� | +3.232 |
LV | +3.072 |
��� | +3.018 |
Neg logit contributions | |
margins | -3.436 |
rig | -3.243 |
agy | -2.900 |
hetical | -2.885 |
spiders | -2.746 |
Token | pop |
Token ID | 1461 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
henko | +0.743 |
ramid | +0.665 |
� | +0.635 |
LV | +0.610 |
��� | +0.609 |
Neg logit contributions | |
margins | -0.658 |
rig | -0.617 |
agy | -0.558 |
hetical | -0.551 |
spiders | -0.526 |
Token | culture |
Token ID | 3968 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
henko | +0.747 |
ramid | +0.670 |
� | +0.640 |
LV | +0.616 |
��� | +0.616 |
Neg logit contributions | |
margins | -0.628 |
rig | -0.588 |
agy | -0.530 |
hetical | -0.524 |
spiders | -0.500 |
Token | reference |
Token ID | 4941 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
henko | +0.472 |
ramid | +0.423 |
� | +0.404 |
LV | +0.388 |
��� | +0.388 |
Neg logit contributions | |
margins | -0.409 |
rig | -0.383 |
agy | -0.346 |
hetical | -0.342 |
spiders | -0.327 |
Token | he |
Token ID | 339 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
henko | +0.776 |
ramid | +0.690 |
� | +0.666 |
LV | +0.634 |
��� | +0.630 |
Neg logit contributions | |
margins | -0.711 |
rig | -0.668 |
agy | -0.606 |
hetical | -0.596 |
spiders | -0.572 |
Token | ."[ |
Token ID | 18161 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
henko | +1.133 |
ramid | +1.009 |
� | +0.970 |
LV | +0.929 |
��� | +0.914 |
Neg logit contributions | |
margins | -1.017 |
rig | -0.956 |
agy | -0.868 |
hetical | -0.855 |
spiders | -0.820 |
Token | 45 |
Token ID | 2231 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
henko | +0.691 |
ramid | +0.546 |
� | +0.489 |
��� | +0.443 |
LV | +0.443 |
Neg logit contributions | |
margins | -1.916 |
rig | -1.841 |
agy | -1.730 |
hetical | -1.720 |
spiders | -1.675 |
Token | ] |
Token ID | 60 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
margins | +0.875 |
rig | +0.808 |
agy | +0.707 |
hetical | +0.697 |
spiders | +0.652 |
Neg logit contributions | |
henko | -1.522 |
ramid | -1.395 |
��� | -1.336 |
� | -1.332 |
LV | -1.287 |
Token | Damascus |
Token ID | 21028 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
henko | +0.422 |
ramid | +0.374 |
� | +0.357 |
LV | +0.343 |
��� | +0.340 |
Neg logit contributions | |
margins | -0.411 |
rig | -0.387 |
agy | -0.352 |
hetical | -0.349 |
spiders | -0.334 |
Token | rel |
Token ID | 823 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
henko | +0.586 |
ramid | +0.520 |
� | +0.500 |
LV | +0.480 |
��� | +0.478 |
Neg logit contributions | |
margins | -0.513 |
rig | -0.482 |
agy | -0.437 |
hetical | -0.432 |
spiders | -0.411 |
Token | ented |
Token ID | 4714 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
margins | +0.404 |
rig | +0.386 |
agy | +0.359 |
hetical | +0.357 |
spiders | +0.346 |
Neg logit contributions | |
henko | -0.226 |
ramid | -0.191 |
� | -0.178 |
��� | -0.167 |
LV | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
henko | +3.594 |
ramid | +3.078 |
� | +3.033 |
LV | +2.889 |
enza | +2.762 |
Neg logit contributions | |
margins | -3.544 |
rig | -3.399 |
agy | -3.099 |
hetical | -3.096 |
aura | -2.943 |
Token | Cos |
Token ID | 10437 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
henko | +0.740 |
ramid | +0.653 |
� | +0.624 |
LV | +0.600 |
��� | +0.593 |
Neg logit contributions | |
margins | -0.734 |
rig | -0.692 |
agy | -0.630 |
hetical | -0.624 |
spiders | -0.598 |
Token | kun |
Token ID | 28374 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
henko | +2.310 |
ramid | +1.912 |
� | +1.775 |
LV | +1.654 |
enza | +1.622 |
Neg logit contributions | |
margins | -3.830 |
rig | -3.615 |
agy | -3.346 |
hetical | -3.321 |
spiders | -3.262 |
Token | K |
Token ID | 509 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
henko | +0.048 |
ramid | +0.042 |
� | +0.040 |
LV | +0.039 |
��� | +0.039 |
Neg logit contributions | |
margins | -0.048 |
rig | -0.045 |
agy | -0.041 |
hetical | -0.041 |
spiders | -0.039 |
Token | irc |
Token ID | 1980 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
margins | +0.524 |
rig | +0.486 |
agy | +0.437 |
hetical | +0.433 |
spiders | +0.413 |
Neg logit contributions | |
henko | -0.658 |
ramid | -0.592 |
� | -0.564 |
LV | -0.544 |
��� | -0.538 |
Token | to |
Token ID | 284 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
henko | +0.075 |
ramid | +0.067 |
� | +0.064 |
LV | +0.061 |
��� | +0.061 |
Neg logit contributions | |
margins | -0.067 |
rig | -0.063 |
agy | -0.057 |
hetical | -0.056 |
spiders | -0.054 |
Token | pay |
Token ID | 1414 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
henko | +0.509 |
ramid | +0.449 |
� | +0.425 |
��� | +0.407 |
LV | +0.406 |
Neg logit contributions | |
margins | -0.569 |
rig | -0.538 |
agy | -0.492 |
hetical | -0.487 |
spiders | -0.469 |
Token | for |
Token ID | 329 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
henko | +0.615 |
ramid | +0.553 |
� | +0.530 |
LV | +0.510 |
��� | +0.508 |
Neg logit contributions | |
margins | -0.476 |
rig | -0.445 |
agy | -0.399 |
hetical | -0.395 |
spiders | -0.375 |
Token | that |
Token ID | 326 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
henko | +0.337 |
ramid | +0.302 |
� | +0.288 |
LV | +0.277 |
��� | +0.276 |
Neg logit contributions | |
margins | -0.291 |
rig | -0.274 |
agy | -0.249 |
hetical | -0.246 |
spiders | -0.233 |
Token | ," |
Token ID | 553 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
henko | +0.329 |
ramid | +0.296 |
� | +0.284 |
LV | +0.273 |
��� | +0.272 |
Neg logit contributions | |
margins | -0.246 |
rig | -0.231 |
agy | -0.208 |
hetical | -0.205 |
spiders | -0.193 |
Token | Owens |
Token ID | 31005 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
henko | +0.523 |
ramid | +0.466 |
� | +0.444 |
LV | +0.426 |
��� | +0.426 |
Neg logit contributions | |
margins | -0.489 |
rig | -0.459 |
agy | -0.417 |
hetical | -0.412 |
spiders | -0.395 |
Token | says |
Token ID | 1139 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
henko | +3.581 |
ramid | +3.050 |
� | +2.978 |
LV | +2.849 |
��� | +2.783 |
Neg logit contributions | |
margins | -3.621 |
rig | -3.414 |
agy | -3.147 |
hetical | -3.105 |
spiders | -2.962 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
henko | +0.233 |
ramid | +0.210 |
� | +0.199 |
��� | +0.193 |
LV | +0.192 |
Neg logit contributions | |
margins | -0.206 |
rig | -0.193 |
agy | -0.174 |
hetical | -0.173 |
spiders | -0.165 |
Token | Studies |
Token ID | 10422 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
henko | +0.536 |
ramid | +0.476 |
� | +0.451 |
��� | +0.433 |
LV | +0.431 |
Neg logit contributions | |
margins | -0.548 |
rig | -0.518 |
agy | -0.470 |
hetical | -0.466 |
spiders | -0.448 |
Token | have |
Token ID | 423 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
henko | +0.843 |
ramid | +0.756 |
� | +0.722 |
LV | +0.697 |
��� | +0.695 |
Neg logit contributions | |
margins | -0.676 |
rig | -0.631 |
agy | -0.569 |
hetical | -0.563 |
spiders | -0.535 |
Token | found |
Token ID | 1043 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
margins | +0.059 |
rig | +0.055 |
agy | +0.050 |
hetical | +0.050 |
spiders | +0.048 |
Neg logit contributions | |
henko | -0.059 |
ramid | -0.053 |
� | -0.050 |
��� | -0.048 |
LV | -0.048 |
Token | causing |
Token ID | 6666 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
henko | +0.344 |
ramid | +0.305 |
� | +0.290 |
LV | +0.278 |
��� | +0.277 |
Neg logit contributions | |
margins | -0.350 |
rig | -0.330 |
agy | -0.301 |
hetical | -0.298 |
spiders | -0.286 |
Token | major |
Token ID | 1688 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
margins | +0.283 |
rig | +0.265 |
agy | +0.238 |
hetical | +0.235 |
spiders | +0.223 |
Neg logit contributions | |
henko | -0.357 |
ramid | -0.321 |
� | -0.308 |
LV | -0.297 |
��� | -0.296 |
Token | scar |
Token ID | 10153 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
henko | +0.773 |
ramid | +0.694 |
� | +0.669 |
LV | +0.643 |
��� | +0.632 |
Neg logit contributions | |
margins | -0.599 |
rig | -0.568 |
agy | -0.511 |
hetical | -0.505 |
spiders | -0.473 |
Token | ring |
Token ID | 1806 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
henko | +1.490 |
ramid | +1.339 |
� | +1.291 |
LV | +1.242 |
��� | +1.233 |
Neg logit contributions | |
margins | -1.161 |
rig | -1.088 |
agy | -0.982 |
hetical | -0.980 |
spiders | -0.920 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
margins | +0.805 |
rig | +0.752 |
agy | +0.676 |
hetical | +0.668 |
spiders | +0.641 |
Neg logit contributions | |
henko | -0.969 |
ramid | -0.872 |
� | -0.829 |
��� | -0.804 |
LV | -0.799 |
Token | deform |
Token ID | 47577 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
henko | +0.519 |
ramid | +0.466 |
� | +0.446 |
LV | +0.428 |
��� | +0.427 |
Neg logit contributions | |
margins | -0.435 |
rig | -0.410 |
agy | -0.370 |
hetical | -0.365 |
spiders | -0.347 |
Token | ity |
Token ID | 414 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
henko | +3.614 |
ramid | +3.209 |
� | +3.028 |
LV | +2.897 |
enza | +2.840 |
Neg logit contributions | |
margins | -3.516 |
rig | -3.297 |
hetical | -3.002 |
agy | -2.993 |
spiders | -2.884 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
margins | +0.158 |
rig | +0.148 |
agy | +0.134 |
hetical | +0.133 |
spiders | +0.127 |
Neg logit contributions | |
henko | -0.175 |
ramid | -0.157 |
� | -0.149 |
��� | -0.143 |
LV | -0.143 |
Token | once |
Token ID | 1752 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
henko | +0.433 |
ramid | +0.385 |
� | +0.366 |
��� | +0.351 |
LV | +0.351 |
Neg logit contributions | |
margins | -0.433 |
rig | -0.408 |
agy | -0.371 |
hetical | -0.367 |
spiders | -0.353 |
Token | again |
Token ID | 757 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
margins | +0.143 |
rig | +0.134 |
agy | +0.120 |
hetical | +0.119 |
spiders | +0.114 |
Neg logit contributions | |
henko | -0.169 |
ramid | -0.152 |
� | -0.145 |
��� | -0.140 |
LV | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
henko | +1.714 |
ramid | +1.526 |
� | +1.463 |
LV | +1.404 |
��� | +1.397 |
Neg logit contributions | |
margins | -1.577 |
rig | -1.487 |
agy | -1.348 |
hetical | -1.335 |
spiders | -1.273 |
Token | achieved |
Token ID | 8793 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
margins | +0.220 |
rig | +0.208 |
agy | +0.190 |
hetical | +0.188 |
spiders | +0.179 |
Neg logit contributions | |
henko | -0.233 |
ramid | -0.208 |
� | -0.198 |
LV | -0.190 |
��� | -0.189 |
Token | representation |
Token ID | 10552 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
henko | +1.409 |
ramid | +1.268 |
� | +1.220 |
LV | +1.176 |
��� | +1.165 |
Neg logit contributions | |
margins | -1.017 |
rig | -0.962 |
agy | -0.870 |
hetical | -0.852 |
spiders | -0.803 |
Token | in |
Token ID | 287 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
margins | +0.307 |
rig | +0.289 |
agy | +0.262 |
hetical | +0.260 |
spiders | +0.248 |
Neg logit contributions | |
henko | -0.333 |
ramid | -0.296 |
� | -0.283 |
LV | -0.272 |
��� | -0.271 |
Token | Australian |
Token ID | 6638 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
margins | +0.157 |
rig | +0.148 |
agy | +0.134 |
hetical | +0.133 |
spiders | +0.126 |
Neg logit contributions | |
henko | -0.177 |
ramid | -0.159 |
� | -0.152 |
��� | -0.146 |
LV | -0.146 |
Token | par |
Token ID | 1582 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
henko | +1.055 |
ramid | +0.938 |
� | +0.892 |
LV | +0.857 |
��� | +0.849 |
Neg logit contributions | |
margins | -1.033 |
rig | -0.980 |
agy | -0.901 |
hetical | -0.886 |
spiders | -0.844 |
Token | liam |
Token ID | 5058 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
henko | +0.996 |
ramid | +0.867 |
� | +0.810 |
LV | +0.772 |
��� | +0.758 |
Neg logit contributions | |
margins | -1.420 |
rig | -1.335 |
agy | -1.252 |
hetical | -1.232 |
spiders | -1.203 |
Token | ents |
Token ID | 658 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
henko | +3.303 |
ramid | +2.831 |
� | +2.712 |
enza | +2.580 |
LV | +2.557 |
Neg logit contributions | |
margins | -3.915 |
rig | -3.654 |
agy | -3.406 |
hetical | -3.361 |
spiders | -3.239 |
Token | , |
Token ID | 11 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
margins | +0.461 |
rig | +0.431 |
agy | +0.390 |
hetical | +0.386 |
spiders | +0.369 |
Neg logit contributions | |
henko | -0.519 |
ramid | -0.465 |
� | -0.442 |
��� | -0.427 |
LV | -0.425 |
Token | mostly |
Token ID | 4632 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
henko | +0.176 |
ramid | +0.157 |
� | +0.150 |
LV | +0.144 |
��� | +0.144 |
Neg logit contributions | |
margins | -0.159 |
rig | -0.149 |
agy | -0.135 |
hetical | -0.134 |
spiders | -0.128 |
Token | in |
Token ID | 287 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
henko | +0.779 |
ramid | +0.689 |
� | +0.658 |
LV | +0.632 |
��� | +0.627 |
Neg logit contributions | |
margins | -0.761 |
rig | -0.721 |
agy | -0.661 |
hetical | -0.651 |
spiders | -0.621 |
Token | upper |
Token ID | 6727 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
henko | +0.105 |
ramid | +0.094 |
� | +0.090 |
LV | +0.087 |
��� | +0.087 |
Neg logit contributions | |
margins | -0.086 |
rig | -0.081 |
agy | -0.073 |
hetical | -0.072 |
spiders | -0.069 |
Token | so |
Token ID | 523 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
margins | +0.027 |
rig | +0.025 |
agy | +0.023 |
hetical | +0.022 |
spiders | +0.021 |
Neg logit contributions | |
henko | -0.036 |
ramid | -0.033 |
� | -0.031 |
��� | -0.030 |
LV | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
henko | +0.608 |
ramid | +0.535 |
� | +0.506 |
��� | +0.483 |
LV | +0.483 |
Neg logit contributions | |
margins | -0.705 |
rig | -0.666 |
agy | -0.610 |
hetical | -0.604 |
spiders | -0.582 |
Token | called |
Token ID | 7174 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
margins | +0.830 |
rig | +0.798 |
agy | +0.724 |
hetical | +0.716 |
rac | +0.684 |
Neg logit contributions | |
henko | -0.793 |
ramid | -0.704 |
��� | -0.671 |
� | -0.663 |
LV | -0.635 |
Token | � |
Token ID | 564 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
margins | +3.142 |
rig | +2.948 |
agy | +2.680 |
hetical | +2.642 |
spiders | +2.570 |
Neg logit contributions | |
henko | -3.052 |
ramid | -2.725 |
� | -2.572 |
LV | -2.475 |
��� | -2.472 |
Token | � |
Token ID | 246 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
henko | +0.030 |
ramid | +0.027 |
� | +0.025 |
��� | +0.024 |
LV | +0.024 |
Neg logit contributions | |
margins | -0.033 |
rig | -0.031 |
agy | -0.028 |
hetical | -0.028 |
spiders | -0.027 |
Token | Dream |
Token ID | 30571 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
margins | +0.416 |
rig | +0.389 |
agy | +0.350 |
hetical | +0.346 |
spiders | +0.331 |
Neg logit contributions | |
henko | -0.502 |
ramid | -0.450 |
� | -0.431 |
��� | -0.415 |
LV | -0.414 |
Token | ers |
Token ID | 364 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
henko | +3.270 |
ramid | +2.841 |
� | +2.747 |
LV | +2.611 |
��� | +2.608 |
Neg logit contributions | |
margins | -3.768 |
rig | -3.593 |
hetical | -3.383 |
agy | -3.308 |
ipes | -3.198 |
Token | � |
Token ID | 447 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
henko | +0.385 |
ramid | +0.343 |
� | +0.327 |
��� | +0.314 |
LV | +0.313 |
Neg logit contributions | |
margins | -0.366 |
rig | -0.344 |
agy | -0.313 |
hetical | -0.309 |
spiders | -0.297 |
Token | � |
Token ID | 247 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
margins | +0.316 |
rig | +0.300 |
agy | +0.275 |
hetical | +0.273 |
spiders | +0.263 |
Neg logit contributions | |
henko | -0.269 |
ramid | -0.238 |
� | -0.222 |
��� | -0.214 |
LV | -0.212 |
Token | from |
Token ID | 422 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
margins | +0.736 |
rig | +0.693 |
agy | +0.626 |
hetical | +0.620 |
spiders | +0.594 |
Neg logit contributions | |
henko | -0.805 |
ramid | -0.722 |
� | -0.683 |
��� | -0.663 |
LV | -0.658 |
Token | deportation |
Token ID | 24031 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
margins | +0.674 |
rig | +0.628 |
agy | +0.558 |
hetical | +0.552 |
spiders | +0.528 |
Neg logit contributions | |
henko | -0.910 |
ramid | -0.822 |
� | -0.786 |
��� | -0.761 |
LV | -0.760 |
Token | systems |
Token ID | 3341 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
margins | +0.554 |
rig | +0.517 |
agy | +0.463 |
hetical | +0.458 |
spiders | +0.437 |
Neg logit contributions | |
henko | -0.708 |
ramid | -0.637 |
� | -0.610 |
��� | -0.589 |
LV | -0.588 |
Token | include |
Token ID | 2291 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
henko | +0.968 |
ramid | +0.870 |
� | +0.827 |
LV | +0.798 |
��� | +0.790 |
Neg logit contributions | |
margins | -0.811 |
rig | -0.763 |
agy | -0.686 |
hetical | -0.681 |
spiders | -0.643 |
Token | Cloud |
Token ID | 10130 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
henko | +1.103 |
ramid | +0.988 |
� | +0.941 |
LV | +0.904 |
��� | +0.901 |
Neg logit contributions | |
margins | -0.979 |
rig | -0.920 |
agy | -0.835 |
hetical | -0.826 |
spiders | -0.784 |
Token | based |
Token ID | 1912 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
henko | +1.563 |
ramid | +1.382 |
� | +1.303 |
LV | +1.252 |
��� | +1.225 |
Neg logit contributions | |
margins | -1.772 |
rig | -1.664 |
agy | -1.530 |
hetical | -1.528 |
spiders | -1.456 |
Token | Sc |
Token ID | 1446 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
henko | +2.216 |
ramid | +1.995 |
� | +1.897 |
LV | +1.829 |
��� | +1.799 |
Neg logit contributions | |
margins | -1.854 |
rig | -1.735 |
agy | -1.585 |
hetical | -1.572 |
spiders | -1.458 |
Token | rub |
Token ID | 25089 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
henko | +2.390 |
ramid | +2.147 |
� | +1.998 |
LV | +1.983 |
enza | +1.889 |
Neg logit contributions | |
margins | -1.930 |
rig | -1.739 |
agy | -1.584 |
hetical | -1.559 |
spiders | -1.486 |
Token | bing |
Token ID | 4623 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
henko | +3.609 |
ramid | +3.196 |
� | +3.038 |
LV | +2.930 |
��� | +2.815 |
Neg logit contributions | |
margins | -3.515 |
rig | -3.272 |
hetical | -3.070 |
agy | -3.012 |
spiders | -2.809 |
Token | centers |
Token ID | 10399 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
henko | +0.182 |
ramid | +0.163 |
� | +0.155 |
LV | +0.149 |
��� | +0.149 |
Neg logit contributions | |
margins | -0.167 |
rig | -0.157 |
agy | -0.142 |
hetical | -0.141 |
spiders | -0.134 |
Token | and |
Token ID | 290 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
henko | +1.085 |
ramid | +0.970 |
� | +0.925 |
LV | +0.886 |
��� | +0.881 |
Neg logit contributions | |
margins | -1.002 |
rig | -0.938 |
agy | -0.853 |
hetical | -0.847 |
spiders | -0.805 |
Token | Content |
Token ID | 14041 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
henko | +0.760 |
ramid | +0.682 |
� | +0.649 |
LV | +0.624 |
��� | +0.622 |
Neg logit contributions | |
margins | -0.670 |
rig | -0.630 |
agy | -0.572 |
hetical | -0.566 |
spiders | -0.537 |
Token | Distribution |
Token ID | 27484 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
henko | +1.214 |
ramid | +1.074 |
� | +1.004 |
LV | +0.966 |
��� | +0.948 |
Neg logit contributions | |
margins | -1.309 |
rig | -1.232 |
hetical | -1.135 |
agy | -1.131 |
spiders | -1.064 |
Token | er |
Token ID | 263 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
henko | +0.989 |
ramid | +0.872 |
� | +0.831 |
LV | +0.797 |
enza | +0.776 |
Neg logit contributions | |
margins | -0.984 |
rig | -0.909 |
agy | -0.831 |
hetical | -0.829 |
spiders | -0.801 |
Token | horn |
Token ID | 25311 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
margins | +0.957 |
rig | +0.892 |
agy | +0.802 |
hetical | +0.793 |
spiders | +0.757 |
Neg logit contributions | |
henko | -1.199 |
ramid | -1.078 |
� | -1.030 |
LV | -0.993 |
��� | -0.989 |
Token | was |
Token ID | 373 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
margins | +1.220 |
rig | +1.148 |
agy | +1.035 |
hetical | +1.024 |
spiders | +0.984 |
Neg logit contributions | |
henko | -1.368 |
ramid | -1.229 |
� | -1.163 |
��� | -1.126 |
LV | -1.115 |
Token | linked |
Token ID | 6692 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
margins | +0.540 |
rig | +0.508 |
agy | +0.458 |
hetical | +0.455 |
spiders | +0.435 |
Neg logit contributions | |
henko | -0.602 |
ramid | -0.541 |
� | -0.514 |
��� | -0.495 |
LV | -0.493 |
Token | to |
Token ID | 284 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
margins | +0.261 |
rig | +0.245 |
agy | +0.222 |
hetical | +0.220 |
spiders | +0.210 |
Neg logit contributions | |
henko | -0.293 |
ramid | -0.262 |
� | -0.250 |
��� | -0.241 |
LV | -0.240 |
Token | pension |
Token ID | 13553 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
henko | +0.618 |
ramid | +0.557 |
� | +0.530 |
LV | +0.510 |
��� | +0.509 |
Neg logit contributions | |
margins | -0.515 |
rig | -0.482 |
agy | -0.436 |
hetical | -0.430 |
spiders | -0.409 |
Token | fraud |
Token ID | 7394 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
henko | +3.612 |
ramid | +3.227 |
� | +3.064 |
LV | +2.927 |
��� | +2.842 |
Neg logit contributions | |
margins | -3.505 |
rig | -3.287 |
agy | -3.030 |
hetical | -2.975 |
spiders | -2.823 |
Token | committed |
Token ID | 5364 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
margins | +0.806 |
rig | +0.757 |
agy | +0.676 |
hetical | +0.666 |
spiders | +0.643 |
Neg logit contributions | |
henko | -0.957 |
ramid | -0.861 |
� | -0.822 |
��� | -0.807 |
LV | -0.791 |
Token | by |
Token ID | 416 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
henko | +0.420 |
ramid | +0.373 |
� | +0.353 |
��� | +0.339 |
LV | +0.337 |
Neg logit contributions | |
margins | -0.453 |
rig | -0.427 |
agy | -0.390 |
hetical | -0.386 |
spiders | -0.372 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
henko | +0.281 |
ramid | +0.251 |
� | +0.240 |
��� | +0.231 |
LV | +0.231 |
Neg logit contributions | |
margins | -0.244 |
rig | -0.228 |
agy | -0.206 |
hetical | -0.204 |
spiders | -0.195 |
Token | company |
Token ID | 1664 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
margins | +0.325 |
rig | +0.304 |
agy | +0.273 |
hetical | +0.271 |
spiders | +0.261 |
Neg logit contributions | |
henko | -0.363 |
ramid | -0.324 |
� | -0.310 |
��� | -0.299 |
LV | -0.297 |
Token | dead |
Token ID | 2636 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
margins | +0.210 |
rig | +0.194 |
agy | +0.172 |
hetical | +0.170 |
spiders | +0.161 |
Neg logit contributions | |
henko | -0.316 |
ramid | -0.287 |
� | -0.275 |
��� | -0.266 |
LV | -0.266 |
Token | wife |
Token ID | 3656 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
henko | +1.861 |
ramid | +1.678 |
� | +1.627 |
LV | +1.559 |
��� | +1.553 |
Neg logit contributions | |
margins | -1.183 |
rig | -1.095 |
agy | -0.969 |
hetical | -0.957 |
spiders | -0.892 |
Token | and |
Token ID | 290 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
margins | +0.680 |
rig | +0.638 |
agy | +0.576 |
hetical | +0.570 |
spiders | +0.545 |
Neg logit contributions | |
henko | -0.787 |
ramid | -0.706 |
� | -0.673 |
��� | -0.648 |
LV | -0.647 |
Token | her |
Token ID | 607 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
margins | +0.085 |
rig | +0.081 |
agy | +0.073 |
hetical | +0.073 |
spiders | +0.070 |
Neg logit contributions | |
henko | -0.085 |
ramid | -0.075 |
� | -0.071 |
��� | -0.069 |
LV | -0.068 |
Token | murderer |
Token ID | 29262 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
margins | +0.050 |
rig | +0.047 |
agy | +0.042 |
hetical | +0.042 |
spiders | +0.040 |
Neg logit contributions | |
henko | -0.052 |
ramid | -0.046 |
� | -0.044 |
��� | -0.042 |
LV | -0.042 |
Token | Oro |
Token ID | 31770 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
henko | +0.824 |
ramid | +0.730 |
� | +0.703 |
LV | +0.672 |
��� | +0.667 |
Neg logit contributions | |
margins | -0.741 |
rig | -0.695 |
agy | -0.628 |
hetical | -0.623 |
spiders | -0.591 |
Token | ku |
Token ID | 23063 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
henko | +3.923 |
ramid | +3.518 |
� | +3.344 |
LV | +3.208 |
��� | +3.168 |
Neg logit contributions | |
margins | -3.215 |
rig | -2.958 |
agy | -2.685 |
hetical | -2.651 |
spiders | -2.513 |
Token | S |
Token ID | 311 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
henko | +1.105 |
ramid | +0.981 |
� | +0.938 |
LV | +0.900 |
��� | +0.897 |
Neg logit contributions | |
margins | -1.013 |
rig | -0.948 |
agy | -0.856 |
hetical | -0.853 |
spiders | -0.810 |
Token | aki |
Token ID | 8182 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
henko | +0.095 |
ramid | +0.084 |
� | +0.081 |
��� | +0.079 |
LV | +0.077 |
Neg logit contributions | |
margins | -0.097 |
rig | -0.093 |
agy | -0.085 |
hetical | -0.083 |
spiders | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
margins | +0.517 |
rig | +0.485 |
agy | +0.438 |
hetical | +0.433 |
spiders | +0.415 |
Neg logit contributions | |
henko | -0.593 |
ramid | -0.531 |
� | -0.506 |
��� | -0.488 |
LV | -0.487 |
Token | who |
Token ID | 508 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
henko | +0.313 |
ramid | +0.281 |
� | +0.268 |
��� | +0.258 |
LV | +0.258 |
Neg logit contributions | |
margins | -0.266 |
rig | -0.249 |
agy | -0.225 |
hetical | -0.222 |
spiders | -0.212 |
Token | girl |
Token ID | 2576 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
henko | +1.223 |
ramid | +1.054 |
� | +0.999 |
LV | +0.951 |
��� | +0.934 |
Neg logit contributions | |
margins | -1.677 |
rig | -1.589 |
agy | -1.478 |
hetical | -1.454 |
spiders | -1.403 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
henko | +1.408 |
ramid | +1.254 |
� | +1.204 |
LV | +1.154 |
��� | +1.144 |
Neg logit contributions | |
margins | -1.254 |
rig | -1.178 |
agy | -1.068 |
hetical | -1.057 |
spiders | -1.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
henko | +0.395 |
ramid | +0.354 |
� | +0.337 |
��� | +0.324 |
LV | +0.324 |
Neg logit contributions | |
margins | -0.351 |
rig | -0.329 |
agy | -0.298 |
hetical | -0.295 |
spiders | -0.282 |
Token |
|
Token ID | 198 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
henko | +0.430 |
ramid | +0.383 |
� | +0.367 |
LV | +0.354 |
enza | +0.337 |
Neg logit contributions | |
margins | -0.388 |
rig | -0.363 |
agy | -0.330 |
hetical | -0.327 |
spiders | -0.313 |
Token | In |
Token ID | 818 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
henko | +0.459 |
ramid | +0.402 |
� | +0.379 |
��� | +0.362 |
LV | +0.361 |
Neg logit contributions | |
margins | -0.571 |
rig | -0.542 |
agy | -0.498 |
hetical | -0.493 |
spiders | -0.475 |
Token | response |
Token ID | 2882 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
henko | +0.929 |
ramid | +0.833 |
� | +0.797 |
LV | +0.765 |
��� | +0.765 |
Neg logit contributions | |
margins | -0.782 |
rig | -0.730 |
agy | -0.660 |
hetical | -0.653 |
spiders | -0.623 |
Token | to |
Token ID | 284 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
henko | +3.489 |
ramid | +3.103 |
� | +2.986 |
��� | +2.838 |
LV | +2.783 |
Neg logit contributions | |
margins | -3.561 |
rig | -3.356 |
hetical | -3.061 |
agy | -3.041 |
spiders | -2.919 |
Token | the |
Token ID | 262 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
henko | +0.085 |
ramid | +0.076 |
� | +0.073 |
��� | +0.070 |
LV | +0.070 |
Neg logit contributions | |
margins | -0.070 |
rig | -0.066 |
agy | -0.059 |
hetical | -0.059 |
spiders | -0.056 |
Token | CNN |
Token ID | 8100 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
henko | +0.606 |
ramid | +0.542 |
� | +0.517 |
��� | +0.497 |
LV | +0.497 |
Neg logit contributions | |
margins | -0.538 |
rig | -0.505 |
agy | -0.456 |
hetical | -0.452 |
spiders | -0.433 |
Token | article |
Token ID | 2708 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
henko | +0.331 |
ramid | +0.297 |
� | +0.283 |
��� | +0.273 |
LV | +0.273 |
Neg logit contributions | |
margins | -0.277 |
rig | -0.259 |
agy | -0.234 |
hetical | -0.231 |
spiders | -0.221 |
Token | drawing |
Token ID | 8263 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
henko | +0.104 |
ramid | +0.093 |
� | +0.088 |
��� | +0.085 |
LV | +0.085 |
Neg logit contributions | |
margins | -0.095 |
rig | -0.090 |
agy | -0.081 |
hetical | -0.080 |
spiders | -0.077 |
Token | of |
Token ID | 286 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
margins | +1.341 |
rig | +1.255 |
agy | +1.125 |
hetical | +1.117 |
spiders | +1.061 |
Neg logit contributions | |
henko | -1.619 |
ramid | -1.465 |
� | -1.386 |
��� | -1.346 |
LV | -1.337 |
Token | Americans |
Token ID | 3399 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
henko | +0.401 |
ramid | +0.352 |
� | +0.334 |
LV | +0.319 |
��� | +0.319 |
Neg logit contributions | |
margins | -0.464 |
rig | -0.439 |
agy | -0.404 |
hetical | -0.400 |
spiders | -0.384 |
Token | support |
Token ID | 1104 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
henko | +0.526 |
ramid | +0.471 |
� | +0.450 |
LV | +0.433 |
��� | +0.432 |
Neg logit contributions | |
margins | -0.453 |
rig | -0.424 |
agy | -0.384 |
hetical | -0.379 |
spiders | -0.362 |
Token | Graham |
Token ID | 11520 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
henko | +1.141 |
ramid | +1.008 |
� | +0.966 |
LV | +0.940 |
��� | +0.927 |
Neg logit contributions | |
margins | -0.995 |
rig | -0.944 |
agy | -0.861 |
hetical | -0.849 |
spiders | -0.809 |
Token | - |
Token ID | 12 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
henko | +0.317 |
ramid | +0.283 |
� | +0.272 |
LV | +0.262 |
��� | +0.260 |
Neg logit contributions | |
margins | -0.268 |
rig | -0.251 |
agy | -0.227 |
hetical | -0.225 |
spiders | -0.214 |
Token | Cass |
Token ID | 43529 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
henko | +0.281 |
ramid | +0.242 |
� | +0.220 |
��� | +0.212 |
LV | +0.204 |
Neg logit contributions | |
margins | -0.458 |
rig | -0.437 |
agy | -0.405 |
hetical | -0.401 |
spiders | -0.390 |
Token | idy |
Token ID | 19325 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
henko | +4.343 |
ramid | +3.862 |
� | +3.760 |
LV | +3.642 |
enza | +3.525 |
Neg logit contributions | |
margins | -2.822 |
rig | -2.590 |
agy | -2.275 |
hetical | -2.273 |
spiders | -2.168 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
henko | +1.805 |
ramid | +1.593 |
� | +1.534 |
LV | +1.487 |
��� | +1.430 |
Neg logit contributions | |
margins | -1.731 |
rig | -1.640 |
agy | -1.498 |
hetical | -1.497 |
spiders | -1.426 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
henko | +0.033 |
ramid | +0.030 |
� | +0.029 |
��� | +0.028 |
LV | +0.027 |
Neg logit contributions | |
margins | -0.027 |
rig | -0.025 |
agy | -0.022 |
hetical | -0.022 |
spiders | -0.021 |
Token | health |
Token ID | 1535 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
henko | +0.052 |
ramid | +0.046 |
� | +0.044 |
��� | +0.042 |
LV | +0.042 |
Neg logit contributions | |
margins | -0.049 |
rig | -0.046 |
agy | -0.042 |
hetical | -0.041 |
spiders | -0.039 |
Token | care |
Token ID | 1337 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
margins | +1.005 |
rig | +0.933 |
agy | +0.837 |
hetical | +0.827 |
spiders | +0.790 |
Neg logit contributions | |
henko | -1.276 |
ramid | -1.149 |
� | -1.097 |
��� | -1.063 |
LV | -1.058 |
Token | . |
Token ID | 13 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
henko | +1.466 |
ramid | +1.314 |
� | +1.250 |
LV | +1.197 |
��� | +1.172 |
Neg logit contributions | |
margins | -1.364 |
rig | -1.287 |
agy | -1.173 |
hetical | -1.155 |
spiders | -1.107 |
Token | This |
Token ID | 770 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
henko | +0.013 |
ramid | +0.012 |
� | +0.011 |
��� | +0.011 |
LV | +0.011 |
Neg logit contributions | |
margins | -0.013 |
rig | -0.013 |
agy | -0.011 |
hetical | -0.011 |
spiders | -0.011 |
Token | showed |
Token ID | 3751 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
henko | +0.076 |
ramid | +0.068 |
� | +0.065 |
LV | +0.063 |
��� | +0.062 |
Neg logit contributions | |
margins | -0.067 |
rig | -0.063 |
agy | -0.058 |
hetical | -0.057 |
spiders | -0.054 |
Token | very |
Token ID | 845 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
margins | +0.080 |
rig | +0.075 |
agy | +0.068 |
hetical | +0.067 |
spiders | +0.063 |
Neg logit contributions | |
henko | -0.102 |
ramid | -0.092 |
� | -0.088 |
LV | -0.085 |
��� | -0.084 |
Token | fast |
Token ID | 3049 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
henko | +0.501 |
ramid | +0.450 |
� | +0.430 |
LV | +0.415 |
��� | +0.414 |
Neg logit contributions | |
margins | -0.404 |
rig | -0.379 |
agy | -0.341 |
hetical | -0.336 |
spiders | -0.320 |
Token | pixel |
Token ID | 17465 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
henko | +0.234 |
ramid | +0.210 |
� | +0.201 |
LV | +0.193 |
��� | +0.192 |
Neg logit contributions | |
margins | -0.181 |
rig | -0.171 |
agy | -0.154 |
hetical | -0.152 |
spiders | -0.143 |
Token | response |
Token ID | 2882 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
henko | +3.952 |
ramid | +3.611 |
� | +3.412 |
��� | +3.250 |
LV | +3.233 |
Neg logit contributions | |
margins | -2.914 |
rig | -2.818 |
hetical | -2.513 |
agy | -2.506 |
raints | -2.380 |
Token | times |
Token ID | 1661 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
henko | +3.050 |
ramid | +2.689 |
� | +2.571 |
LV | +2.472 |
��� | +2.383 |
Neg logit contributions | |
margins | -2.672 |
rig | -2.597 |
agy | -2.383 |
hetical | -2.357 |
aura | -2.189 |
Token | ( |
Token ID | 357 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
henko | +0.851 |
ramid | +0.756 |
� | +0.722 |
LV | +0.697 |
��� | +0.683 |
Neg logit contributions | |
margins | -0.750 |
rig | -0.711 |
agy | -0.644 |
hetical | -0.636 |
spiders | -0.603 |
Token | 2 |
Token ID | 17 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
henko | +0.372 |
ramid | +0.329 |
� | +0.311 |
LV | +0.298 |
��� | +0.293 |
Neg logit contributions | |
margins | -0.425 |
rig | -0.399 |
agy | -0.367 |
hetical | -0.365 |
spiders | -0.352 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
henko | +0.131 |
ramid | +0.115 |
� | +0.109 |
LV | +0.104 |
��� | +0.104 |
Neg logit contributions | |
margins | -0.154 |
rig | -0.146 |
agy | -0.134 |
hetical | -0.133 |
spiders | -0.128 |
Token | - |
Token ID | 12 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
henko | +0.214 |
ramid | +0.191 |
� | +0.183 |
��� | +0.175 |
LV | +0.175 |
Neg logit contributions | |
margins | -0.201 |
rig | -0.189 |
agy | -0.171 |
hetical | -0.170 |
spiders | -0.163 |
Token | circ |
Token ID | 21170 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
margins | +0.080 |
rig | +0.074 |
agy | +0.066 |
hetical | +0.065 |
spiders | +0.061 |
Neg logit contributions | |
henko | -0.122 |
ramid | -0.111 |
� | -0.107 |
��� | -0.103 |
LV | -0.103 |
Token | u |
Token ID | 84 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
margins | +0.249 |
rig | +0.235 |
agy | +0.214 |
hetical | +0.212 |
spiders | +0.203 |
Neg logit contributions | |
henko | -0.246 |
ramid | -0.219 |
� | -0.208 |
��� | -0.201 |
LV | -0.200 |
Token | ited |
Token ID | 863 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
margins | +0.798 |
rig | +0.759 |
agy | +0.694 |
hetical | +0.689 |
spiders | +0.662 |
Neg logit contributions | |
henko | -0.671 |
ramid | -0.589 |
� | -0.557 |
��� | -0.537 |
LV | -0.532 |
Token | the |
Token ID | 262 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
margins | +0.531 |
rig | +0.497 |
agy | +0.450 |
hetical | +0.446 |
spiders | +0.425 |
Neg logit contributions | |
henko | -0.622 |
ramid | -0.557 |
� | -0.532 |
��� | -0.512 |
LV | -0.511 |
Token | courts |
Token ID | 8028 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
margins | +0.095 |
rig | +0.089 |
agy | +0.080 |
hetical | +0.080 |
spiders | +0.075 |
Neg logit contributions | |
henko | -0.117 |
ramid | -0.105 |
� | -0.100 |
��� | -0.097 |
LV | -0.096 |
Token | � |
Token ID | 447 |
Feature activation | -9.60e-03 |
Pos logit contributions | |
margins | +2.569 |
rig | +2.427 |
agy | +2.179 |
hetical | +2.143 |
spiders | +2.051 |
Neg logit contributions | |
henko | -2.922 |
ramid | -2.632 |
� | -2.488 |
��� | -2.440 |
LV | -2.415 |
Token | � |
Token ID | 247 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
henko | +0.019 |
ramid | +0.017 |
� | +0.016 |
��� | +0.015 |
LV | +0.015 |
Neg logit contributions | |
margins | -0.024 |
rig | -0.023 |
agy | -0.021 |
hetical | -0.021 |
spiders | -0.020 |
Token | constitutional |
Token ID | 9758 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
margins | +0.072 |
rig | +0.067 |
agy | +0.061 |
hetical | +0.060 |
spiders | +0.058 |
Neg logit contributions | |
henko | -0.080 |
ramid | -0.072 |
� | -0.069 |
LV | -0.066 |
��� | -0.066 |
Token | role |
Token ID | 2597 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
margins | +0.675 |
rig | +0.630 |
agy | +0.564 |
hetical | +0.557 |
spiders | +0.530 |
Neg logit contributions | |
henko | -0.893 |
ramid | -0.805 |
� | -0.771 |
��� | -0.743 |
LV | -0.743 |
Token | in |
Token ID | 287 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
henko | +0.008 |
ramid | +0.008 |
� | +0.007 |
��� | +0.007 |
LV | +0.007 |
Neg logit contributions | |
margins | -0.008 |
rig | -0.007 |
agy | -0.006 |
hetical | -0.006 |
spiders | -0.006 |
Token | count |
Token ID | 954 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
margins | +0.162 |
rig | +0.152 |
agy | +0.138 |
hetical | +0.137 |
spiders | +0.131 |
Neg logit contributions | |
henko | -0.176 |
ramid | -0.157 |
� | -0.149 |
��� | -0.144 |
LV | -0.143 |
Token | | |
Token ID | 930 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
margins | +1.497 |
rig | +1.413 |
agy | +1.282 |
hetical | +1.275 |
spiders | +1.229 |
Neg logit contributions | |
henko | -1.394 |
ramid | -1.228 |
� | -1.162 |
��� | -1.122 |
LV | -1.111 |
Token | | |
Token ID | 930 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
margins | +0.200 |
rig | +0.188 |
agy | +0.170 |
hetical | +0.169 |
spiders | +0.162 |
Neg logit contributions | |
henko | -0.210 |
ramid | -0.187 |
� | -0.178 |
��� | -0.171 |
LV | -0.171 |
Token | -------------------- |
Token ID | 41436 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
margins | +0.081 |
rig | +0.076 |
agy | +0.069 |
hetical | +0.069 |
spiders | +0.066 |
Neg logit contributions | |
henko | -0.083 |
ramid | -0.074 |
� | -0.070 |
��� | -0.067 |
LV | -0.067 |
Token | -+ |
Token ID | 19529 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
margins | +2.038 |
rig | +1.923 |
agy | +1.737 |
hetical | +1.732 |
spiders | +1.675 |
Neg logit contributions | |
henko | -1.927 |
ramid | -1.688 |
� | -1.598 |
��� | -1.548 |
LV | -1.529 |
Token | -------- |
Token ID | 982 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
margins | +2.384 |
rig | +2.266 |
agy | +2.071 |
hetical | +2.067 |
spiders | +2.003 |
Neg logit contributions | |
henko | -1.863 |
ramid | -1.618 |
� | -1.518 |
��� | -1.462 |
LV | -1.440 |
Token | -+ |
Token ID | 19529 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
margins | +3.112 |
rig | +2.921 |
agy | +2.628 |
hetical | +2.624 |
spiders | +2.520 |
Neg logit contributions | |
henko | -3.294 |
ramid | -2.918 |
� | -2.766 |
��� | -2.677 |
LV | -2.668 |
Token | ------- |
Token ID | 26866 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
margins | +2.218 |
rig | +2.103 |
agy | +1.923 |
hetical | +1.916 |
spiders | +1.850 |
Neg logit contributions | |
henko | -1.813 |
ramid | -1.584 |
� | -1.489 |
��� | -1.430 |
LV | -1.419 |
Token | | |
Token ID | 91 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
margins | +2.322 |
rig | +2.176 |
agy | +1.958 |
hetical | +1.947 |
spiders | +1.867 |
Neg logit contributions | |
henko | -2.613 |
ramid | -2.329 |
� | -2.215 |
��� | -2.146 |
LV | -2.132 |
Token | | |
Token ID | 930 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
margins | +1.124 |
rig | +1.063 |
agy | +0.971 |
hetical | +0.965 |
spiders | +0.932 |
Neg logit contributions | |
henko | -0.962 |
ramid | -0.845 |
� | -0.799 |
��� | -0.766 |
LV | -0.760 |
Token | org |
Token ID | 8745 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
margins | +0.137 |
rig | +0.129 |
agy | +0.117 |
hetical | +0.116 |
spiders | +0.112 |
Neg logit contributions | |
henko | -0.139 |
ramid | -0.123 |
� | -0.117 |
��� | -0.112 |
LV | -0.112 |
Token | indicator |
Token ID | 16916 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
margins | +0.643 |
rig | +0.603 |
agy | +0.545 |
hetical | +0.539 |
spiders | +0.515 |
Neg logit contributions | |
henko | -0.733 |
ramid | -0.656 |
� | -0.626 |
��� | -0.603 |
LV | -0.602 |
Token | of |
Token ID | 286 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
margins | +0.171 |
rig | +0.161 |
agy | +0.145 |
hetical | +0.143 |
spiders | +0.137 |
Neg logit contributions | |
henko | -0.200 |
ramid | -0.180 |
� | -0.171 |
��� | -0.165 |
LV | -0.165 |
Token | what |
Token ID | 644 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
henko | +0.058 |
ramid | +0.052 |
� | +0.050 |
LV | +0.048 |
��� | +0.048 |
Neg logit contributions | |
margins | -0.046 |
rig | -0.043 |
agy | -0.039 |
hetical | -0.039 |
spiders | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
margins | +0.022 |
rig | +0.021 |
agy | +0.019 |
hetical | +0.019 |
spiders | +0.018 |
Neg logit contributions | |
henko | -0.028 |
ramid | -0.025 |
� | -0.024 |
LV | -0.023 |
��� | -0.023 |
Token | cal |
Token ID | 2386 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
henko | +0.176 |
ramid | +0.161 |
� | +0.154 |
LV | +0.149 |
��� | +0.148 |
Neg logit contributions | |
margins | -0.102 |
rig | -0.094 |
agy | -0.083 |
hetical | -0.082 |
spiders | -0.077 |
Token | ving |
Token ID | 1075 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
margins | +0.827 |
rig | +0.772 |
agy | +0.708 |
hetical | +0.698 |
spiders | +0.675 |
Neg logit contributions | |
henko | -0.829 |
ramid | -0.730 |
� | -0.698 |
LV | -0.665 |
��� | -0.659 |
Token | event |
Token ID | 1785 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
margins | +2.417 |
rig | +2.213 |
agy | +1.898 |
hetical | +1.880 |
spiders | +1.803 |
Neg logit contributions | |
henko | -4.217 |
ramid | -3.857 |
� | -3.693 |
��� | -3.652 |
LV | -3.574 |
Token | means |
Token ID | 1724 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
margins | +0.961 |
rig | +0.898 |
agy | +0.807 |
hetical | +0.798 |
spiders | +0.763 |
Neg logit contributions | |
henko | -1.183 |
ramid | -1.064 |
� | -1.016 |
��� | -0.981 |
LV | -0.978 |
Token | at |
Token ID | 379 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
margins | +0.166 |
rig | +0.155 |
agy | +0.140 |
hetical | +0.139 |
spiders | +0.133 |
Neg logit contributions | |
henko | -0.193 |
ramid | -0.173 |
� | -0.165 |
��� | -0.159 |
LV | -0.159 |
Token | a |
Token ID | 257 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
margins | +0.596 |
rig | +0.558 |
agy | +0.508 |
hetical | +0.500 |
spiders | +0.473 |
Neg logit contributions | |
henko | -0.756 |
ramid | -0.681 |
� | -0.652 |
LV | -0.627 |
��� | -0.620 |
Token | particular |
Token ID | 1948 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
margins | +0.327 |
rig | +0.309 |
agy | +0.283 |
hetical | +0.280 |
spiders | +0.269 |
Neg logit contributions | |
henko | -0.313 |
ramid | -0.277 |
� | -0.263 |
LV | -0.252 |
��� | -0.251 |
Token | and |
Token ID | 290 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
henko | +0.049 |
ramid | +0.044 |
� | +0.042 |
LV | +0.040 |
��� | +0.040 |
Neg logit contributions | |
margins | -0.043 |
rig | -0.040 |
agy | -0.037 |
hetical | -0.036 |
spiders | -0.034 |
Token | half |
Token ID | 2063 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
henko | +0.411 |
ramid | +0.368 |
� | +0.352 |
LV | +0.338 |
��� | +0.337 |
Neg logit contributions | |
margins | -0.333 |
rig | -0.311 |
agy | -0.282 |
hetical | -0.279 |
spiders | -0.263 |
Token | a |
Token ID | 257 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
margins | +0.667 |
rig | +0.624 |
agy | +0.559 |
hetical | +0.553 |
spiders | +0.528 |
Neg logit contributions | |
henko | -0.845 |
ramid | -0.761 |
� | -0.727 |
��� | -0.703 |
LV | -0.701 |
Token | cup |
Token ID | 6508 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
henko | +0.582 |
ramid | +0.520 |
� | +0.496 |
LV | +0.476 |
��� | +0.473 |
Neg logit contributions | |
margins | -0.512 |
rig | -0.478 |
agy | -0.437 |
hetical | -0.431 |
spiders | -0.410 |
Token | c |
Token ID | 269 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
henko | +0.402 |
ramid | +0.357 |
� | +0.342 |
LV | +0.327 |
��� | +0.324 |
Neg logit contributions | |
margins | -0.361 |
rig | -0.337 |
agy | -0.310 |
hetical | -0.303 |
spiders | -0.289 |
Token | ilantro |
Token ID | 48311 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
henko | +0.725 |
ramid | +0.626 |
� | +0.588 |
LV | +0.560 |
��� | +0.546 |
Neg logit contributions | |
margins | -0.914 |
rig | -0.852 |
agy | -0.783 |
hetical | -0.781 |
spiders | -0.757 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
margins | +2.786 |
rig | +2.609 |
agy | +2.312 |
hetical | +2.297 |
spiders | +2.239 |
Neg logit contributions | |
henko | -3.227 |
ramid | -2.899 |
� | -2.745 |
��� | -2.714 |
LV | -2.657 |
Token | We |
Token ID | 775 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
henko | +0.273 |
ramid | +0.244 |
� | +0.233 |
LV | +0.224 |
��� | +0.223 |
Neg logit contributions | |
margins | -0.250 |
rig | -0.234 |
agy | -0.213 |
hetical | -0.210 |
spiders | -0.201 |
Token | then |
Token ID | 788 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
henko | +0.407 |
ramid | +0.364 |
� | +0.348 |
LV | +0.333 |
��� | +0.333 |
Neg logit contributions | |
margins | -0.355 |
rig | -0.332 |
agy | -0.301 |
hetical | -0.297 |
spiders | -0.284 |
Token | add |
Token ID | 751 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
margins | +0.027 |
rig | +0.025 |
agy | +0.022 |
hetical | +0.022 |
spiders | +0.021 |
Neg logit contributions | |
henko | -0.035 |
ramid | -0.031 |
� | -0.030 |
LV | -0.029 |
��� | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
henko | +0.818 |
ramid | +0.730 |
� | +0.699 |
LV | +0.670 |
��� | +0.669 |
Neg logit contributions | |
margins | -0.712 |
rig | -0.668 |
agy | -0.607 |
hetical | -0.599 |
spiders | -0.568 |
Token | of |
Token ID | 286 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
henko | +0.851 |
ramid | +0.751 |
� | +0.725 |
LV | +0.695 |
��� | +0.678 |
Neg logit contributions | |
margins | -0.766 |
rig | -0.718 |
agy | -0.653 |
hetical | -0.644 |
spiders | -0.620 |
Token | a |
Token ID | 257 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
henko | +0.389 |
ramid | +0.347 |
� | +0.332 |
LV | +0.319 |
��� | +0.318 |
Neg logit contributions | |
margins | -0.341 |
rig | -0.321 |
agy | -0.290 |
hetical | -0.287 |
spiders | -0.273 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
henko | +0.147 |
ramid | +0.131 |
� | +0.125 |
��� | +0.120 |
LV | +0.120 |
Neg logit contributions | |
margins | -0.132 |
rig | -0.124 |
agy | -0.112 |
hetical | -0.111 |
spiders | -0.106 |
Token | fit |
Token ID | 4197 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
henko | +0.351 |
ramid | +0.314 |
� | +0.300 |
LV | +0.288 |
��� | +0.288 |
Neg logit contributions | |
margins | -0.309 |
rig | -0.291 |
agy | -0.263 |
hetical | -0.260 |
spiders | -0.248 |
Token | with |
Token ID | 351 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
henko | +0.936 |
ramid | +0.824 |
� | +0.791 |
LV | +0.757 |
��� | +0.749 |
Neg logit contributions | |
margins | -0.906 |
rig | -0.854 |
agy | -0.776 |
hetical | -0.768 |
spiders | -0.736 |
Token | Raj |
Token ID | 13308 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
henko | +0.791 |
ramid | +0.705 |
� | +0.673 |
LV | +0.648 |
��� | +0.648 |
Neg logit contributions | |
margins | -0.700 |
rig | -0.659 |
agy | -0.596 |
hetical | -0.590 |
spiders | -0.562 |
Token | on |
Token ID | 261 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
margins | +2.679 |
rig | +2.531 |
agy | +2.254 |
hetical | +2.221 |
spiders | +2.127 |
Neg logit contributions | |
henko | -3.213 |
ramid | -2.902 |
� | -2.763 |
��� | -2.679 |
LV | -2.641 |
Token | R |
Token ID | 371 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
margins | +0.747 |
rig | +0.696 |
agy | +0.617 |
hetical | +0.614 |
spiders | +0.584 |
Neg logit contributions | |
henko | -1.019 |
ramid | -0.922 |
� | -0.884 |
��� | -0.850 |
LV | -0.847 |
Token | ondo |
Token ID | 22311 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
margins | +2.052 |
rig | +1.993 |
agy | +1.826 |
hetical | +1.807 |
rac | +1.726 |
Neg logit contributions | |
henko | -1.526 |
ramid | -1.353 |
� | -1.277 |
��� | -1.250 |
LV | -1.207 |
Token | ? |
Token ID | 30 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
margins | +0.688 |
rig | +0.642 |
agy | +0.577 |
hetical | +0.570 |
spiders | +0.545 |
Neg logit contributions | |
henko | -0.856 |
ramid | -0.771 |
� | -0.736 |
��� | -0.711 |
LV | -0.709 |
Token | Why |
Token ID | 4162 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
margins | +0.793 |
rig | +0.744 |
agy | +0.673 |
hetical | +0.668 |
spiders | +0.635 |
Neg logit contributions | |
henko | -0.863 |
ramid | -0.775 |
� | -0.735 |
��� | -0.717 |
LV | -0.701 |
Token | absence |
Token ID | 8889 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
margins | +0.066 |
rig | +0.062 |
agy | +0.056 |
hetical | +0.055 |
spiders | +0.053 |
Neg logit contributions | |
henko | -0.079 |
ramid | -0.071 |
� | -0.067 |
��� | -0.065 |
LV | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
margins | +1.387 |
rig | +1.298 |
agy | +1.167 |
hetical | +1.156 |
spiders | +1.105 |
Neg logit contributions | |
henko | -1.646 |
ramid | -1.480 |
� | -1.411 |
��� | -1.371 |
LV | -1.356 |
Token | v |
Token ID | 410 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
margins | +0.217 |
rig | +0.204 |
agy | +0.184 |
hetical | +0.182 |
spiders | +0.171 |
Neg logit contributions | |
henko | -0.280 |
ramid | -0.251 |
� | -0.240 |
LV | -0.232 |
��� | -0.230 |
Token | ort |
Token ID | 419 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
margins | +0.811 |
rig | +0.755 |
agy | +0.678 |
hetical | +0.670 |
spiders | +0.639 |
Neg logit contributions | |
henko | -1.044 |
ramid | -0.940 |
� | -0.899 |
LV | -0.867 |
��� | -0.862 |
Token | ons |
Token ID | 684 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
margins | +0.238 |
rig | +0.221 |
agy | +0.200 |
hetical | +0.198 |
spiders | +0.189 |
Neg logit contributions | |
henko | -0.286 |
ramid | -0.256 |
� | -0.244 |
LV | -0.235 |
��� | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
margins | +0.161 |
rig | +0.151 |
agy | +0.136 |
hetical | +0.135 |
spiders | +0.129 |
Neg logit contributions | |
henko | -0.179 |
ramid | -0.160 |
� | -0.153 |
��� | -0.148 |
LV | -0.147 |
Token | V |
Token ID | 569 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
margins | +0.446 |
rig | +0.420 |
agy | +0.382 |
hetical | +0.378 |
spiders | +0.364 |
Neg logit contributions | |
henko | -0.441 |
ramid | -0.391 |
� | -0.372 |
��� | -0.357 |
LV | -0.356 |
Token | ort |
Token ID | 419 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
margins | +0.162 |
rig | +0.151 |
agy | +0.136 |
hetical | +0.134 |
spiders | +0.128 |
Neg logit contributions | |
henko | -0.211 |
ramid | -0.190 |
� | -0.182 |
��� | -0.176 |
LV | -0.176 |
Token | ons |
Token ID | 684 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
henko | +0.856 |
ramid | +0.766 |
� | +0.729 |
LV | +0.702 |
��� | +0.701 |
Neg logit contributions | |
margins | -0.715 |
rig | -0.668 |
agy | -0.602 |
hetical | -0.596 |
spiders | -0.571 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
henko | +0.527 |
ramid | +0.472 |
� | +0.450 |
LV | +0.434 |
��� | +0.432 |
Neg logit contributions | |
margins | -0.446 |
rig | -0.419 |
agy | -0.377 |
hetical | -0.374 |
spiders | -0.355 |
Token | meanwhile |
Token ID | 15066 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
margins | +0.213 |
rig | +0.199 |
agy | +0.180 |
hetical | +0.178 |
spiders | +0.170 |
Neg logit contributions | |
henko | -0.250 |
ramid | -0.224 |
� | -0.214 |
��� | -0.206 |
LV | -0.206 |
Token | to |
Token ID | 284 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
henko | +0.923 |
ramid | +0.820 |
� | +0.791 |
LV | +0.753 |
��� | +0.742 |
Neg logit contributions | |
margins | -0.879 |
rig | -0.829 |
hetical | -0.753 |
agy | -0.748 |
spiders | -0.716 |
Token | living |
Token ID | 2877 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
margins | +0.187 |
rig | +0.174 |
agy | +0.156 |
hetical | +0.154 |
spiders | +0.148 |
Neg logit contributions | |
henko | -0.240 |
ramid | -0.217 |
� | -0.207 |
��� | -0.199 |
LV | -0.199 |
Token | brains |
Token ID | 14290 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
margins | +0.072 |
rig | +0.067 |
agy | +0.060 |
hetical | +0.059 |
spiders | +0.056 |
Neg logit contributions | |
henko | -0.098 |
ramid | -0.088 |
� | -0.085 |
��� | -0.082 |
LV | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
henko | +0.033 |
ramid | +0.030 |
� | +0.028 |
��� | +0.027 |
LV | +0.027 |
Neg logit contributions | |
margins | -0.030 |
rig | -0.028 |
agy | -0.025 |
hetical | -0.025 |
spiders | -0.024 |
Token | To |
Token ID | 1675 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
henko | +0.046 |
ramid | +0.041 |
� | +0.039 |
��� | +0.038 |
LV | +0.037 |
Neg logit contributions | |
margins | -0.047 |
rig | -0.045 |
agy | -0.041 |
hetical | -0.040 |
spiders | -0.039 |
Token | study |
Token ID | 2050 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
henko | +0.036 |
ramid | +0.032 |
� | +0.031 |
LV | +0.030 |
��� | +0.030 |
Neg logit contributions | |
margins | -0.027 |
rig | -0.025 |
agy | -0.022 |
hetical | -0.022 |
spiders | -0.021 |
Token | both |
Token ID | 1111 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
margins | +0.633 |
rig | +0.592 |
agy | +0.533 |
hetical | +0.527 |
spiders | +0.506 |
Neg logit contributions | |
henko | -0.756 |
ramid | -0.682 |
� | -0.648 |
��� | -0.625 |
LV | -0.624 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
henko | +0.424 |
ramid | +0.380 |
� | +0.365 |
LV | +0.351 |
��� | +0.351 |
Neg logit contributions | |
margins | -0.345 |
rig | -0.323 |
agy | -0.290 |
hetical | -0.287 |
spiders | -0.273 |
Token | nature |
Token ID | 3450 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
henko | +0.532 |
ramid | +0.478 |
� | +0.459 |
LV | +0.442 |
��� | +0.441 |
Neg logit contributions | |
margins | -0.404 |
rig | -0.378 |
agy | -0.338 |
hetical | -0.335 |
spiders | -0.317 |
Token | of |
Token ID | 286 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
henko | +0.956 |
ramid | +0.855 |
� | +0.820 |
LV | +0.788 |
��� | +0.787 |
Neg logit contributions | |
margins | -0.822 |
rig | -0.771 |
agy | -0.696 |
hetical | -0.689 |
spiders | -0.657 |
Token | seizures |
Token ID | 24715 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
henko | +0.762 |
ramid | +0.678 |
� | +0.649 |
LV | +0.623 |
��� | +0.622 |
Neg logit contributions | |
margins | -0.697 |
rig | -0.655 |
agy | -0.594 |
hetical | -0.588 |
spiders | -0.560 |
Token | weather |
Token ID | 6193 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
henko | +0.436 |
ramid | +0.390 |
� | +0.378 |
LV | +0.363 |
��� | +0.354 |
Neg logit contributions | |
margins | -0.324 |
rig | -0.306 |
agy | -0.276 |
hetical | -0.271 |
spiders | -0.254 |
Token | events |
Token ID | 2995 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
margins | +1.824 |
rig | +1.678 |
agy | +1.472 |
hetical | +1.438 |
spiders | +1.386 |
Neg logit contributions | |
henko | -2.894 |
ramid | -2.646 |
� | -2.515 |
��� | -2.485 |
LV | -2.440 |
Token | linked |
Token ID | 6692 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
margins | +1.884 |
rig | +1.750 |
agy | +1.563 |
hetical | +1.536 |
spiders | +1.491 |
Neg logit contributions | |
henko | -2.355 |
ramid | -2.148 |
� | -2.024 |
��� | -2.006 |
LV | -1.950 |
Token | to |
Token ID | 284 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
henko | +0.661 |
ramid | +0.588 |
� | +0.563 |
LV | +0.537 |
��� | +0.528 |
Neg logit contributions | |
margins | -0.612 |
rig | -0.576 |
agy | -0.523 |
hetical | -0.519 |
spiders | -0.494 |
Token | climate |
Token ID | 4258 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
henko | +0.792 |
ramid | +0.712 |
� | +0.681 |
LV | +0.656 |
��� | +0.652 |
Neg logit contributions | |
margins | -0.637 |
rig | -0.598 |
agy | -0.541 |
hetical | -0.535 |
spiders | -0.505 |
Token | change |
Token ID | 1487 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
margins | +0.159 |
rig | +0.142 |
agy | +0.119 |
hetical | +0.117 |
spiders | +0.104 |
Neg logit contributions | |
henko | -0.432 |
ramid | -0.397 |
� | -0.386 |
LV | -0.375 |
��� | -0.372 |
Token | , |
Token ID | 11 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
margins | +1.490 |
rig | +1.392 |
agy | +1.245 |
hetical | +1.227 |
spiders | +1.187 |
Neg logit contributions | |
henko | -1.763 |
ramid | -1.592 |
� | -1.509 |
��� | -1.478 |
LV | -1.450 |
Token | and |
Token ID | 290 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
henko | +0.115 |
ramid | +0.104 |
� | +0.099 |
LV | +0.096 |
��� | +0.095 |
Neg logit contributions | |
margins | -0.090 |
rig | -0.084 |
agy | -0.076 |
hetical | -0.075 |
spiders | -0.071 |
Token | other |
Token ID | 584 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
henko | +0.317 |
ramid | +0.286 |
� | +0.274 |
LV | +0.264 |
��� | +0.263 |
Neg logit contributions | |
margins | -0.234 |
rig | -0.219 |
agy | -0.197 |
hetical | -0.194 |
spiders | -0.184 |
Token | social |
Token ID | 1919 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
henko | +0.548 |
ramid | +0.500 |
� | +0.482 |
LV | +0.465 |
��� | +0.459 |
Neg logit contributions | |
margins | -0.326 |
rig | -0.305 |
agy | -0.272 |
hetical | -0.266 |
spiders | -0.246 |
Token | costs |
Token ID | 3484 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
margins | +1.147 |
rig | +1.070 |
agy | +0.949 |
hetical | +0.931 |
spiders | +0.876 |
Neg logit contributions | |
henko | -1.802 |
ramid | -1.638 |
� | -1.575 |
LV | -1.519 |
��� | -1.508 |
Token | well |
Token ID | 880 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
margins | +0.351 |
rig | +0.328 |
agy | +0.295 |
hetical | +0.292 |
spiders | +0.277 |
Neg logit contributions | |
henko | -0.452 |
ramid | -0.406 |
� | -0.389 |
LV | -0.375 |
��� | -0.374 |
Token | as |
Token ID | 355 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
margins | +0.340 |
rig | +0.317 |
agy | +0.283 |
hetical | +0.280 |
spiders | +0.265 |
Neg logit contributions | |
henko | -0.470 |
ramid | -0.424 |
� | -0.407 |
LV | -0.392 |
��� | -0.391 |
Token | in |
Token ID | 287 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
margins | +0.032 |
rig | +0.030 |
agy | +0.027 |
hetical | +0.027 |
spiders | +0.026 |
Neg logit contributions | |
henko | -0.038 |
ramid | -0.034 |
� | -0.033 |
LV | -0.031 |
��� | -0.031 |
Token | - |
Token ID | 12 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
margins | +0.260 |
rig | +0.246 |
agy | +0.224 |
hetical | +0.222 |
spiders | +0.213 |
Neg logit contributions | |
henko | -0.249 |
ramid | -0.220 |
� | -0.209 |
��� | -0.200 |
LV | -0.200 |
Token | game |
Token ID | 6057 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
henko | +0.147 |
ramid | +0.134 |
� | +0.128 |
LV | +0.124 |
��� | +0.123 |
Neg logit contributions | |
margins | -0.100 |
rig | -0.092 |
agy | -0.082 |
hetical | -0.081 |
spiders | -0.077 |
Token | bonuses |
Token ID | 17568 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
margins | +0.801 |
rig | +0.746 |
agy | +0.667 |
hetical | +0.659 |
spiders | +0.627 |
Neg logit contributions | |
henko | -1.076 |
ramid | -0.970 |
� | -0.930 |
��� | -0.897 |
LV | -0.897 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
margins | +0.410 |
rig | +0.385 |
agy | +0.349 |
hetical | +0.345 |
spiders | +0.330 |
Neg logit contributions | |
henko | -0.453 |
ramid | -0.405 |
� | -0.386 |
��� | -0.372 |
LV | -0.371 |
Token | Some |
Token ID | 2773 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
margins | +0.396 |
rig | +0.372 |
agy | +0.335 |
hetical | +0.332 |
spiders | +0.317 |
Neg logit contributions | |
henko | -0.454 |
ramid | -0.407 |
� | -0.388 |
��� | -0.374 |
LV | -0.373 |
Token | had |
Token ID | 550 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
henko | +0.516 |
ramid | +0.460 |
� | +0.441 |
LV | +0.426 |
��� | +0.421 |
Neg logit contributions | |
margins | -0.418 |
rig | -0.393 |
agy | -0.354 |
hetical | -0.351 |
spiders | -0.331 |
Token | already |
Token ID | 1541 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
margins | +0.266 |
rig | +0.251 |
agy | +0.228 |
hetical | +0.225 |
spiders | +0.215 |
Neg logit contributions | |
henko | -0.289 |
ramid | -0.258 |
� | -0.246 |
LV | -0.236 |
��� | -0.236 |
Token | shipped |
Token ID | 14338 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
henko | +0.574 |
ramid | +0.505 |
� | +0.479 |
LV | +0.458 |
��� | +0.458 |
Neg logit contributions | |
margins | -0.635 |
rig | -0.601 |
agy | -0.550 |
hetical | -0.545 |
spiders | -0.523 |
Token | gin |
Token ID | 39733 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
margins | +0.632 |
rig | +0.592 |
agy | +0.534 |
hetical | +0.527 |
spiders | +0.505 |
Neg logit contributions | |
henko | -0.742 |
ramid | -0.665 |
� | -0.635 |
��� | -0.611 |
LV | -0.611 |
Token | ag |
Token ID | 363 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
margins | +0.049 |
rig | +0.046 |
agy | +0.041 |
hetical | +0.040 |
spiders | +0.038 |
Neg logit contributions | |
henko | -0.067 |
ramid | -0.060 |
� | -0.058 |
LV | -0.056 |
��� | -0.056 |
Token | awa |
Token ID | 6909 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
henko | +1.362 |
ramid | +1.199 |
� | +1.133 |
LV | +1.083 |
��� | +1.082 |
Neg logit contributions | |
margins | -1.444 |
rig | -1.354 |
agy | -1.241 |
hetical | -1.230 |
spiders | -1.189 |
Token | n |
Token ID | 299 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
henko | +0.307 |
ramid | +0.273 |
� | +0.260 |
LV | +0.250 |
��� | +0.249 |
Neg logit contributions | |
margins | -0.286 |
rig | -0.269 |
agy | -0.244 |
hetical | -0.243 |
spiders | -0.232 |
Token | atin |
Token ID | 10680 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
henko | +0.221 |
ramid | +0.197 |
� | +0.188 |
LV | +0.180 |
��� | +0.180 |
Neg logit contributions | |
margins | -0.195 |
rig | -0.181 |
agy | -0.164 |
hetical | -0.163 |
spiders | -0.156 |
Token | ay |
Token ID | 38762 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
margins | +0.455 |
rig | +0.426 |
agy | +0.386 |
hetical | +0.382 |
spiders | +0.366 |
Neg logit contributions | |
henko | -0.508 |
ramid | -0.454 |
� | -0.433 |
LV | -0.416 |
��� | -0.416 |
Token | n |
Token ID | 299 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
margins | +1.325 |
rig | +1.250 |
agy | +1.131 |
hetical | +1.114 |
spiders | +1.068 |
Neg logit contributions | |
henko | -1.432 |
ramid | -1.279 |
� | -1.218 |
��� | -1.172 |
LV | -1.172 |
Token | aa |
Token ID | 7252 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
henko | +0.089 |
ramid | +0.080 |
� | +0.076 |
LV | +0.073 |
��� | +0.073 |
Neg logit contributions | |
margins | -0.080 |
rig | -0.074 |
agy | -0.067 |
hetical | -0.067 |
spiders | -0.064 |
Token | ay |
Token ID | 323 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
margins | +0.185 |
rig | +0.173 |
agy | +0.157 |
hetical | +0.156 |
spiders | +0.149 |
Neg logit contributions | |
henko | -0.204 |
ramid | -0.182 |
� | -0.174 |
LV | -0.167 |
��� | -0.166 |
Token | on |
Token ID | 261 |
Feature activation | -9.39e-02 |
Pos logit contributions | |
margins | +1.366 |
rig | +1.288 |
agy | +1.163 |
hetical | +1.147 |
spiders | +1.098 |
Neg logit contributions | |
henko | -1.504 |
ramid | -1.346 |
� | -1.281 |
��� | -1.238 |
LV | -1.234 |
Token | sa |
Token ID | 473 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
henko | +0.222 |
ramid | +0.198 |
� | +0.189 |
LV | +0.181 |
��� | +0.181 |
Neg logit contributions | |
margins | -0.203 |
rig | -0.189 |
agy | -0.172 |
hetical | -0.171 |
spiders | -0.164 |
Token | Air |
Token ID | 3701 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
henko | +0.142 |
ramid | +0.127 |
� | +0.120 |
��� | +0.117 |
LV | +0.115 |
Neg logit contributions | |
margins | -0.128 |
rig | -0.121 |
agy | -0.109 |
hetical | -0.108 |
spiders | -0.103 |
Token | Force |
Token ID | 5221 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
henko | +0.766 |
ramid | +0.692 |
� | +0.665 |
LV | +0.641 |
��� | +0.639 |
Neg logit contributions | |
margins | -0.565 |
rig | -0.527 |
agy | -0.470 |
hetical | -0.468 |
spiders | -0.442 |
Token | research |
Token ID | 2267 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
margins | +0.162 |
rig | +0.152 |
agy | +0.137 |
hetical | +0.135 |
spiders | +0.130 |
Neg logit contributions | |
henko | -0.193 |
ramid | -0.174 |
� | -0.165 |
��� | -0.160 |
LV | -0.159 |
Token | labs |
Token ID | 27887 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
margins | +0.181 |
rig | +0.170 |
agy | +0.152 |
hetical | +0.151 |
spiders | +0.143 |
Neg logit contributions | |
henko | -0.227 |
ramid | -0.204 |
� | -0.195 |
LV | -0.188 |
��� | -0.188 |
Token | across |
Token ID | 1973 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
henko | +0.149 |
ramid | +0.133 |
� | +0.127 |
��� | +0.122 |
LV | +0.122 |
Neg logit contributions | |
margins | -0.126 |
rig | -0.118 |
agy | -0.106 |
hetical | -0.105 |
spiders | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | -6.82e-04 |
Pos logit contributions | |
margins | +0.339 |
rig | +0.318 |
agy | +0.287 |
hetical | +0.284 |
spiders | +0.271 |
Neg logit contributions | |
henko | -0.400 |
ramid | -0.359 |
� | -0.343 |
��� | -0.330 |
LV | -0.330 |
Token | country |
Token ID | 1499 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
henko | +0.002 |
ramid | +0.001 |
� | +0.001 |
LV | +0.001 |
��� | +0.001 |
Neg logit contributions | |
margins | -0.002 |
rig | -0.001 |
agy | -0.001 |
hetical | -0.001 |
spiders | -0.001 |
Token | sponsor |
Token ID | 17487 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
margins | +0.067 |
rig | +0.063 |
agy | +0.057 |
hetical | +0.056 |
spiders | +0.053 |
Neg logit contributions | |
henko | -0.081 |
ramid | -0.073 |
� | -0.070 |
��� | -0.067 |
LV | -0.067 |
Token | similar |
Token ID | 2092 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
henko | +0.430 |
ramid | +0.388 |
� | +0.373 |
LV | +0.360 |
��� | +0.359 |
Neg logit contributions | |
margins | -0.318 |
rig | -0.297 |
agy | -0.266 |
hetical | -0.262 |
spiders | -0.249 |
Token | contests |
Token ID | 22830 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
margins | +0.777 |
rig | +0.730 |
agy | +0.662 |
hetical | +0.656 |
spiders | +0.631 |
Neg logit contributions | |
henko | -0.795 |
ramid | -0.708 |
� | -0.672 |
��� | -0.648 |
LV | -0.644 |
Token | on |
Token ID | 319 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
margins | +0.256 |
rig | +0.240 |
agy | +0.216 |
hetical | +0.214 |
spiders | +0.204 |
Neg logit contributions | |
henko | -0.296 |
ramid | -0.265 |
� | -0.252 |
��� | -0.245 |
LV | -0.243 |
Token | , |
Token ID | 11 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
margins | +0.492 |
rig | +0.464 |
agy | +0.424 |
hetical | +0.420 |
spiders | +0.403 |
Neg logit contributions | |
henko | -0.467 |
ramid | -0.413 |
� | -0.393 |
��� | -0.377 |
LV | -0.376 |
Token | Train |
Token ID | 16835 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
henko | +0.213 |
ramid | +0.188 |
� | +0.179 |
��� | +0.171 |
LV | +0.171 |
Neg logit contributions | |
margins | -0.221 |
rig | -0.208 |
agy | -0.190 |
hetical | -0.188 |
spiders | -0.181 |
Token | wreck |
Token ID | 39238 |
Feature activation | -7.15e-03 |
Pos logit contributions | |
henko | +0.346 |
ramid | +0.309 |
� | +0.294 |
LV | +0.283 |
��� | +0.280 |
Neg logit contributions | |
margins | -0.334 |
rig | -0.314 |
agy | -0.286 |
hetical | -0.282 |
spiders | -0.270 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
henko | +0.017 |
ramid | +0.015 |
� | +0.014 |
��� | +0.014 |
LV | +0.014 |
Neg logit contributions | |
margins | -0.015 |
rig | -0.014 |
agy | -0.013 |
hetical | -0.013 |
spiders | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
henko | +0.670 |
ramid | +0.598 |
� | +0.572 |
LV | +0.551 |
��� | +0.549 |
Neg logit contributions | |
margins | -0.563 |
rig | -0.529 |
agy | -0.477 |
hetical | -0.473 |
spiders | -0.449 |
Token | a |
Token ID | 257 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
henko | +0.603 |
ramid | +0.539 |
� | +0.517 |
LV | +0.499 |
��� | +0.496 |
Neg logit contributions | |
margins | -0.488 |
rig | -0.458 |
agy | -0.414 |
hetical | -0.408 |
spiders | -0.386 |
Token | Lafayette |
Token ID | 41388 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
henko | +0.522 |
ramid | +0.467 |
� | +0.446 |
LV | +0.430 |
��� | +0.430 |
Neg logit contributions | |
margins | -0.449 |
rig | -0.421 |
agy | -0.381 |
hetical | -0.377 |
spiders | -0.359 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
henko | +2.106 |
ramid | +1.859 |
� | +1.772 |
LV | +1.722 |
��� | +1.703 |
Neg logit contributions | |
margins | -2.128 |
rig | -2.002 |
agy | -1.844 |
hetical | -1.816 |
spiders | -1.739 |
Token | Louisiana |
Token ID | 13340 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
henko | +0.557 |
ramid | +0.500 |
� | +0.478 |
LV | +0.461 |
��� | +0.459 |
Neg logit contributions | |
margins | -0.466 |
rig | -0.437 |
agy | -0.394 |
hetical | -0.390 |
spiders | -0.372 |
Token | theater |
Token ID | 13766 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
henko | +1.674 |
ramid | +1.486 |
� | +1.420 |
LV | +1.377 |
��� | +1.362 |
Neg logit contributions | |
margins | -1.558 |
rig | -1.461 |
agy | -1.342 |
hetical | -1.319 |
spiders | -1.259 |
Token | in |
Token ID | 287 |
Feature activation | -5.69e-04 |
Pos logit contributions | |
henko | +1.021 |
ramid | +0.914 |
� | +0.875 |
LV | +0.847 |
��� | +0.835 |
Neg logit contributions | |
margins | -0.853 |
rig | -0.796 |
agy | -0.721 |
hetical | -0.717 |
spiders | -0.678 |
Token | time |
Token ID | 640 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
margins | +0.469 |
rig | +0.440 |
agy | +0.394 |
hetical | +0.390 |
spiders | +0.368 |
Neg logit contributions | |
henko | -0.627 |
ramid | -0.565 |
� | -0.541 |
LV | -0.521 |
��� | -0.520 |
Token | to |
Token ID | 284 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
margins | +1.083 |
rig | +1.012 |
agy | +0.907 |
hetical | +0.898 |
spiders | +0.859 |
Neg logit contributions | |
henko | -1.325 |
ramid | -1.190 |
� | -1.132 |
��� | -1.101 |
LV | -1.093 |
Token | lose |
Token ID | 4425 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
margins | +0.446 |
rig | +0.416 |
agy | +0.372 |
hetical | +0.367 |
spiders | +0.350 |
Neg logit contributions | |
henko | -0.594 |
ramid | -0.536 |
� | -0.513 |
��� | -0.496 |
LV | -0.495 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
margins | +0.692 |
rig | +0.648 |
agy | +0.585 |
hetical | +0.578 |
spiders | +0.554 |
Neg logit contributions | |
henko | -0.788 |
ramid | -0.706 |
� | -0.671 |
��� | -0.649 |
LV | -0.646 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
henko | +0.128 |
ramid | +0.114 |
� | +0.109 |
LV | +0.105 |
��� | +0.104 |
Neg logit contributions | |
margins | -0.114 |
rig | -0.107 |
agy | -0.097 |
hetical | -0.096 |
spiders | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
margins | +0.044 |
rig | +0.041 |
agy | +0.037 |
hetical | +0.037 |
spiders | +0.035 |
Neg logit contributions | |
henko | -0.051 |
ramid | -0.046 |
� | -0.044 |
LV | -0.042 |
��� | -0.041 |
Token | Adapt |
Token ID | 48003 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
henko | +0.057 |
ramid | +0.050 |
� | +0.047 |
��� | +0.045 |
LV | +0.045 |
Neg logit contributions | |
margins | -0.069 |
rig | -0.066 |
agy | -0.060 |
hetical | -0.060 |
spiders | -0.058 |
Token | ed |
Token ID | 276 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
margins | +0.197 |
rig | +0.181 |
agy | +0.158 |
hetical | +0.157 |
spiders | +0.146 |
Neg logit contributions | |
henko | -0.352 |
ramid | -0.321 |
� | -0.310 |
LV | -0.300 |
��� | -0.298 |
Token | from |
Token ID | 422 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
margins | +0.397 |
rig | +0.378 |
agy | +0.351 |
hetical | +0.346 |
spiders | +0.334 |
Neg logit contributions | |
henko | -0.289 |
ramid | -0.251 |
� | -0.236 |
LV | -0.225 |
��� | -0.224 |
Token | the |
Token ID | 262 |
Feature activation | -3.16e-03 |
Pos logit contributions | |
margins | +0.590 |
rig | +0.553 |
agy | +0.502 |
hetical | +0.497 |
spiders | +0.477 |
Neg logit contributions | |
henko | -0.627 |
ramid | -0.560 |
� | -0.532 |
��� | -0.511 |
LV | -0.511 |
Token | forthcoming |
Token ID | 21220 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
henko | +0.008 |
ramid | +0.007 |
� | +0.006 |
��� | +0.006 |
LV | +0.006 |
Neg logit contributions | |
margins | -0.007 |
rig | -0.006 |
agy | -0.006 |
hetical | -0.006 |
spiders | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
henko | +1.271 |
ramid | +1.127 |
� | +1.075 |
LV | +1.040 |
��� | +1.024 |
Neg logit contributions | |
margins | -1.117 |
rig | -1.037 |
hetical | -0.945 |
agy | -0.944 |
spiders | -0.898 |
Token | Space |
Token ID | 4687 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
henko | +0.207 |
ramid | +0.180 |
� | +0.172 |
LV | +0.167 |
��� | +0.163 |
Neg logit contributions | |
margins | -0.221 |
rig | -0.208 |
agy | -0.191 |
hetical | -0.191 |
spiders | -0.182 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
henko | +0.028 |
ramid | +0.025 |
� | +0.024 |
LV | +0.023 |
��� | +0.023 |
Neg logit contributions | |
margins | -0.022 |
rig | -0.020 |
agy | -0.018 |
hetical | -0.018 |
spiders | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
henko | +0.558 |
ramid | +0.499 |
� | +0.476 |
LV | +0.458 |
��� | +0.457 |
Neg logit contributions | |
margins | -0.496 |
rig | -0.465 |
agy | -0.421 |
hetical | -0.416 |
spiders | -0.398 |
Token | The |
Token ID | 383 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
henko | +0.314 |
ramid | +0.280 |
� | +0.266 |
��� | +0.256 |
LV | +0.255 |
Neg logit contributions | |
margins | -0.296 |
rig | -0.279 |
agy | -0.252 |
hetical | -0.250 |
spiders | -0.240 |
Token | students |
Token ID | 2444 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
henko | +0.743 |
ramid | +0.670 |
� | +0.641 |
LV | +0.617 |
��� | +0.612 |
Neg logit contributions | |
margins | -0.580 |
rig | -0.549 |
agy | -0.496 |
hetical | -0.489 |
spiders | -0.460 |
Token | undertook |
Token ID | 45730 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
henko | +0.446 |
ramid | +0.400 |
� | +0.382 |
LV | +0.367 |
��� | +0.367 |
Neg logit contributions | |
margins | -0.384 |
rig | -0.360 |
agy | -0.325 |
hetical | -0.321 |
spiders | -0.307 |
Token | this |
Token ID | 428 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
henko | +0.453 |
ramid | +0.407 |
� | +0.390 |
LV | +0.375 |
��� | +0.375 |
Neg logit contributions | |
margins | -0.359 |
rig | -0.336 |
agy | -0.303 |
hetical | -0.299 |
spiders | -0.284 |
Token | project |
Token ID | 1628 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
henko | +0.031 |
ramid | +0.028 |
� | +0.027 |
LV | +0.026 |
��� | +0.026 |
Neg logit contributions | |
margins | -0.022 |
rig | -0.020 |
agy | -0.018 |
hetical | -0.018 |
spiders | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
henko | +1.268 |
ramid | +1.119 |
� | +1.073 |
LV | +1.026 |
��� | +1.018 |
Neg logit contributions | |
margins | -1.230 |
rig | -1.159 |
agy | -1.054 |
hetical | -1.043 |
spiders | -0.997 |
Token | R |
Token ID | 371 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
henko | +0.081 |
ramid | +0.072 |
� | +0.069 |
LV | +0.067 |
��� | +0.066 |
Neg logit contributions | |
margins | -0.069 |
rig | -0.064 |
agy | -0.058 |
hetical | -0.057 |
spiders | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
henko | +0.754 |
ramid | +0.673 |
� | +0.642 |
LV | +0.617 |
��� | +0.603 |
Neg logit contributions | |
margins | -0.721 |
rig | -0.676 |
agy | -0.615 |
hetical | -0.609 |
spiders | -0.584 |
Token | 30 |
Token ID | 1542 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
henko | +0.908 |
ramid | +0.792 |
� | +0.750 |
LV | +0.716 |
��� | +0.703 |
Neg logit contributions | |
margins | -1.128 |
rig | -1.068 |
agy | -0.985 |
hetical | -0.977 |
spiders | -0.939 |
Token | , |
Token ID | 11 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
henko | +0.842 |
ramid | +0.750 |
� | +0.716 |
LV | +0.688 |
��� | +0.686 |
Neg logit contributions | |
margins | -0.774 |
rig | -0.727 |
agy | -0.660 |
hetical | -0.653 |
spiders | -0.624 |
Token | 1976 |
Token ID | 15408 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
henko | +0.717 |
ramid | +0.638 |
� | +0.608 |
LV | +0.584 |
��� | +0.581 |
Neg logit contributions | |
margins | -0.662 |
rig | -0.623 |
agy | -0.566 |
hetical | -0.560 |
spiders | -0.534 |
Token | . |
Token ID | 13 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
henko | +1.147 |
ramid | +1.022 |
� | +0.976 |
LV | +0.937 |
��� | +0.934 |
Neg logit contributions | |
margins | -1.058 |
rig | -0.994 |
agy | -0.901 |
hetical | -0.892 |
spiders | -0.853 |
Token | She |
Token ID | 1375 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
henko | +0.140 |
ramid | +0.125 |
� | +0.118 |
��� | +0.114 |
LV | +0.113 |
Neg logit contributions | |
margins | -0.139 |
rig | -0.131 |
agy | -0.119 |
hetical | -0.118 |
spiders | -0.113 |
Token | was |
Token ID | 373 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
henko | +0.712 |
ramid | +0.646 |
� | +0.620 |
��� | +0.600 |
LV | +0.599 |
Neg logit contributions | |
margins | -0.471 |
rig | -0.436 |
agy | -0.387 |
hetical | -0.382 |
spiders | -0.362 |
Token | unconscious |
Token ID | 14917 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
henko | +0.322 |
ramid | +0.289 |
� | +0.276 |
��� | +0.266 |
LV | +0.266 |
Neg logit contributions | |
margins | -0.272 |
rig | -0.255 |
agy | -0.230 |
hetical | -0.227 |
spiders | -0.217 |
Token | when |
Token ID | 618 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
henko | +0.407 |
ramid | +0.363 |
� | +0.348 |
LV | +0.334 |
��� | +0.333 |
Neg logit contributions | |
margins | -0.353 |
rig | -0.331 |
agy | -0.299 |
hetical | -0.296 |
spiders | -0.282 |
Token | police |
Token ID | 1644 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
henko | +1.352 |
ramid | +1.205 |
� | +1.159 |
LV | +1.117 |
��� | +1.116 |
Neg logit contributions | |
margins | -1.068 |
rig | -0.993 |
agy | -0.896 |
hetical | -0.889 |
spiders | -0.836 |
Token | found |
Token ID | 1043 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
henko | +0.767 |
ramid | +0.687 |
� | +0.658 |
LV | +0.638 |
��� | +0.630 |
Neg logit contributions | |
margins | -0.588 |
rig | -0.546 |
agy | -0.494 |
hetical | -0.488 |
spiders | -0.459 |
Token | A |
Token ID | 32 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
margins | +1.200 |
rig | +1.138 |
agy | +1.045 |
hetical | +1.024 |
spiders | +0.979 |
Neg logit contributions | |
henko | -1.135 |
ramid | -1.015 |
��� | -0.977 |
� | -0.937 |
LV | -0.887 |
Token | - |
Token ID | 12 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
margins | +1.012 |
rig | +0.962 |
agy | +0.878 |
hetical | +0.869 |
spiders | +0.836 |
Neg logit contributions | |
henko | -0.922 |
ramid | -0.813 |
� | -0.767 |
��� | -0.745 |
LV | -0.732 |
Token | Sports |
Token ID | 18153 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
henko | +0.232 |
ramid | +0.202 |
� | +0.190 |
��� | +0.183 |
LV | +0.180 |
Neg logit contributions | |
margins | -0.300 |
rig | -0.287 |
agy | -0.263 |
hetical | -0.261 |
spiders | -0.252 |
Token | - |
Token ID | 12 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
henko | +1.351 |
ramid | +1.195 |
� | +1.135 |
LV | +1.089 |
��� | +1.086 |
Neg logit contributions | |
margins | -1.405 |
rig | -1.321 |
agy | -1.209 |
hetical | -1.195 |
spiders | -1.149 |
Token | Lou |
Token ID | 24016 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
henko | +0.994 |
ramid | +0.868 |
� | +0.819 |
LV | +0.780 |
��� | +0.778 |
Neg logit contributions | |
margins | -1.262 |
rig | -1.195 |
agy | -1.100 |
hetical | -1.091 |
spiders | -1.052 |
Token | CK |
Token ID | 45233 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
henko | +0.973 |
ramid | +0.818 |
� | +0.763 |
LV | +0.725 |
��� | +0.719 |
Neg logit contributions | |
margins | -1.643 |
rig | -1.563 |
agy | -1.460 |
hetical | -1.447 |
spiders | -1.398 |
Token | - |
Token ID | 12 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
henko | +2.734 |
ramid | +2.420 |
� | +2.296 |
LV | +2.219 |
��� | +2.195 |
Neg logit contributions | |
margins | -2.788 |
rig | -2.605 |
agy | -2.404 |
hetical | -2.366 |
spiders | -2.267 |
Token | 08 |
Token ID | 2919 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
henko | +1.101 |
ramid | +0.962 |
� | +0.909 |
LV | +0.867 |
��� | +0.861 |
Neg logit contributions | |
margins | -1.392 |
rig | -1.316 |
agy | -1.213 |
hetical | -1.203 |
spiders | -1.160 |
Token | Election |
Token ID | 14219 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
margins | +0.020 |
rig | +0.019 |
agy | +0.017 |
hetical | +0.017 |
spiders | +0.016 |
Neg logit contributions | |
henko | -0.018 |
ramid | -0.016 |
� | -0.015 |
��� | -0.015 |
LV | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
margins | +0.654 |
rig | +0.620 |
agy | +0.560 |
hetical | +0.558 |
spiders | +0.537 |
Neg logit contributions | |
henko | -0.614 |
ramid | -0.543 |
� | -0.517 |
��� | -0.494 |
LV | -0.492 |
Token | W |
Token ID | 54 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
henko | +0.516 |
ramid | +0.450 |
� | +0.423 |
��� | +0.407 |
LV | +0.401 |
Neg logit contributions | |
margins | -0.652 |
rig | -0.620 |
agy | -0.569 |
hetical | -0.564 |
spiders | -0.544 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
henko | +0.648 |
ramid | +0.583 |
� | +0.553 |
LV | +0.530 |
��� | +0.527 |
Neg logit contributions | |
margins | -0.568 |
rig | -0.539 |
agy | -0.492 |
hetical | -0.478 |
spiders | -0.460 |
Token | . |
Token ID | 13 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
henko | +1.431 |
ramid | +1.278 |
� | +1.220 |
LV | +1.172 |
��� | +1.151 |
Neg logit contributions | |
margins | -1.323 |
rig | -1.245 |
agy | -1.138 |
hetical | -1.121 |
spiders | -1.074 |
Token | The |
Token ID | 383 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
henko | +0.220 |
ramid | +0.196 |
� | +0.187 |
��� | +0.180 |
LV | +0.179 |
Neg logit contributions | |
margins | -0.209 |
rig | -0.197 |
agy | -0.178 |
hetical | -0.177 |
spiders | -0.169 |
Token | American |
Token ID | 1605 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
henko | +0.745 |
ramid | +0.670 |
� | +0.637 |
LV | +0.612 |
��� | +0.611 |
Neg logit contributions | |
margins | -0.635 |
rig | -0.598 |
agy | -0.543 |
hetical | -0.536 |
spiders | -0.508 |
Token | people |
Token ID | 661 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
henko | +1.295 |
ramid | +1.144 |
� | +1.083 |
LV | +1.028 |
��� | +1.021 |
Neg logit contributions | |
margins | -1.458 |
rig | -1.378 |
agy | -1.271 |
hetical | -1.253 |
spiders | -1.199 |
Token | bailed |
Token ID | 47739 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
henko | +0.986 |
ramid | +0.882 |
� | +0.843 |
LV | +0.810 |
��� | +0.805 |
Neg logit contributions | |
margins | -0.835 |
rig | -0.785 |
agy | -0.709 |
hetical | -0.699 |
spiders | -0.667 |
Token | these |
Token ID | 777 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
henko | +2.796 |
ramid | +2.461 |
� | +2.339 |
LV | +2.227 |
��� | +2.189 |
Neg logit contributions | |
margins | -2.982 |
rig | -2.828 |
agy | -2.632 |
hetical | -2.591 |
spiders | -2.459 |
Token | sociop |
Token ID | 41221 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
margins | +0.231 |
rig | +0.216 |
agy | +0.194 |
hetical | +0.192 |
spiders | +0.184 |
Neg logit contributions | |
henko | -0.277 |
ramid | -0.249 |
� | -0.238 |
��� | -0.229 |
LV | -0.229 |
Token | aths |
Token ID | 33148 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
margins | +0.242 |
rig | +0.228 |
agy | +0.208 |
hetical | +0.206 |
spiders | +0.198 |
Neg logit contributions | |
henko | -0.237 |
ramid | -0.210 |
� | -0.200 |
��� | -0.192 |
LV | -0.191 |
Token | out |
Token ID | 503 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
henko | +0.034 |
ramid | +0.030 |
� | +0.028 |
��� | +0.027 |
LV | +0.027 |
Neg logit contributions | |
margins | -0.033 |
rig | -0.031 |
agy | -0.028 |
hetical | -0.028 |
spiders | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
henko | +0.102 |
ramid | +0.091 |
� | +0.087 |
��� | +0.084 |
LV | +0.083 |
Neg logit contributions | |
margins | -0.090 |
rig | -0.084 |
agy | -0.076 |
hetical | -0.075 |
spiders | -0.072 |
Token | vor |
Token ID | 20867 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
margins | +1.027 |
rig | +0.984 |
agy | +0.904 |
hetical | +0.899 |
spiders | +0.865 |
Neg logit contributions | |
henko | -0.734 |
ramid | -0.634 |
� | -0.599 |
��� | -0.571 |
LV | -0.563 |
Token | ak |
Token ID | 461 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
margins | +0.842 |
rig | +0.808 |
agy | +0.751 |
hetical | +0.739 |
spiders | +0.713 |
Neg logit contributions | |
henko | -0.584 |
ramid | -0.510 |
� | -0.480 |
��� | -0.468 |
LV | -0.454 |
Token | and |
Token ID | 290 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
margins | +0.240 |
rig | +0.225 |
agy | +0.202 |
hetical | +0.200 |
spiders | +0.191 |
Neg logit contributions | |
henko | -0.296 |
ramid | -0.267 |
� | -0.255 |
��� | -0.245 |
LV | -0.245 |
Token | Brah |
Token ID | 36415 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
margins | +0.071 |
rig | +0.066 |
agy | +0.060 |
hetical | +0.059 |
spiders | +0.056 |
Neg logit contributions | |
henko | -0.083 |
ramid | -0.074 |
� | -0.071 |
LV | -0.068 |
��� | -0.068 |
Token | ms |
Token ID | 907 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
margins | +0.719 |
rig | +0.685 |
agy | +0.634 |
hetical | +0.628 |
spiders | +0.608 |
Neg logit contributions | |
henko | -0.477 |
ramid | -0.410 |
� | -0.385 |
��� | -0.366 |
LV | -0.363 |
Token | met |
Token ID | 1138 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
margins | +0.529 |
rig | +0.493 |
agy | +0.440 |
hetical | +0.435 |
spiders | +0.415 |
Neg logit contributions | |
henko | -0.710 |
ramid | -0.644 |
� | -0.615 |
��� | -0.597 |
LV | -0.593 |
Token | in |
Token ID | 287 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
henko | +2.642 |
ramid | +2.286 |
� | +2.239 |
LV | +2.146 |
��� | +2.079 |
Neg logit contributions | |
margins | -2.449 |
rig | -2.312 |
hetical | -2.096 |
agy | -2.093 |
ipes | -1.964 |
Token | 1880 |
Token ID | 34865 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
henko | +0.402 |
ramid | +0.360 |
� | +0.343 |
LV | +0.331 |
��� | +0.329 |
Neg logit contributions | |
margins | -0.342 |
rig | -0.322 |
agy | -0.291 |
hetical | -0.288 |
spiders | -0.273 |
Token | , |
Token ID | 11 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
margins | +0.719 |
rig | +0.673 |
agy | +0.606 |
hetical | +0.599 |
spiders | +0.575 |
Neg logit contributions | |
henko | -0.841 |
ramid | -0.758 |
� | -0.720 |
��� | -0.698 |
LV | -0.693 |
Token | only |
Token ID | 691 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
margins | +0.555 |
rig | +0.522 |
agy | +0.471 |
hetical | +0.467 |
spiders | +0.446 |
Neg logit contributions | |
henko | -0.629 |
ramid | -0.559 |
� | -0.535 |
LV | -0.514 |
��� | -0.513 |
Token | three |
Token ID | 1115 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
margins | +0.390 |
rig | +0.367 |
agy | +0.332 |
hetical | +0.330 |
spiders | +0.313 |
Neg logit contributions | |
henko | -0.435 |
ramid | -0.386 |
� | -0.371 |
LV | -0.356 |
��� | -0.355 |
Token | a |
Token ID | 257 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
margins | +0.055 |
rig | +0.052 |
agy | +0.047 |
hetical | +0.046 |
spiders | +0.044 |
Neg logit contributions | |
henko | -0.067 |
ramid | -0.060 |
� | -0.058 |
LV | -0.055 |
��� | -0.055 |
Token | spread |
Token ID | 4104 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
margins | +0.144 |
rig | +0.135 |
agy | +0.121 |
hetical | +0.120 |
spiders | +0.114 |
Neg logit contributions | |
henko | -0.177 |
ramid | -0.159 |
� | -0.152 |
��� | -0.147 |
LV | -0.146 |
Token | of |
Token ID | 286 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
margins | +2.284 |
rig | +2.149 |
agy | +1.917 |
hetical | +1.892 |
spiders | +1.799 |
Neg logit contributions | |
henko | -2.937 |
ramid | -2.663 |
� | -2.529 |
��� | -2.477 |
LV | -2.446 |
Token | addiction |
Token ID | 13230 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
henko | +0.685 |
ramid | +0.613 |
� | +0.586 |
LV | +0.564 |
��� | +0.562 |
Neg logit contributions | |
margins | -0.571 |
rig | -0.538 |
agy | -0.488 |
hetical | -0.480 |
spiders | -0.454 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
henko | +1.907 |
ramid | +1.685 |
� | +1.618 |
LV | +1.554 |
��� | +1.522 |
Neg logit contributions | |
margins | -1.705 |
rig | -1.614 |
agy | -1.471 |
hetical | -1.452 |
spiders | -1.374 |
Token | overdose |
Token ID | 27357 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
henko | +0.316 |
ramid | +0.283 |
� | +0.270 |
LV | +0.260 |
��� | +0.258 |
Neg logit contributions | |
margins | -0.271 |
rig | -0.255 |
agy | -0.232 |
hetical | -0.228 |
spiders | -0.217 |
Token | , |
Token ID | 11 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
henko | +2.539 |
ramid | +2.198 |
� | +2.086 |
LV | +1.999 |
��� | +1.922 |
Neg logit contributions | |
margins | -2.982 |
rig | -2.865 |
agy | -2.642 |
hetical | -2.619 |
spiders | -2.488 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
margins | +0.082 |
rig | +0.077 |
agy | +0.069 |
hetical | +0.068 |
spiders | +0.066 |
Neg logit contributions | |
henko | -0.095 |
ramid | -0.085 |
� | -0.081 |
��� | -0.078 |
LV | -0.078 |
Token | to |
Token ID | 284 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
henko | +1.669 |
ramid | +1.478 |
� | +1.415 |
LV | +1.358 |
��� | +1.348 |
Neg logit contributions | |
margins | -1.578 |
rig | -1.491 |
agy | -1.358 |
hetical | -1.345 |
spiders | -1.275 |
Token | pills |
Token ID | 19521 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
henko | +0.649 |
ramid | +0.583 |
� | +0.558 |
LV | +0.538 |
��� | +0.536 |
Neg logit contributions | |
margins | -0.517 |
rig | -0.486 |
agy | -0.437 |
hetical | -0.432 |
spiders | -0.409 |
Token | we |
Token ID | 356 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
henko | +1.342 |
ramid | +1.199 |
� | +1.144 |
��� | +1.098 |
LV | +1.098 |
Neg logit contributions | |
margins | -1.210 |
rig | -1.136 |
agy | -1.028 |
hetical | -1.018 |
spiders | -0.974 |
Token | defeated |
Token ID | 9772 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
henko | +1.029 |
ramid | +0.902 |
� | +0.858 |
LV | +0.821 |
��� | +0.814 |
Neg logit contributions | |
margins | -1.158 |
rig | -1.093 |
agy | -1.004 |
hetical | -0.994 |
spiders | -0.950 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
henko | +0.962 |
ramid | +0.847 |
� | +0.813 |
LV | +0.781 |
��� | +0.767 |
Neg logit contributions | |
margins | -0.912 |
rig | -0.861 |
agy | -0.782 |
hetical | -0.776 |
spiders | -0.735 |
Token | ' |
Token ID | 705 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
henko | +0.304 |
ramid | +0.270 |
� | +0.258 |
LV | +0.248 |
��� | +0.246 |
Neg logit contributions | |
margins | -0.282 |
rig | -0.265 |
agy | -0.241 |
hetical | -0.238 |
spiders | -0.227 |
Token |
|
Token ID | 198 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
margins | +0.867 |
rig | +0.812 |
agy | +0.732 |
hetical | +0.724 |
spiders | +0.693 |
Neg logit contributions | |
henko | -1.013 |
ramid | -0.909 |
� | -0.867 |
��� | -0.836 |
LV | -0.833 |
Token |
|
Token ID | 198 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
henko | +0.069 |
ramid | +0.062 |
� | +0.059 |
LV | +0.057 |
��� | +0.056 |
Neg logit contributions | |
margins | -0.060 |
rig | -0.056 |
agy | -0.050 |
hetical | -0.050 |
spiders | -0.048 |
Token | Res |
Token ID | 4965 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
henko | +0.109 |
ramid | +0.095 |
� | +0.090 |
��� | +0.086 |
LV | +0.085 |
Neg logit contributions | |
margins | -0.141 |
rig | -0.134 |
agy | -0.123 |
hetical | -0.122 |
spiders | -0.118 |
Token | a |
Token ID | 64 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
henko | +2.084 |
ramid | +1.840 |
� | +1.748 |
LV | +1.681 |
enza | +1.631 |
Neg logit contributions | |
margins | -1.862 |
rig | -1.720 |
agy | -1.563 |
hetical | -1.555 |
spiders | -1.504 |
Token | ech |
Token ID | 3055 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
margins | +0.768 |
rig | +0.733 |
agy | +0.681 |
hetical | +0.675 |
spiders | +0.650 |
Neg logit contributions | |
henko | -0.502 |
ramid | -0.433 |
� | -0.409 |
��� | -0.396 |
LV | -0.384 |
Token | turns |
Token ID | 4962 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
margins | +0.251 |
rig | +0.235 |
agy | +0.212 |
hetical | +0.210 |
spiders | +0.200 |
Neg logit contributions | |
henko | -0.294 |
ramid | -0.264 |
� | -0.252 |
��� | -0.242 |
LV | -0.242 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
margins | +1.965 |
rig | +1.837 |
agy | +1.651 |
hetical | +1.630 |
spiders | +1.567 |
Neg logit contributions | |
henko | -2.383 |
ramid | -2.148 |
� | -2.047 |
��� | -1.981 |
LV | -1.972 |
Token | and |
Token ID | 290 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
margins | +0.566 |
rig | +0.529 |
agy | +0.475 |
hetical | +0.470 |
spiders | +0.449 |
Neg logit contributions | |
henko | -0.694 |
ramid | -0.624 |
� | -0.596 |
��� | -0.574 |
LV | -0.574 |