Token | house |
Token ID | 2156 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
CCC | +0.525 |
HEAD | +0.523 |
HQ | +0.500 |
CDC | +0.499 |
INTON | +0.480 |
Neg logit contributions | |
mos | -0.529 |
rout | -0.502 |
onomy | -0.501 |
� | -0.493 |
wise | -0.482 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
CCC | +1.503 |
HEAD | +1.492 |
HQ | +1.426 |
CDC | +1.390 |
INTON | +1.333 |
Neg logit contributions | |
mos | -2.070 |
onomy | -2.009 |
rout | -1.991 |
� | -1.980 |
wise | -1.918 |
Token | The |
Token ID | 383 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
CCC | +0.493 |
HEAD | +0.491 |
HQ | +0.474 |
CDC | +0.466 |
INTON | +0.453 |
Neg logit contributions | |
mos | -0.361 |
onomy | -0.347 |
rout | -0.342 |
� | -0.341 |
wise | -0.325 |
Token | property |
Token ID | 3119 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
HEAD | +0.354 |
CCC | +0.354 |
HQ | +0.340 |
CDC | +0.338 |
INTON | +0.324 |
Neg logit contributions | |
mos | -0.331 |
rout | -0.318 |
onomy | -0.314 |
� | -0.309 |
wise | -0.304 |
Token | now |
Token ID | 783 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
CCC | +2.098 |
HEAD | +2.086 |
HQ | +2.005 |
CDC | +1.970 |
INTON | +1.905 |
Neg logit contributions | |
mos | -2.034 |
onomy | -1.958 |
rout | -1.948 |
� | -1.928 |
wise | -1.864 |
Token | belongs |
Token ID | 14448 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
CCC | +1.717 |
HEAD | +1.710 |
HQ | +1.656 |
CDC | +1.633 |
INTON | +1.596 |
Neg logit contributions | |
mos | -1.039 |
rout | -0.985 |
onomy | -0.980 |
� | -0.965 |
wise | -0.923 |
Token | to |
Token ID | 284 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
CCC | +4.367 |
HEAD | +4.332 |
HQ | +4.203 |
CDC | +4.100 |
INTON | +3.964 |
Neg logit contributions | |
mos | -3.606 |
onomy | -3.484 |
rout | -3.425 |
� | -3.404 |
wise | -3.262 |
Token | Cit |
Token ID | 15792 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
HEAD | +0.634 |
CCC | +0.633 |
HQ | +0.609 |
CDC | +0.597 |
INTON | +0.580 |
Neg logit contributions | |
mos | -0.594 |
onomy | -0.569 |
rout | -0.565 |
� | -0.563 |
wise | -0.546 |
Token | ib |
Token ID | 571 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
CCC | +0.328 |
HEAD | +0.328 |
HQ | +0.303 |
CDC | +0.296 |
INTON | +0.283 |
Neg logit contributions | |
mos | -0.684 |
onomy | -0.680 |
rout | -0.662 |
� | -0.653 |
wise | -0.643 |
Token | ank |
Token ID | 962 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
CCC | +0.814 |
HEAD | +0.803 |
HQ | +0.766 |
CDC | +0.756 |
INTON | +0.726 |
Neg logit contributions | |
mos | -0.877 |
onomy | -0.872 |
rout | -0.844 |
� | -0.839 |
wise | -0.815 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
CCC | +0.248 |
HEAD | +0.247 |
HQ | +0.234 |
CDC | +0.232 |
INTON | +0.225 |
Neg logit contributions | |
mos | -0.321 |
onomy | -0.310 |
� | -0.309 |
rout | -0.307 |
wise | -0.297 |
Token | it |
Token ID | 340 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
CCC | +0.038 |
HEAD | +0.037 |
HQ | +0.036 |
CDC | +0.035 |
INTON | +0.035 |
Neg logit contributions | |
mos | -0.032 |
onomy | -0.031 |
rout | -0.031 |
� | -0.030 |
wise | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
CCC | +0.042 |
HEAD | +0.041 |
HQ | +0.040 |
CDC | +0.039 |
INTON | +0.038 |
Neg logit contributions | |
mos | -0.041 |
onomy | -0.039 |
rout | -0.039 |
� | -0.039 |
wise | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
mos | +0.069 |
onomy | +0.067 |
rout | +0.065 |
� | +0.065 |
wise | +0.063 |
Neg logit contributions | |
CCC | -0.092 |
HEAD | -0.092 |
HQ | -0.089 |
CDC | -0.087 |
INTON | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
mos | +0.153 |
onomy | +0.146 |
rout | +0.144 |
� | +0.139 |
wise | +0.136 |
Neg logit contributions | |
CCC | -0.275 |
HEAD | -0.273 |
HQ | -0.264 |
CDC | -0.263 |
INTON | -0.259 |
Token | Never |
Token ID | 12295 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
mos | +0.037 |
onomy | +0.037 |
� | +0.036 |
rout | +0.036 |
wise | +0.034 |
Neg logit contributions | |
CCC | -0.028 |
HEAD | -0.028 |
HQ | -0.027 |
CDC | -0.026 |
INTON | -0.025 |
Token | mind |
Token ID | 2000 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
CCC | +0.105 |
HEAD | +0.104 |
HQ | +0.100 |
CDC | +0.099 |
INTON | +0.095 |
Neg logit contributions | |
mos | -0.081 |
onomy | -0.078 |
rout | -0.077 |
� | -0.076 |
wise | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | +5.79e-03 |
Pos logit contributions | |
CCC | +3.613 |
HEAD | +3.592 |
HQ | +3.454 |
CDC | +3.387 |
INTON | +3.248 |
Neg logit contributions | |
mos | -3.635 |
onomy | -3.524 |
rout | -3.468 |
� | -3.463 |
wise | -3.303 |
Token | fact |
Token ID | 1109 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
CCC | +0.009 |
HEAD | +0.009 |
HQ | +0.009 |
CDC | +0.009 |
INTON | +0.008 |
Neg logit contributions | |
mos | -0.011 |
onomy | -0.011 |
rout | -0.011 |
� | -0.010 |
wise | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
CCC | +0.772 |
HEAD | +0.769 |
HQ | +0.739 |
CDC | +0.723 |
INTON | +0.696 |
Neg logit contributions | |
mos | -0.780 |
onomy | -0.754 |
rout | -0.746 |
� | -0.740 |
wise | -0.712 |
Token | Team |
Token ID | 4816 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
mos | +0.344 |
onomy | +0.329 |
rout | +0.328 |
� | +0.325 |
wise | +0.315 |
Neg logit contributions | |
CCC | -0.404 |
HEAD | -0.402 |
HQ | -0.387 |
CDC | -0.381 |
INTON | -0.371 |
Token | Canada |
Token ID | 3340 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
mos | +1.112 |
onomy | +1.075 |
rout | +1.065 |
� | +1.055 |
wise | +1.014 |
Neg logit contributions | |
CCC | -1.100 |
HEAD | -1.091 |
HQ | -1.056 |
CDC | -1.029 |
INTON | -0.995 |
Token | The |
Token ID | 464 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
CCC | +0.045 |
HEAD | +0.045 |
HQ | +0.043 |
CDC | +0.042 |
INTON | +0.041 |
Neg logit contributions | |
mos | -0.054 |
onomy | -0.053 |
� | -0.052 |
rout | -0.052 |
wise | -0.049 |
Token | family |
Token ID | 1641 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
CCC | +0.555 |
HEAD | +0.553 |
HQ | +0.530 |
CDC | +0.522 |
INTON | +0.506 |
Neg logit contributions | |
mos | -0.513 |
rout | -0.493 |
onomy | -0.491 |
� | -0.482 |
wise | -0.473 |
Token | said |
Token ID | 531 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
CCC | +0.769 |
HEAD | +0.764 |
HQ | +0.737 |
CDC | +0.730 |
INTON | +0.709 |
Neg logit contributions | |
mos | -0.725 |
rout | -0.695 |
onomy | -0.694 |
� | -0.680 |
wise | -0.666 |
Token | that |
Token ID | 326 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
CCC | +0.678 |
HEAD | +0.672 |
HQ | +0.647 |
CDC | +0.636 |
INTON | +0.615 |
Neg logit contributions | |
mos | -0.612 |
onomy | -0.587 |
rout | -0.583 |
� | -0.578 |
wise | -0.558 |
Token | when |
Token ID | 618 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
mos | +0.069 |
onomy | +0.066 |
rout | +0.066 |
� | +0.065 |
wise | +0.063 |
Neg logit contributions | |
CCC | -0.079 |
HEAD | -0.078 |
HQ | -0.075 |
CDC | -0.074 |
INTON | -0.072 |
Token | Warm |
Token ID | 25692 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
CCC | +1.521 |
HEAD | +1.510 |
HQ | +1.453 |
CDC | +1.427 |
INTON | +1.380 |
Neg logit contributions | |
mos | -1.376 |
onomy | -1.324 |
rout | -1.311 |
� | -1.305 |
wise | -1.255 |
Token | b |
Token ID | 65 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
CCC | +3.423 |
HEAD | +3.402 |
HQ | +3.267 |
CDC | +3.193 |
INTON | +3.076 |
Neg logit contributions | |
mos | -3.833 |
onomy | -3.711 |
rout | -3.674 |
� | -3.652 |
wise | -3.523 |
Token | ier |
Token ID | 959 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
mos | +0.077 |
onomy | +0.075 |
rout | +0.074 |
� | +0.073 |
wise | +0.071 |
Neg logit contributions | |
CCC | -0.069 |
HEAD | -0.068 |
HQ | -0.065 |
CDC | -0.064 |
INTON | -0.062 |
Token | returned |
Token ID | 4504 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
CCC | +1.238 |
HEAD | +1.219 |
HQ | +1.183 |
CDC | +1.159 |
INTON | +1.129 |
Neg logit contributions | |
mos | -1.215 |
rout | -1.159 |
onomy | -1.153 |
� | -1.136 |
wise | -1.116 |
Token | home |
Token ID | 1363 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
mos | +0.241 |
onomy | +0.229 |
rout | +0.229 |
� | +0.225 |
wise | +0.220 |
Neg logit contributions | |
CCC | -0.297 |
HEAD | -0.294 |
HQ | -0.283 |
CDC | -0.280 |
INTON | -0.272 |
Token | last |
Token ID | 938 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
CCC | +0.212 |
HEAD | +0.211 |
HQ | +0.203 |
CDC | +0.200 |
INTON | +0.194 |
Neg logit contributions | |
mos | -0.197 |
onomy | -0.188 |
rout | -0.187 |
� | -0.186 |
wise | -0.180 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
mos | +1.208 |
onomy | +1.177 |
rout | +1.164 |
� | +1.144 |
wise | +1.107 |
Neg logit contributions | |
CCC | -1.096 |
HEAD | -1.082 |
HQ | -1.025 |
CDC | -1.024 |
INTON | -1.006 |
Token | : |
Token ID | 25 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
mos | +0.325 |
onomy | +0.314 |
rout | +0.311 |
wise | +0.303 |
� | +0.303 |
Neg logit contributions | |
CCC | -0.300 |
HEAD | -0.297 |
CDC | -0.282 |
HQ | -0.282 |
INTON | -0.278 |
Token | 47 |
Token ID | 2857 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
CCC | +0.190 |
HEAD | +0.189 |
HQ | +0.179 |
CDC | +0.175 |
INTON | +0.166 |
Neg logit contributions | |
mos | -0.304 |
onomy | -0.295 |
rout | -0.293 |
� | -0.291 |
wise | -0.283 |
Token | ] |
Token ID | 60 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
mos | +0.301 |
onomy | +0.288 |
rout | +0.288 |
� | +0.279 |
wise | +0.275 |
Neg logit contributions | |
CCC | -0.343 |
HEAD | -0.340 |
HQ | -0.326 |
CDC | -0.325 |
INTON | -0.321 |
Token | < |
Token ID | 1279 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
HEAD | +0.374 |
CCC | +0.374 |
HQ | +0.359 |
CDC | +0.349 |
INTON | +0.338 |
Neg logit contributions | |
mos | -0.400 |
onomy | -0.390 |
rout | -0.385 |
� | -0.383 |
wise | -0.368 |
Token | abal |
Token ID | 44349 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
mos | +0.935 |
onomy | +0.910 |
� | +0.889 |
rout | +0.886 |
wise | +0.849 |
Neg logit contributions | |
CCC | -0.947 |
HEAD | -0.943 |
HQ | -0.900 |
CDC | -0.888 |
INTON | -0.872 |
Token | icious |
Token ID | 6243 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
CCC | +3.723 |
HEAD | +3.693 |
HQ | +3.582 |
CDC | +3.490 |
INTON | +3.368 |
Neg logit contributions | |
mos | -3.371 |
onomy | -3.232 |
rout | -3.217 |
� | -3.202 |
wise | -3.066 |
Token | s |
Token ID | 82 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
CCC | +1.130 |
HEAD | +1.123 |
HQ | +1.081 |
CDC | +1.060 |
INTON | +1.026 |
Neg logit contributions | |
mos | -1.081 |
onomy | -1.045 |
rout | -1.032 |
� | -1.026 |
wise | -0.987 |
Token | > |
Token ID | 29 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
CCC | +0.950 |
HEAD | +0.944 |
HQ | +0.910 |
CDC | +0.892 |
INTON | +0.862 |
Neg logit contributions | |
mos | -0.897 |
onomy | -0.867 |
rout | -0.856 |
� | -0.850 |
wise | -0.818 |
Token | lol |
Token ID | 19462 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
mos | +0.176 |
rout | +0.166 |
onomy | +0.166 |
� | +0.163 |
wise | +0.159 |
Neg logit contributions | |
CCC | -0.212 |
HEAD | -0.209 |
HQ | -0.203 |
CDC | -0.200 |
INTON | -0.194 |
Token | m |
Token ID | 285 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
mos | +0.612 |
onomy | +0.585 |
rout | +0.581 |
� | +0.574 |
wise | +0.554 |
Neg logit contributions | |
CCC | -0.762 |
HEAD | -0.758 |
HQ | -0.733 |
CDC | -0.720 |
INTON | -0.699 |
Token | lineup |
Token ID | 12750 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
mos | +0.461 |
rout | +0.445 |
onomy | +0.440 |
� | +0.431 |
wise | +0.422 |
Neg logit contributions | |
CCC | -0.628 |
HEAD | -0.626 |
HQ | -0.603 |
CDC | -0.599 |
INTON | -0.586 |
Token | . |
Token ID | 13 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
mos | +0.298 |
rout | +0.288 |
onomy | +0.286 |
� | +0.283 |
wise | +0.279 |
Neg logit contributions | |
CCC | -0.237 |
HEAD | -0.234 |
HQ | -0.223 |
CDC | -0.221 |
INTON | -0.215 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
CCC | +0.078 |
HEAD | +0.077 |
HQ | +0.074 |
CDC | +0.073 |
INTON | +0.071 |
Neg logit contributions | |
mos | -0.076 |
onomy | -0.073 |
rout | -0.072 |
� | -0.072 |
wise | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
mos | +0.242 |
onomy | +0.231 |
rout | +0.228 |
� | +0.220 |
wise | +0.215 |
Neg logit contributions | |
CCC | -0.436 |
HEAD | -0.432 |
HQ | -0.418 |
CDC | -0.416 |
INTON | -0.410 |
Token | Never |
Token ID | 12295 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
mos | +0.235 |
onomy | +0.233 |
� | +0.228 |
rout | +0.225 |
wise | +0.217 |
Neg logit contributions | |
CCC | -0.178 |
HEAD | -0.176 |
HQ | -0.168 |
CDC | -0.164 |
INTON | -0.161 |
Token | mind |
Token ID | 2000 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
CCC | +0.061 |
HEAD | +0.060 |
HQ | +0.058 |
CDC | +0.058 |
INTON | +0.055 |
Neg logit contributions | |
mos | -0.048 |
onomy | -0.046 |
rout | -0.046 |
� | -0.045 |
wise | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
CCC | +3.384 |
HEAD | +3.364 |
HQ | +3.233 |
CDC | +3.170 |
INTON | +3.043 |
Neg logit contributions | |
mos | -3.395 |
onomy | -3.293 |
rout | -3.239 |
� | -3.238 |
wise | -3.088 |
Token | fact |
Token ID | 1109 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
mos | +0.227 |
onomy | +0.218 |
rout | +0.218 |
� | +0.215 |
wise | +0.210 |
Neg logit contributions | |
HEAD | -0.214 |
CCC | -0.214 |
HQ | -0.206 |
CDC | -0.201 |
INTON | -0.195 |
Token | that |
Token ID | 326 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
CCC | +0.441 |
HEAD | +0.439 |
HQ | +0.422 |
CDC | +0.414 |
INTON | +0.400 |
Neg logit contributions | |
mos | -0.430 |
onomy | -0.415 |
rout | -0.411 |
� | -0.408 |
wise | -0.393 |
Token | he |
Token ID | 339 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
mos | +0.592 |
onomy | +0.565 |
rout | +0.564 |
� | +0.556 |
wise | +0.542 |
Neg logit contributions | |
CCC | -0.706 |
HEAD | -0.701 |
HQ | -0.675 |
CDC | -0.666 |
INTON | -0.649 |
Token | � |
Token ID | 447 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
mos | +0.122 |
onomy | +0.117 |
rout | +0.117 |
� | +0.116 |
wise | +0.111 |
Neg logit contributions | |
CCC | -0.136 |
HEAD | -0.135 |
HQ | -0.130 |
CDC | -0.128 |
INTON | -0.125 |
Token | _ |
Token ID | 62 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
mos | +0.600 |
onomy | +0.578 |
rout | +0.573 |
� | +0.570 |
wise | +0.553 |
Neg logit contributions | |
CCC | -0.591 |
HEAD | -0.582 |
HQ | -0.567 |
CDC | -0.559 |
INTON | -0.536 |
Token | B |
Token ID | 33 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
CCC | +0.174 |
HEAD | +0.171 |
HQ | +0.164 |
CDC | +0.161 |
INTON | +0.155 |
Neg logit contributions | |
mos | -0.264 |
onomy | -0.257 |
� | -0.254 |
rout | -0.253 |
wise | -0.245 |
Token | GR |
Token ID | 10761 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
CCC | +0.364 |
HEAD | +0.363 |
HQ | +0.348 |
CDC | +0.340 |
INTON | +0.324 |
Neg logit contributions | |
mos | -0.504 |
� | -0.491 |
onomy | -0.489 |
rout | -0.480 |
wise | -0.466 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
CCC | +0.025 |
HEAD | +0.025 |
HQ | +0.024 |
CDC | +0.024 |
INTON | +0.023 |
Neg logit contributions | |
mos | -0.029 |
onomy | -0.028 |
� | -0.028 |
rout | -0.028 |
wise | -0.027 |
Token | G |
Token ID | 38 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
mos | +0.155 |
onomy | +0.150 |
rout | +0.149 |
� | +0.148 |
wise | +0.144 |
Neg logit contributions | |
CCC | -0.126 |
HEAD | -0.124 |
HQ | -0.119 |
CDC | -0.117 |
INTON | -0.113 |
Token | RAY |
Token ID | 30631 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
HEAD | +0.032 |
CCC | +0.032 |
HQ | +0.029 |
CDC | +0.028 |
INTON | +0.026 |
Neg logit contributions | |
mos | -0.114 |
onomy | -0.111 |
� | -0.111 |
rout | -0.110 |
wise | -0.108 |
Token | ) |
Token ID | 8 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
HEAD | +3.033 |
CCC | +3.004 |
HQ | +2.855 |
CDC | +2.771 |
INTON | +2.667 |
Neg logit contributions | |
mos | -3.806 |
onomy | -3.726 |
rout | -3.655 |
� | -3.638 |
wise | -3.508 |
Token | # |
Token ID | 1303 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
CCC | +0.889 |
HEAD | +0.883 |
HQ | +0.850 |
CDC | +0.834 |
INTON | +0.807 |
Neg logit contributions | |
mos | -0.876 |
onomy | -0.842 |
rout | -0.837 |
� | -0.827 |
wise | -0.801 |
Token | smooth |
Token ID | 7209 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
CCC | +1.807 |
HEAD | +1.797 |
HQ | +1.737 |
CDC | +1.705 |
INTON | +1.653 |
Neg logit contributions | |
mos | -1.410 |
onomy | -1.356 |
rout | -1.339 |
� | -1.329 |
wise | -1.273 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
CCC | +0.504 |
HEAD | +0.501 |
HQ | +0.483 |
CDC | +0.476 |
INTON | +0.460 |
Neg logit contributions | |
mos | -0.431 |
onomy | -0.413 |
rout | -0.412 |
� | -0.407 |
wise | -0.393 |
Token | image |
Token ID | 2939 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
CCC | +0.331 |
HEAD | +0.329 |
HQ | +0.317 |
CDC | +0.313 |
INTON | +0.304 |
Neg logit contributions | |
mos | -0.301 |
rout | -0.288 |
onomy | -0.286 |
� | -0.281 |
wise | -0.274 |
Token | 1973 |
Token ID | 15674 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
mos | +0.511 |
rout | +0.486 |
onomy | +0.482 |
� | +0.475 |
wise | +0.466 |
Neg logit contributions | |
CCC | -0.622 |
HEAD | -0.621 |
HQ | -0.595 |
CDC | -0.589 |
INTON | -0.580 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
mos | +0.355 |
onomy | +0.341 |
rout | +0.339 |
� | +0.338 |
wise | +0.328 |
Neg logit contributions | |
CCC | -0.284 |
HEAD | -0.281 |
HQ | -0.270 |
CDC | -0.263 |
INTON | -0.257 |
Token | He |
Token ID | 679 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
CCC | +0.291 |
HEAD | +0.288 |
HQ | +0.278 |
CDC | +0.273 |
INTON | +0.264 |
Neg logit contributions | |
mos | -0.263 |
onomy | -0.253 |
rout | -0.250 |
� | -0.249 |
wise | -0.239 |
Token | has |
Token ID | 468 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
CCC | +0.323 |
HEAD | +0.320 |
HQ | +0.310 |
CDC | +0.304 |
INTON | +0.296 |
Neg logit contributions | |
mos | -0.298 |
onomy | -0.286 |
rout | -0.284 |
� | -0.282 |
wise | -0.271 |
Token | never |
Token ID | 1239 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
CCC | +0.527 |
HEAD | +0.523 |
HQ | +0.505 |
CDC | +0.496 |
INTON | +0.485 |
Neg logit contributions | |
mos | -0.446 |
onomy | -0.422 |
rout | -0.421 |
� | -0.419 |
wise | -0.405 |
Token | belonged |
Token ID | 19611 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
CCC | +0.821 |
HEAD | +0.813 |
HQ | +0.786 |
CDC | +0.775 |
INTON | +0.753 |
Neg logit contributions | |
mos | -0.677 |
rout | -0.640 |
onomy | -0.636 |
� | -0.632 |
wise | -0.613 |
Token | to |
Token ID | 284 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
CCC | +3.519 |
HEAD | +3.509 |
HQ | +3.381 |
CDC | +3.299 |
INTON | +3.184 |
Neg logit contributions | |
mos | -3.201 |
onomy | -3.136 |
rout | -3.080 |
� | -3.033 |
wise | -2.899 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
CCC | +0.484 |
HEAD | +0.480 |
HQ | +0.464 |
CDC | +0.456 |
INTON | +0.444 |
Neg logit contributions | |
mos | -0.403 |
rout | -0.380 |
onomy | -0.379 |
� | -0.377 |
wise | -0.364 |
Token | Miami |
Token ID | 8437 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
CCC | +0.287 |
HEAD | +0.287 |
HQ | +0.276 |
CDC | +0.271 |
INTON | +0.264 |
Neg logit contributions | |
mos | -0.258 |
onomy | -0.245 |
rout | -0.243 |
� | -0.240 |
wise | -0.234 |
Token | that |
Token ID | 326 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
CCC | +0.557 |
HEAD | +0.555 |
HQ | +0.534 |
CDC | +0.524 |
INTON | +0.511 |
Neg logit contributions | |
mos | -0.503 |
onomy | -0.481 |
rout | -0.476 |
� | -0.473 |
wise | -0.458 |
Token | rich |
Token ID | 5527 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
CCC | +0.457 |
HEAD | +0.454 |
HQ | +0.440 |
CDC | +0.430 |
INTON | +0.419 |
Neg logit contributions | |
mos | -0.381 |
onomy | -0.365 |
rout | -0.363 |
� | -0.360 |
wise | -0.345 |
Token | filming |
Token ID | 17691 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
CCC | +1.064 |
HEAD | +1.057 |
HQ | +1.012 |
CDC | +1.010 |
INTON | +0.987 |
Neg logit contributions | |
mos | -0.749 |
onomy | -0.708 |
rout | -0.700 |
� | -0.698 |
wise | -0.675 |
Token | took |
Token ID | 1718 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
mos | +0.515 |
rout | +0.482 |
wise | +0.467 |
onomy | +0.467 |
� | +0.461 |
Neg logit contributions | |
CCC | -0.770 |
HEAD | -0.766 |
CDC | -0.740 |
HQ | -0.736 |
INTON | -0.729 |
Token | place |
Token ID | 1295 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
CCC | +0.783 |
HEAD | +0.777 |
HQ | +0.754 |
CDC | +0.747 |
INTON | +0.734 |
Neg logit contributions | |
mos | -0.406 |
rout | -0.380 |
onomy | -0.373 |
wise | -0.358 |
� | -0.358 |
Token | near |
Token ID | 1474 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
CCC | +0.632 |
HEAD | +0.628 |
HQ | +0.605 |
CDC | +0.599 |
INTON | +0.584 |
Neg logit contributions | |
mos | -0.458 |
onomy | -0.435 |
rout | -0.433 |
� | -0.422 |
wise | -0.412 |
Token | Alfred |
Token ID | 22044 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
CCC | +0.360 |
HEAD | +0.355 |
HQ | +0.341 |
CDC | +0.336 |
INTON | +0.327 |
Neg logit contributions | |
mos | -0.326 |
onomy | -0.318 |
rout | -0.314 |
� | -0.313 |
wise | -0.301 |
Token | Lerner |
Token ID | 49750 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
HEAD | +0.293 |
CCC | +0.290 |
HQ | +0.273 |
CDC | +0.269 |
INTON | +0.263 |
Neg logit contributions | |
mos | -0.579 |
onomy | -0.571 |
� | -0.567 |
rout | -0.558 |
wise | -0.541 |
Token | Hall |
Token ID | 4789 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
CCC | +3.936 |
HEAD | +3.912 |
HQ | +3.783 |
CDC | +3.728 |
INTON | +3.621 |
Neg logit contributions | |
mos | -2.730 |
onomy | -2.620 |
rout | -2.592 |
� | -2.569 |
wise | -2.456 |
Token | . |
Token ID | 13 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
CCC | +0.239 |
HEAD | +0.239 |
HQ | +0.225 |
CDC | +0.224 |
INTON | +0.217 |
Neg logit contributions | |
mos | -0.320 |
onomy | -0.311 |
rout | -0.308 |
� | -0.304 |
wise | -0.299 |
Token | Other |
Token ID | 3819 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
CCC | +0.609 |
HEAD | +0.604 |
HQ | +0.578 |
CDC | +0.563 |
INTON | +0.545 |
Neg logit contributions | |
mos | -0.718 |
onomy | -0.694 |
� | -0.690 |
rout | -0.689 |
wise | -0.661 |
Token | filming |
Token ID | 17691 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
CCC | +0.556 |
HEAD | +0.552 |
CDC | +0.530 |
HQ | +0.527 |
INTON | +0.519 |
Neg logit contributions | |
mos | -0.357 |
rout | -0.328 |
onomy | -0.328 |
� | -0.322 |
wise | -0.320 |
Token | locations |
Token ID | 7064 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
mos | +0.315 |
rout | +0.297 |
wise | +0.285 |
onomy | +0.284 |
� | +0.280 |
Neg logit contributions | |
CCC | -0.397 |
HEAD | -0.389 |
HQ | -0.372 |
CDC | -0.371 |
INTON | -0.369 |
Token | Business |
Token ID | 24749 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
CCC | +0.108 |
HEAD | +0.107 |
HQ | +0.102 |
CDC | +0.099 |
INTON | +0.098 |
Neg logit contributions | |
mos | -0.147 |
onomy | -0.146 |
rout | -0.143 |
� | -0.142 |
wise | -0.136 |
Token | owners |
Token ID | 4393 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
mos | +0.872 |
onomy | +0.845 |
rout | +0.839 |
� | +0.828 |
wise | +0.804 |
Neg logit contributions | |
HEAD | -1.084 |
CCC | -1.083 |
HQ | -1.037 |
CDC | -1.031 |
INTON | -0.997 |
Token | will |
Token ID | 481 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
CCC | +1.130 |
HEAD | +1.126 |
HQ | +1.082 |
CDC | +1.067 |
INTON | +1.035 |
Neg logit contributions | |
mos | -0.924 |
onomy | -0.888 |
rout | -0.881 |
� | -0.865 |
wise | -0.842 |
Token | have |
Token ID | 423 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
CCC | +0.880 |
HEAD | +0.875 |
HQ | +0.848 |
CDC | +0.831 |
INTON | +0.808 |
Neg logit contributions | |
mos | -0.676 |
onomy | -0.646 |
rout | -0.644 |
� | -0.630 |
wise | -0.614 |
Token | to |
Token ID | 284 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
CCC | +0.449 |
HEAD | +0.446 |
HQ | +0.431 |
CDC | +0.423 |
INTON | +0.410 |
Neg logit contributions | |
mos | -0.361 |
onomy | -0.348 |
rout | -0.344 |
� | -0.341 |
wise | -0.328 |
Token | shoulder |
Token ID | 8163 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
CCC | +0.659 |
HEAD | +0.656 |
HQ | +0.635 |
CDC | +0.624 |
INTON | +0.606 |
Neg logit contributions | |
mos | -0.489 |
rout | -0.466 |
onomy | -0.466 |
� | -0.454 |
wise | -0.445 |
Token | part |
Token ID | 636 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
CCC | +3.368 |
HEAD | +3.336 |
HQ | +3.225 |
CDC | +3.137 |
INTON | +3.033 |
Neg logit contributions | |
mos | -3.267 |
onomy | -3.179 |
� | -3.117 |
rout | -3.114 |
wise | -2.963 |
Token | of |
Token ID | 286 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
CCC | +1.174 |
HEAD | +1.169 |
HQ | +1.134 |
CDC | +1.106 |
INTON | +1.067 |
Neg logit contributions | |
mos | -0.997 |
onomy | -0.955 |
rout | -0.944 |
� | -0.935 |
wise | -0.892 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
CCC | +0.472 |
HEAD | +0.472 |
HQ | +0.452 |
CDC | +0.446 |
INTON | +0.431 |
Neg logit contributions | |
mos | -0.430 |
rout | -0.412 |
onomy | -0.412 |
� | -0.404 |
wise | -0.395 |
Token | burden |
Token ID | 10538 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
HEAD | +0.222 |
CCC | +0.220 |
HQ | +0.210 |
CDC | +0.207 |
INTON | +0.201 |
Neg logit contributions | |
mos | -0.241 |
rout | -0.234 |
onomy | -0.232 |
� | -0.226 |
wise | -0.225 |
Token | as |
Token ID | 355 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
CCC | +0.918 |
HEAD | +0.915 |
HQ | +0.881 |
CDC | +0.868 |
INTON | +0.850 |
Neg logit contributions | |
mos | -0.736 |
rout | -0.705 |
onomy | -0.704 |
� | -0.685 |
wise | -0.675 |
Token | a |
Token ID | 257 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
mos | +0.459 |
onomy | +0.435 |
� | +0.431 |
rout | +0.430 |
wise | +0.419 |
Neg logit contributions | |
CCC | -0.562 |
HEAD | -0.558 |
HQ | -0.538 |
CDC | -0.532 |
INTON | -0.522 |
Token | new |
Token ID | 649 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
CCC | +0.170 |
HEAD | +0.168 |
HQ | +0.163 |
CDC | +0.161 |
INTON | +0.156 |
Neg logit contributions | |
mos | -0.139 |
onomy | -0.133 |
rout | -0.132 |
� | -0.130 |
wise | -0.127 |
Token | approach |
Token ID | 3164 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
CCC | +0.231 |
HEAD | +0.229 |
HQ | +0.222 |
CDC | +0.219 |
INTON | +0.212 |
Neg logit contributions | |
mos | -0.186 |
onomy | -0.179 |
rout | -0.177 |
� | -0.175 |
wise | -0.170 |
Token | toward |
Token ID | 3812 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
CCC | +0.410 |
HEAD | +0.406 |
HQ | +0.392 |
CDC | +0.385 |
INTON | +0.373 |
Neg logit contributions | |
mos | -0.388 |
onomy | -0.375 |
rout | -0.369 |
� | -0.368 |
wise | -0.357 |
Token | the |
Token ID | 262 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
CCC | +0.607 |
HEAD | +0.603 |
HQ | +0.582 |
CDC | +0.574 |
INTON | +0.555 |
Neg logit contributions | |
mos | -0.531 |
onomy | -0.509 |
rout | -0.504 |
� | -0.501 |
wise | -0.484 |
Token | Dark |
Token ID | 3801 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
CCC | +0.378 |
HEAD | +0.375 |
HQ | +0.363 |
CDC | +0.358 |
INTON | +0.347 |
Neg logit contributions | |
mos | -0.291 |
onomy | -0.278 |
rout | -0.275 |
� | -0.272 |
wise | -0.264 |
Token | Knight |
Token ID | 6700 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
CCC | +3.487 |
HEAD | +3.480 |
HQ | +3.374 |
CDC | +3.266 |
INTON | +3.175 |
Neg logit contributions | |
mos | -3.057 |
onomy | -2.951 |
rout | -2.910 |
� | -2.839 |
wise | -2.748 |
Token | : |
Token ID | 25 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
mos | +0.666 |
onomy | +0.638 |
� | +0.636 |
rout | +0.632 |
wise | +0.616 |
Neg logit contributions | |
CCC | -0.680 |
HEAD | -0.664 |
HQ | -0.641 |
CDC | -0.640 |
INTON | -0.616 |
Token | an |
Token ID | 281 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
CCC | +1.282 |
HEAD | +1.277 |
HQ | +1.232 |
CDC | +1.203 |
INTON | +1.168 |
Neg logit contributions | |
mos | -1.097 |
onomy | -1.062 |
rout | -1.049 |
� | -1.038 |
wise | -0.993 |
Token | original |
Token ID | 2656 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
CCC | +0.363 |
HEAD | +0.362 |
HQ | +0.347 |
CDC | +0.343 |
INTON | +0.331 |
Neg logit contributions | |
mos | -0.310 |
onomy | -0.299 |
rout | -0.295 |
� | -0.293 |
wise | -0.283 |
Token | story |
Token ID | 1621 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
CCC | +1.349 |
HEAD | +1.343 |
HQ | +1.297 |
CDC | +1.268 |
INTON | +1.227 |
Neg logit contributions | |
mos | -1.149 |
onomy | -1.108 |
rout | -1.095 |
� | -1.088 |
wise | -1.040 |
Token | aper |
Token ID | 2136 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
CCC | +0.896 |
HEAD | +0.892 |
HQ | +0.855 |
CDC | +0.841 |
INTON | +0.812 |
Neg logit contributions | |
mos | -0.890 |
onomy | -0.856 |
rout | -0.850 |
� | -0.843 |
wise | -0.814 |
Token | if |
Token ID | 611 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
CCC | +0.838 |
HEAD | +0.833 |
HQ | +0.799 |
CDC | +0.795 |
INTON | +0.771 |
Neg logit contributions | |
mos | -0.694 |
onomy | -0.661 |
rout | -0.660 |
� | -0.648 |
wise | -0.638 |
Token | you |
Token ID | 345 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
mos | +0.612 |
rout | +0.577 |
onomy | +0.575 |
� | +0.570 |
wise | +0.555 |
Neg logit contributions | |
CCC | -0.944 |
HEAD | -0.936 |
HQ | -0.903 |
CDC | -0.901 |
INTON | -0.871 |
Token | don |
Token ID | 836 |
Feature activation | -4.28e-03 |
Pos logit contributions | |
mos | +0.207 |
rout | +0.196 |
onomy | +0.193 |
� | +0.190 |
wise | +0.188 |
Neg logit contributions | |
CCC | -0.274 |
HEAD | -0.273 |
HQ | -0.263 |
CDC | -0.260 |
INTON | -0.257 |
Token | 't |
Token ID | 470 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
mos | +0.010 |
onomy | +0.010 |
rout | +0.010 |
� | +0.010 |
wise | +0.009 |
Neg logit contributions | |
HEAD | -0.005 |
CCC | -0.005 |
HQ | -0.004 |
CDC | -0.004 |
INTON | -0.004 |
Token | mind |
Token ID | 2000 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
CCC | +0.404 |
HEAD | +0.403 |
HQ | +0.389 |
CDC | +0.385 |
INTON | +0.378 |
Neg logit contributions | |
mos | -0.279 |
rout | -0.265 |
onomy | -0.259 |
� | -0.254 |
wise | -0.252 |
Token | getting |
Token ID | 1972 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
CCC | +3.455 |
HEAD | +3.433 |
HQ | +3.318 |
CDC | +3.243 |
INTON | +3.132 |
Neg logit contributions | |
mos | -3.083 |
onomy | -2.994 |
rout | -2.944 |
� | -2.932 |
wise | -2.802 |
Token | it |
Token ID | 340 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
mos | +0.093 |
rout | +0.089 |
onomy | +0.088 |
� | +0.087 |
wise | +0.086 |
Neg logit contributions | |
CCC | -0.108 |
HEAD | -0.107 |
HQ | -0.103 |
CDC | -0.102 |
INTON | -0.099 |
Token | on |
Token ID | 319 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
CCC | +0.715 |
HEAD | +0.708 |
HQ | +0.679 |
CDC | +0.674 |
INTON | +0.655 |
Neg logit contributions | |
mos | -0.693 |
rout | -0.662 |
onomy | -0.658 |
� | -0.650 |
wise | -0.635 |
Token | DVD |
Token ID | 12490 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
CCC | +0.319 |
HEAD | +0.318 |
HQ | +0.304 |
CDC | +0.302 |
INTON | +0.293 |
Neg logit contributions | |
mos | -0.346 |
rout | -0.333 |
onomy | -0.328 |
� | -0.327 |
wise | -0.320 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
CCC | +1.897 |
HEAD | +1.876 |
HQ | +1.797 |
CDC | +1.766 |
INTON | +1.704 |
Neg logit contributions | |
mos | -2.271 |
onomy | -2.195 |
rout | -2.182 |
� | -2.161 |
wise | -2.104 |
Token | are |
Token ID | 389 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
CCC | +0.761 |
HEAD | +0.751 |
HQ | +0.726 |
CDC | +0.715 |
INTON | +0.693 |
Neg logit contributions | |
mos | -0.683 |
rout | -0.657 |
onomy | -0.655 |
� | -0.644 |
wise | -0.625 |
Token | nine |
Token ID | 5193 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
CCC | +0.759 |
HEAD | +0.748 |
HQ | +0.726 |
CDC | +0.716 |
INTON | +0.700 |
Neg logit contributions | |
mos | -0.681 |
rout | -0.656 |
onomy | -0.646 |
� | -0.639 |
wise | -0.633 |
Token | in |
Token ID | 287 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
CCC | +0.424 |
HEAD | +0.420 |
HQ | +0.406 |
CDC | +0.400 |
INTON | +0.388 |
Neg logit contributions | |
mos | -0.363 |
onomy | -0.348 |
rout | -0.347 |
� | -0.343 |
wise | -0.334 |
Token | number |
Token ID | 1271 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
CCC | +0.115 |
HEAD | +0.115 |
HQ | +0.111 |
CDC | +0.109 |
INTON | +0.105 |
Neg logit contributions | |
mos | -0.098 |
onomy | -0.094 |
rout | -0.093 |
� | -0.092 |
wise | -0.088 |
Token | : |
Token ID | 25 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
mos | +0.449 |
onomy | +0.433 |
rout | +0.432 |
� | +0.427 |
wise | +0.420 |
Neg logit contributions | |
CCC | -0.371 |
HEAD | -0.366 |
HQ | -0.352 |
CDC | -0.346 |
INTON | -0.336 |
Token | Fro |
Token ID | 9734 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
CCC | +1.128 |
HEAD | +1.117 |
HQ | +1.082 |
CDC | +1.061 |
INTON | +1.028 |
Neg logit contributions | |
mos | -1.050 |
onomy | -1.008 |
rout | -1.003 |
� | -0.993 |
wise | -0.965 |
Token | do |
Token ID | 4598 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
CCC | +3.722 |
HEAD | +3.699 |
HQ | +3.580 |
CDC | +3.513 |
INTON | +3.408 |
Neg logit contributions | |
mos | -2.829 |
onomy | -2.721 |
rout | -2.684 |
� | -2.665 |
wise | -2.551 |
Token | , |
Token ID | 11 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
CCC | +1.444 |
HEAD | +1.426 |
HQ | +1.373 |
CDC | +1.344 |
INTON | +1.294 |
Neg logit contributions | |
mos | -1.826 |
onomy | -1.765 |
rout | -1.755 |
� | -1.744 |
wise | -1.694 |
Token | Sam |
Token ID | 3409 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
mos | +0.098 |
onomy | +0.093 |
rout | +0.093 |
� | +0.093 |
wise | +0.090 |
Neg logit contributions | |
CCC | -0.107 |
HEAD | -0.106 |
HQ | -0.103 |
CDC | -0.102 |
INTON | -0.098 |
Token | , |
Token ID | 11 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
CCC | +0.074 |
HEAD | +0.073 |
HQ | +0.070 |
CDC | +0.069 |
INTON | +0.066 |
Neg logit contributions | |
mos | -0.092 |
onomy | -0.089 |
rout | -0.088 |
� | -0.088 |
wise | -0.085 |
Token | Merry |
Token ID | 39001 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
mos | +0.088 |
onomy | +0.085 |
rout | +0.084 |
� | +0.083 |
wise | +0.081 |
Neg logit contributions | |
CCC | -0.098 |
HEAD | -0.097 |
HQ | -0.094 |
CDC | -0.093 |
INTON | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
CCC | +0.012 |
HEAD | +0.012 |
HQ | +0.012 |
CDC | +0.011 |
INTON | +0.011 |
Neg logit contributions | |
mos | -0.011 |
rout | -0.011 |
onomy | -0.010 |
� | -0.010 |
wise | -0.010 |
Token | renowned |
Token ID | 22140 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
CCC | +0.156 |
HEAD | +0.155 |
HQ | +0.149 |
CDC | +0.147 |
INTON | +0.143 |
Neg logit contributions | |
mos | -0.144 |
rout | -0.139 |
onomy | -0.137 |
� | -0.134 |
wise | -0.133 |
Token | Bud |
Token ID | 10370 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
mos | +0.022 |
rout | +0.021 |
onomy | +0.021 |
� | +0.021 |
wise | +0.021 |
Neg logit contributions | |
CCC | -0.023 |
HEAD | -0.022 |
HQ | -0.022 |
CDC | -0.021 |
INTON | -0.021 |
Token | we |
Token ID | 732 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
mos | +1.458 |
onomy | +1.406 |
rout | +1.391 |
� | +1.380 |
wise | +1.344 |
Neg logit contributions | |
CCC | -1.279 |
HEAD | -1.247 |
HQ | -1.191 |
CDC | -1.186 |
INTON | -1.145 |
Token | iser |
Token ID | 5847 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
CCC | +0.855 |
HEAD | +0.842 |
HQ | +0.810 |
CDC | +0.801 |
INTON | +0.766 |
Neg logit contributions | |
mos | -0.921 |
onomy | -0.898 |
rout | -0.869 |
� | -0.866 |
wise | -0.841 |
Token | Cly |
Token ID | 29133 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
CCC | +0.114 |
HEAD | +0.111 |
HQ | +0.107 |
CDC | +0.105 |
INTON | +0.103 |
Neg logit contributions | |
mos | -0.158 |
onomy | -0.152 |
rout | -0.152 |
� | -0.150 |
wise | -0.147 |
Token | des |
Token ID | 8906 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
CCC | +2.938 |
HEAD | +2.920 |
HQ | +2.799 |
CDC | +2.725 |
INTON | +2.621 |
Neg logit contributions | |
mos | -3.573 |
onomy | -3.464 |
rout | -3.433 |
� | -3.421 |
wise | -3.297 |
Token | d |
Token ID | 67 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
CCC | +0.581 |
HEAD | +0.571 |
HQ | +0.553 |
CDC | +0.540 |
INTON | +0.524 |
Neg logit contributions | |
mos | -0.553 |
onomy | -0.533 |
rout | -0.529 |
� | -0.524 |
wise | -0.507 |
Token | ales |
Token ID | 2040 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
CCC | +0.267 |
HEAD | +0.266 |
HQ | +0.256 |
CDC | +0.253 |
INTON | +0.246 |
Neg logit contributions | |
mos | -0.223 |
onomy | -0.216 |
� | -0.211 |
rout | -0.211 |
wise | -0.201 |
Token | paid |
Token ID | 3432 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
CCC | +1.097 |
HEAD | +1.082 |
HQ | +1.046 |
CDC | +1.035 |
INTON | +1.007 |
Neg logit contributions | |
mos | -0.986 |
rout | -0.945 |
onomy | -0.942 |
� | -0.929 |
wise | -0.897 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
mos | +0.872 |
rout | +0.825 |
onomy | +0.822 |
� | +0.803 |
wise | +0.794 |
Neg logit contributions | |
CCC | -1.059 |
HEAD | -1.050 |
HQ | -1.014 |
CDC | -1.008 |
INTON | -0.975 |
Token | he |
Token ID | 339 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
CCC | +0.234 |
HEAD | +0.231 |
HQ | +0.223 |
CDC | +0.219 |
INTON | +0.212 |
Neg logit contributions | |
mos | -0.213 |
onomy | -0.206 |
rout | -0.202 |
� | -0.200 |
wise | -0.194 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
CCC | +0.593 |
HEAD | +0.587 |
HQ | +0.564 |
CDC | +0.554 |
INTON | +0.539 |
Neg logit contributions | |
mos | -0.594 |
onomy | -0.566 |
rout | -0.562 |
� | -0.552 |
wise | -0.542 |
Token | to |
Token ID | 284 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
mos | +0.095 |
onomy | +0.091 |
rout | +0.090 |
� | +0.089 |
wise | +0.086 |
Neg logit contributions | |
CCC | -0.116 |
HEAD | -0.115 |
HQ | -0.110 |
CDC | -0.109 |
INTON | -0.105 |
Token | adapt |
Token ID | 6068 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
CCC | +0.025 |
HEAD | +0.025 |
HQ | +0.024 |
CDC | +0.024 |
INTON | +0.023 |
Neg logit contributions | |
mos | -0.018 |
rout | -0.017 |
onomy | -0.017 |
� | -0.017 |
wise | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
CCC | +0.951 |
HEAD | +0.943 |
HQ | +0.909 |
CDC | +0.891 |
INTON | +0.865 |
Neg logit contributions | |
mos | -0.891 |
onomy | -0.860 |
rout | -0.849 |
� | -0.847 |
wise | -0.813 |
Token | lur |
Token ID | 20605 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
mos | +0.063 |
onomy | +0.060 |
rout | +0.060 |
� | +0.059 |
wise | +0.057 |
Neg logit contributions | |
CCC | -0.067 |
HEAD | -0.067 |
HQ | -0.064 |
CDC | -0.063 |
INTON | -0.061 |
Token | id |
Token ID | 312 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
CCC | +3.426 |
HEAD | +3.416 |
HQ | +3.307 |
CDC | +3.243 |
INTON | +3.109 |
Neg logit contributions | |
mos | -3.035 |
onomy | -2.916 |
rout | -2.896 |
� | -2.874 |
wise | -2.743 |
Token | Robert |
Token ID | 5199 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
CCC | +0.248 |
HEAD | +0.246 |
HQ | +0.236 |
CDC | +0.233 |
INTON | +0.226 |
Neg logit contributions | |
mos | -0.228 |
onomy | -0.221 |
rout | -0.218 |
� | -0.217 |
wise | -0.209 |
Token | Bl |
Token ID | 1086 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
mos | +0.281 |
onomy | +0.272 |
rout | +0.268 |
� | +0.266 |
wise | +0.257 |
Neg logit contributions | |
CCC | -0.311 |
HEAD | -0.309 |
HQ | -0.298 |
CDC | -0.292 |
INTON | -0.284 |
Token | och |
Token ID | 5374 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
CCC | +0.095 |
HEAD | +0.095 |
HQ | +0.091 |
CDC | +0.089 |
INTON | +0.087 |
Neg logit contributions | |
mos | -0.077 |
onomy | -0.075 |
rout | -0.073 |
� | -0.072 |
wise | -0.070 |
Token | novel |
Token ID | 5337 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
CCC | +0.543 |
HEAD | +0.538 |
HQ | +0.519 |
CDC | +0.511 |
INTON | +0.494 |
Neg logit contributions | |
mos | -0.484 |
onomy | -0.468 |
rout | -0.463 |
� | -0.459 |
wise | -0.443 |
Token | in |
Token ID | 287 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
CCC | +0.090 |
HEAD | +0.089 |
HQ | +0.085 |
CDC | +0.084 |
INTON | +0.081 |
Neg logit contributions | |
mos | -0.108 |
rout | -0.103 |
onomy | -0.103 |
� | -0.101 |
wise | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
CCC | +0.182 |
HEAD | +0.182 |
HQ | +0.175 |
CDC | +0.172 |
INTON | +0.166 |
Neg logit contributions | |
mos | -0.163 |
rout | -0.155 |
onomy | -0.155 |
� | -0.152 |
wise | -0.148 |
Token | Geneva |
Token ID | 20552 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
mos | +0.108 |
rout | +0.102 |
onomy | +0.102 |
� | +0.099 |
wise | +0.098 |
Neg logit contributions | |
HEAD | -0.127 |
CCC | -0.127 |
HQ | -0.121 |
CDC | -0.120 |
INTON | -0.117 |
Token | graveyard |
Token ID | 27672 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
CCC | +0.022 |
HEAD | +0.022 |
HQ | +0.021 |
CDC | +0.021 |
INTON | +0.020 |
Neg logit contributions | |
mos | -0.023 |
onomy | -0.022 |
rout | -0.022 |
� | -0.022 |
wise | -0.021 |
Token | where |
Token ID | 810 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
CCC | +0.208 |
HEAD | +0.207 |
HQ | +0.200 |
CDC | +0.196 |
INTON | +0.190 |
Neg logit contributions | |
mos | -0.201 |
onomy | -0.193 |
rout | -0.192 |
� | -0.189 |
wise | -0.183 |
Token | Borg |
Token ID | 29004 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
CCC | +0.121 |
HEAD | +0.120 |
HQ | +0.116 |
CDC | +0.114 |
INTON | +0.112 |
Neg logit contributions | |
mos | -0.093 |
rout | -0.088 |
onomy | -0.088 |
� | -0.087 |
wise | -0.084 |
Token | es |
Token ID | 274 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
CCC | +3.585 |
HEAD | +3.569 |
HQ | +3.443 |
CDC | +3.385 |
INTON | +3.279 |
Neg logit contributions | |
mos | -2.917 |
onomy | -2.813 |
rout | -2.775 |
� | -2.751 |
wise | -2.642 |
Token | 's |
Token ID | 338 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
CCC | +0.978 |
HEAD | +0.971 |
HQ | +0.945 |
CDC | +0.923 |
INTON | +0.903 |
Neg logit contributions | |
mos | -0.919 |
rout | -0.874 |
onomy | -0.870 |
� | -0.858 |
wise | -0.836 |
Token | well |
Token ID | 880 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
CCC | +0.449 |
HEAD | +0.448 |
HQ | +0.432 |
CDC | +0.427 |
INTON | +0.415 |
Neg logit contributions | |
mos | -0.370 |
rout | -0.351 |
onomy | -0.349 |
� | -0.344 |
wise | -0.338 |
Token | - |
Token ID | 12 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
CCC | +0.460 |
HEAD | +0.456 |
HQ | +0.439 |
CDC | +0.430 |
INTON | +0.414 |
Neg logit contributions | |
mos | -0.511 |
onomy | -0.495 |
rout | -0.489 |
� | -0.486 |
wise | -0.471 |
Token | t |
Token ID | 83 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
HEAD | +0.079 |
CCC | +0.079 |
HQ | +0.075 |
CDC | +0.073 |
INTON | +0.072 |
Neg logit contributions | |
mos | -0.086 |
onomy | -0.083 |
rout | -0.082 |
� | -0.081 |
wise | -0.080 |
Token | photo |
Token ID | 4590 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
CCC | +0.722 |
HEAD | +0.720 |
HQ | +0.692 |
CDC | +0.683 |
INTON | +0.661 |
Neg logit contributions | |
mos | -0.663 |
rout | -0.632 |
onomy | -0.632 |
� | -0.619 |
wise | -0.608 |
Token | has |
Token ID | 468 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
CCC | +1.051 |
HEAD | +1.044 |
HQ | +1.008 |
CDC | +0.985 |
INTON | +0.956 |
Neg logit contributions | |
mos | -1.061 |
onomy | -1.018 |
rout | -1.013 |
� | -1.004 |
wise | -0.970 |
Token | provoked |
Token ID | 29579 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
CCC | +0.175 |
HEAD | +0.174 |
HQ | +0.168 |
CDC | +0.165 |
INTON | +0.163 |
Neg logit contributions | |
mos | -0.136 |
rout | -0.127 |
� | -0.127 |
onomy | -0.125 |
wise | -0.122 |
Token | outrage |
Token ID | 11616 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
mos | +0.345 |
rout | +0.329 |
onomy | +0.326 |
� | +0.321 |
wise | +0.314 |
Neg logit contributions | |
CCC | -0.439 |
HEAD | -0.438 |
HQ | -0.423 |
CDC | -0.416 |
INTON | -0.404 |
Token | in |
Token ID | 287 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
CCC | +0.576 |
HEAD | +0.569 |
HQ | +0.548 |
CDC | +0.539 |
INTON | +0.520 |
Neg logit contributions | |
mos | -0.603 |
onomy | -0.579 |
rout | -0.579 |
� | -0.569 |
wise | -0.556 |
Token | Borg |
Token ID | 29004 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
CCC | +0.417 |
HEAD | +0.415 |
HQ | +0.401 |
CDC | +0.395 |
INTON | +0.384 |
Neg logit contributions | |
mos | -0.337 |
rout | -0.318 |
onomy | -0.317 |
� | -0.315 |
wise | -0.305 |
Token | es |
Token ID | 274 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
CCC | +3.582 |
HEAD | +3.569 |
HQ | +3.440 |
CDC | +3.383 |
INTON | +3.278 |
Neg logit contributions | |
mos | -2.902 |
onomy | -2.805 |
rout | -2.762 |
� | -2.738 |
wise | -2.629 |
Token | 's |
Token ID | 338 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
CCC | +0.986 |
HEAD | +0.978 |
HQ | +0.933 |
CDC | +0.915 |
INTON | +0.878 |
Neg logit contributions | |
mos | -1.313 |
onomy | -1.272 |
rout | -1.259 |
� | -1.254 |
wise | -1.216 |
Token | native |
Token ID | 6868 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
CCC | +0.398 |
HEAD | +0.395 |
HQ | +0.381 |
CDC | +0.380 |
INTON | +0.367 |
Neg logit contributions | |
mos | -0.265 |
onomy | -0.250 |
rout | -0.249 |
� | -0.246 |
wise | -0.239 |
Token | Argentina |
Token ID | 16519 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
mos | +0.540 |
onomy | +0.509 |
rout | +0.507 |
� | +0.494 |
wise | +0.482 |
Neg logit contributions | |
CCC | -0.782 |
HEAD | -0.781 |
HQ | -0.751 |
CDC | -0.749 |
INTON | -0.724 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
mos | +0.372 |
onomy | +0.358 |
rout | +0.356 |
� | +0.354 |
wise | +0.345 |
Neg logit contributions | |
CCC | -0.312 |
HEAD | -0.309 |
HQ | -0.297 |
CDC | -0.290 |
INTON | -0.281 |
Token | Sutton |
Token ID | 39964 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
mos | +0.218 |
onomy | +0.211 |
rout | +0.210 |
� | +0.209 |
wise | +0.202 |
Neg logit contributions | |
CCC | -0.229 |
HEAD | -0.225 |
HQ | -0.217 |
CDC | -0.213 |
INTON | -0.206 |
Token | , |
Token ID | 11 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
mos | +0.912 |
onomy | +0.882 |
rout | +0.879 |
� | +0.870 |
wise | +0.845 |
Neg logit contributions | |
CCC | -0.761 |
HEAD | -0.749 |
HQ | -0.722 |
CDC | -0.710 |
INTON | -0.687 |
Token | probably |
Token ID | 2192 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
CCC | +0.109 |
HEAD | +0.109 |
HQ | +0.105 |
CDC | +0.103 |
INTON | +0.100 |
Neg logit contributions | |
mos | -0.102 |
onomy | -0.098 |
rout | -0.097 |
� | -0.097 |
wise | -0.093 |
Token | no |
Token ID | 645 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
mos | +0.207 |
onomy | +0.200 |
rout | +0.199 |
� | +0.198 |
wise | +0.193 |
Neg logit contributions | |
CCC | -0.194 |
HEAD | -0.192 |
HQ | -0.185 |
CDC | -0.183 |
INTON | -0.176 |
Token | Kenny |
Token ID | 22102 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
CCC | +0.050 |
HEAD | +0.050 |
HQ | +0.048 |
CDC | +0.047 |
INTON | +0.046 |
Neg logit contributions | |
mos | -0.042 |
rout | -0.040 |
onomy | -0.040 |
� | -0.039 |
wise | -0.038 |
Token | Dal |
Token ID | 12348 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
mos | +0.621 |
onomy | +0.600 |
rout | +0.594 |
� | +0.591 |
wise | +0.572 |
Neg logit contributions | |
CCC | -0.573 |
HEAD | -0.565 |
HQ | -0.542 |
CDC | -0.533 |
INTON | -0.514 |
Token | g |
Token ID | 70 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
HEAD | +3.154 |
CCC | +3.091 |
HQ | +2.956 |
CDC | +2.915 |
INTON | +2.811 |
Neg logit contributions | |
mos | -3.288 |
onomy | -3.194 |
rout | -3.178 |
� | -3.156 |
wise | -2.999 |
Token | lish |
Token ID | 1836 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
mos | +0.377 |
onomy | +0.371 |
� | +0.360 |
rout | +0.358 |
wise | +0.351 |
Neg logit contributions | |
CCC | -0.738 |
HEAD | -0.736 |
HQ | -0.721 |
CDC | -0.712 |
INTON | -0.675 |
Token | either |
Token ID | 2035 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
CCC | +1.552 |
HEAD | +1.540 |
HQ | +1.475 |
CDC | +1.441 |
INTON | +1.384 |
Neg logit contributions | |
mos | -1.990 |
onomy | -1.931 |
rout | -1.913 |
� | -1.902 |
wise | -1.841 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
CCC | +0.730 |
HEAD | +0.722 |
HQ | +0.691 |
CDC | +0.675 |
INTON | +0.646 |
Neg logit contributions | |
mos | -1.050 |
onomy | -1.019 |
rout | -1.011 |
� | -1.004 |
wise | -0.978 |
Token | because |
Token ID | 780 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
mos | +0.202 |
onomy | +0.193 |
rout | +0.193 |
� | +0.190 |
wise | +0.185 |
Neg logit contributions | |
CCC | -0.224 |
HEAD | -0.222 |
HQ | -0.214 |
CDC | -0.211 |
INTON | -0.204 |
Token | Jun |
Token ID | 7653 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
mos | +0.056 |
onomy | +0.054 |
rout | +0.054 |
� | +0.053 |
wise | +0.051 |
Neg logit contributions | |
CCC | -0.063 |
HEAD | -0.063 |
HQ | -0.061 |
CDC | -0.060 |
INTON | -0.058 |
Token | io |
Token ID | 952 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
CCC | +1.127 |
HEAD | +1.120 |
HQ | +1.082 |
CDC | +1.061 |
INTON | +1.027 |
Neg logit contributions | |
mos | -0.953 |
onomy | -0.918 |
rout | -0.907 |
� | -0.901 |
wise | -0.864 |
Token | Val |
Token ID | 3254 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
CCC | +0.712 |
HEAD | +0.709 |
HQ | +0.685 |
CDC | +0.672 |
INTON | +0.652 |
Neg logit contributions | |
mos | -0.625 |
onomy | -0.598 |
rout | -0.593 |
� | -0.587 |
wise | -0.566 |
Token | er |
Token ID | 263 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
CCC | +0.368 |
HEAD | +0.366 |
HQ | +0.352 |
CDC | +0.343 |
INTON | +0.333 |
Neg logit contributions | |
mos | -0.373 |
onomy | -0.361 |
rout | -0.356 |
� | -0.352 |
wise | -0.341 |
Token | io |
Token ID | 952 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
mos | +0.801 |
onomy | +0.780 |
rout | +0.767 |
� | +0.759 |
wise | +0.735 |
Neg logit contributions | |
CCC | -0.681 |
HEAD | -0.677 |
HQ | -0.651 |
CDC | -0.636 |
INTON | -0.611 |
Token | Borg |
Token ID | 29004 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
CCC | +0.590 |
HEAD | +0.588 |
HQ | +0.568 |
CDC | +0.557 |
INTON | +0.540 |
Neg logit contributions | |
mos | -0.541 |
rout | -0.516 |
onomy | -0.516 |
� | -0.509 |
wise | -0.491 |
Token | he |
Token ID | 258 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
CCC | +3.124 |
HEAD | +3.090 |
HQ | +2.980 |
CDC | +2.914 |
INTON | +2.808 |
Neg logit contributions | |
mos | -3.152 |
onomy | -3.037 |
rout | -3.018 |
� | -2.995 |
wise | -2.882 |
Token | se |
Token ID | 325 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
mos | +0.215 |
onomy | +0.207 |
rout | +0.204 |
� | +0.203 |
wise | +0.196 |
Neg logit contributions | |
CCC | -0.243 |
HEAD | -0.242 |
HQ | -0.233 |
CDC | -0.229 |
INTON | -0.223 |
Token | ( |
Token ID | 357 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
CCC | +0.246 |
HEAD | +0.244 |
HQ | +0.236 |
CDC | +0.232 |
INTON | +0.224 |
Neg logit contributions | |
mos | -0.230 |
onomy | -0.220 |
rout | -0.219 |
� | -0.217 |
wise | -0.210 |
Token | called |
Token ID | 7174 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
CCC | +0.394 |
HEAD | +0.394 |
HQ | +0.375 |
CDC | +0.368 |
INTON | +0.360 |
Neg logit contributions | |
mos | -0.506 |
onomy | -0.490 |
rout | -0.485 |
� | -0.483 |
wise | -0.464 |
Token | " |
Token ID | 366 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
mos | +0.379 |
onomy | +0.358 |
rout | +0.357 |
� | +0.354 |
wise | +0.342 |
Neg logit contributions | |
CCC | -0.398 |
HEAD | -0.397 |
HQ | -0.382 |
CDC | -0.378 |
INTON | -0.365 |
Token | of |
Token ID | 286 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
CCC | +0.487 |
HEAD | +0.486 |
HQ | +0.471 |
CDC | +0.460 |
INTON | +0.449 |
Neg logit contributions | |
mos | -0.425 |
onomy | -0.409 |
rout | -0.404 |
� | -0.404 |
wise | -0.385 |
Token | � |
Token ID | 564 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
mos | +0.169 |
onomy | +0.163 |
rout | +0.161 |
� | +0.160 |
wise | +0.154 |
Neg logit contributions | |
CCC | -0.180 |
HEAD | -0.180 |
HQ | -0.174 |
CDC | -0.171 |
INTON | -0.164 |
Token | � |
Token ID | 250 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
CCC | +0.184 |
HEAD | +0.184 |
HQ | +0.179 |
CDC | +0.176 |
INTON | +0.173 |
Neg logit contributions | |
mos | -0.062 |
� | -0.059 |
onomy | -0.059 |
rout | -0.057 |
wise | -0.052 |
Token | Operation |
Token ID | 32180 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
mos | +0.110 |
onomy | +0.107 |
� | +0.105 |
rout | +0.105 |
wise | +0.100 |
Neg logit contributions | |
CCC | -0.083 |
HEAD | -0.083 |
HQ | -0.079 |
CDC | -0.077 |
INTON | -0.075 |
Token | Human |
Token ID | 5524 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
mos | +1.146 |
onomy | +1.100 |
rout | +1.088 |
� | +1.077 |
wise | +1.041 |
Neg logit contributions | |
CCC | -1.156 |
HEAD | -1.156 |
HQ | -1.115 |
CDC | -1.094 |
INTON | -1.067 |
Token | Warm |
Token ID | 25692 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
CCC | +0.252 |
HEAD | +0.248 |
HQ | +0.239 |
CDC | +0.232 |
INTON | +0.226 |
Neg logit contributions | |
mos | -0.290 |
onomy | -0.284 |
rout | -0.278 |
� | -0.277 |
wise | -0.268 |
Token | th |
Token ID | 400 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
CCC | +2.856 |
HEAD | +2.828 |
HQ | +2.715 |
CDC | +2.650 |
INTON | +2.549 |
Neg logit contributions | |
mos | -3.421 |
onomy | -3.319 |
rout | -3.286 |
� | -3.269 |
wise | -3.154 |
Token | � |
Token ID | 447 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
mos | +0.142 |
onomy | +0.137 |
rout | +0.135 |
� | +0.135 |
wise | +0.129 |
Neg logit contributions | |
CCC | -0.140 |
HEAD | -0.140 |
HQ | -0.134 |
CDC | -0.131 |
INTON | -0.128 |
Token | � |
Token ID | 251 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
CCC | +0.599 |
HEAD | +0.596 |
HQ | +0.579 |
CDC | +0.570 |
INTON | +0.555 |
Neg logit contributions | |
mos | -0.296 |
onomy | -0.281 |
rout | -0.276 |
� | -0.271 |
wise | -0.258 |
Token | said |
Token ID | 531 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
CCC | +0.227 |
HEAD | +0.226 |
HQ | +0.218 |
CDC | +0.213 |
INTON | +0.207 |
Neg logit contributions | |
mos | -0.219 |
onomy | -0.211 |
rout | -0.209 |
� | -0.208 |
wise | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
mos | +0.041 |
onomy | +0.040 |
rout | +0.039 |
� | +0.039 |
wise | +0.038 |
Neg logit contributions | |
CCC | -0.031 |
HEAD | -0.031 |
HQ | -0.030 |
CDC | -0.029 |
INTON | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
CCC | +0.406 |
HEAD | +0.405 |
HQ | +0.390 |
CDC | +0.383 |
INTON | +0.373 |
Neg logit contributions | |
mos | -0.357 |
onomy | -0.344 |
rout | -0.343 |
� | -0.338 |
wise | -0.329 |
Token | private |
Token ID | 2839 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
CCC | +0.095 |
HEAD | +0.094 |
HQ | +0.090 |
CDC | +0.089 |
INTON | +0.087 |
Neg logit contributions | |
mos | -0.077 |
rout | -0.075 |
onomy | -0.074 |
� | -0.072 |
wise | -0.071 |
Token | conversation |
Token ID | 5273 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
mos | +0.320 |
onomy | +0.310 |
rout | +0.308 |
� | +0.301 |
wise | +0.294 |
Neg logit contributions | |
CCC | -0.439 |
HEAD | -0.438 |
HQ | -0.420 |
CDC | -0.416 |
INTON | -0.406 |
Token | – |
Token ID | 784 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
mos | +0.854 |
rout | +0.831 |
onomy | +0.829 |
� | +0.819 |
wise | +0.804 |
Neg logit contributions | |
CCC | -0.687 |
HEAD | -0.686 |
HQ | -0.657 |
CDC | -0.642 |
INTON | -0.621 |
Token | never |
Token ID | 1239 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
CCC | +1.231 |
HEAD | +1.224 |
HQ | +1.179 |
CDC | +1.155 |
INTON | +1.116 |
Neg logit contributions | |
mos | -1.163 |
onomy | -1.124 |
rout | -1.110 |
� | -1.104 |
wise | -1.060 |
Token | mind |
Token ID | 2000 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
CCC | +0.580 |
HEAD | +0.575 |
HQ | +0.555 |
CDC | +0.547 |
INTON | +0.527 |
Neg logit contributions | |
mos | -0.526 |
onomy | -0.503 |
rout | -0.502 |
� | -0.494 |
wise | -0.484 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
CCC | +3.213 |
HEAD | +3.184 |
HQ | +3.071 |
CDC | +3.003 |
INTON | +2.896 |
Neg logit contributions | |
mos | -3.012 |
onomy | -2.928 |
� | -2.864 |
rout | -2.853 |
wise | -2.709 |
Token | corporate |
Token ID | 6355 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
CCC | +0.023 |
HEAD | +0.022 |
HQ | +0.022 |
CDC | +0.021 |
INTON | +0.021 |
Neg logit contributions | |
mos | -0.017 |
rout | -0.016 |
onomy | -0.016 |
� | -0.015 |
wise | -0.015 |
Token | one |
Token ID | 530 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
mos | +0.380 |
rout | +0.367 |
onomy | +0.366 |
� | +0.353 |
wise | +0.349 |
Neg logit contributions | |
CCC | -0.450 |
HEAD | -0.447 |
HQ | -0.428 |
CDC | -0.427 |
INTON | -0.414 |
Token | . |
Token ID | 13 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
CCC | +0.011 |
HEAD | +0.011 |
HQ | +0.011 |
CDC | +0.011 |
INTON | +0.010 |
Neg logit contributions | |
mos | -0.015 |
onomy | -0.015 |
rout | -0.014 |
� | -0.014 |
wise | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
CCC | +0.747 |
HEAD | +0.742 |
HQ | +0.717 |
CDC | +0.703 |
INTON | +0.682 |
Neg logit contributions | |
mos | -0.635 |
onomy | -0.613 |
rout | -0.605 |
� | -0.601 |
wise | -0.577 |
Token | group |
Token ID | 1448 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
CCC | +0.665 |
HEAD | +0.664 |
HQ | +0.636 |
CDC | +0.632 |
INTON | +0.612 |
Neg logit contributions | |
mos | -0.560 |
onomy | -0.538 |
rout | -0.533 |
� | -0.527 |
wise | -0.504 |
Token | Raqqa |
Token ID | 30391 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
mos | +0.241 |
onomy | +0.231 |
rout | +0.229 |
� | +0.228 |
wise | +0.219 |
Neg logit contributions | |
CCC | -0.228 |
HEAD | -0.226 |
HQ | -0.216 |
CDC | -0.215 |
INTON | -0.210 |
Token | is |
Token ID | 318 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
CCC | +0.175 |
HEAD | +0.174 |
HQ | +0.165 |
CDC | +0.164 |
INTON | +0.160 |
Neg logit contributions | |
mos | -0.189 |
onomy | -0.183 |
rout | -0.181 |
� | -0.180 |
wise | -0.173 |
Token | Being |
Token ID | 11204 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
mos | +0.353 |
rout | +0.338 |
onomy | +0.334 |
� | +0.330 |
wise | +0.323 |
Neg logit contributions | |
CCC | -0.426 |
HEAD | -0.425 |
HQ | -0.407 |
CDC | -0.404 |
INTON | -0.398 |
Token | Sl |
Token ID | 3454 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
mos | +0.160 |
onomy | +0.154 |
rout | +0.154 |
� | +0.153 |
wise | +0.148 |
Neg logit contributions | |
CCC | -0.103 |
HEAD | -0.101 |
HQ | -0.097 |
CDC | -0.094 |
INTON | -0.091 |
Token | aughtered |
Token ID | 32734 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
CCC | +0.678 |
HEAD | +0.670 |
HQ | +0.653 |
CDC | +0.641 |
INTON | +0.624 |
Neg logit contributions | |
mos | -0.545 |
onomy | -0.528 |
rout | -0.515 |
� | -0.507 |
odox | -0.486 |
Token | Sil |
Token ID | 4243 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
mos | +3.057 |
� | +2.917 |
rout | +2.877 |
onomy | +2.796 |
wise | +2.704 |
Neg logit contributions | |
CCC | -5.129 |
HEAD | -4.956 |
CDC | -4.953 |
HQ | -4.864 |
INTON | -4.812 |
Token | ently |
Token ID | 1473 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
CCC | +0.779 |
HEAD | +0.776 |
HQ | +0.752 |
CDC | +0.736 |
INTON | +0.710 |
Neg logit contributions | |
mos | -0.632 |
onomy | -0.606 |
rout | -0.602 |
� | -0.593 |
wise | -0.570 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
CCC | +0.358 |
HEAD | +0.356 |
HQ | +0.338 |
CDC | +0.332 |
INTON | +0.321 |
Neg logit contributions | |
mos | -0.466 |
onomy | -0.452 |
� | -0.448 |
rout | -0.448 |
wise | -0.431 |
Token |
|
Token ID | 198 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
mos | +0.301 |
onomy | +0.290 |
rout | +0.286 |
� | +0.286 |
wise | +0.271 |
Neg logit contributions | |
CCC | -0.393 |
HEAD | -0.392 |
HQ | -0.378 |
CDC | -0.371 |
INTON | -0.361 |
Token |
|
Token ID | 198 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
mos | +0.537 |
onomy | +0.510 |
rout | +0.506 |
� | +0.489 |
wise | +0.473 |
Neg logit contributions | |
CCC | -1.005 |
HEAD | -0.997 |
HQ | -0.966 |
CDC | -0.959 |
INTON | -0.949 |
Token | look |
Token ID | 804 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
CCC | +0.247 |
HEAD | +0.245 |
HQ | +0.237 |
CDC | +0.233 |
INTON | +0.226 |
Neg logit contributions | |
mos | -0.188 |
onomy | -0.179 |
rout | -0.179 |
� | -0.176 |
wise | -0.170 |
Token | when |
Token ID | 618 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
mos | +0.275 |
rout | +0.264 |
onomy | +0.262 |
� | +0.261 |
wise | +0.255 |
Neg logit contributions | |
CCC | -0.271 |
HEAD | -0.268 |
HQ | -0.260 |
CDC | -0.256 |
INTON | -0.247 |
Token | they |
Token ID | 484 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
CCC | +1.367 |
HEAD | +1.358 |
HQ | +1.315 |
CDC | +1.294 |
INTON | +1.255 |
Neg logit contributions | |
mos | -1.019 |
rout | -0.968 |
onomy | -0.963 |
� | -0.957 |
wise | -0.921 |
Token | are |
Token ID | 389 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
CCC | +0.753 |
HEAD | +0.748 |
HQ | +0.726 |
CDC | +0.713 |
INTON | +0.694 |
Neg logit contributions | |
mos | -0.507 |
onomy | -0.481 |
rout | -0.480 |
� | -0.472 |
wise | -0.454 |
Token | se |
Token ID | 384 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
CCC | +0.870 |
HEAD | +0.864 |
HQ | +0.834 |
CDC | +0.824 |
INTON | +0.797 |
Neg logit contributions | |
mos | -0.748 |
rout | -0.713 |
onomy | -0.705 |
� | -0.702 |
wise | -0.683 |
Token | wn |
Token ID | 675 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
CCC | +1.205 |
HEAD | +1.199 |
HQ | +1.164 |
CDC | +1.142 |
INTON | +1.109 |
Neg logit contributions | |
mos | -0.803 |
onomy | -0.772 |
rout | -0.758 |
� | -0.756 |
wise | -0.716 |
Token | on |
Token ID | 319 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
mos | +3.753 |
rout | +3.612 |
wise | +3.584 |
onomy | +3.471 |
� | +3.438 |
Neg logit contributions | |
CCC | -3.840 |
HEAD | -3.773 |
HQ | -3.724 |
CDC | -3.657 |
INTON | -3.518 |
Token | and |
Token ID | 290 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
CCC | +0.075 |
HEAD | +0.074 |
HQ | +0.071 |
CDC | +0.069 |
INTON | +0.067 |
Neg logit contributions | |
mos | -0.091 |
rout | -0.088 |
onomy | -0.087 |
� | -0.087 |
wise | -0.085 |
Token | mimic |
Token ID | 26332 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
mos | +0.126 |
rout | +0.120 |
onomy | +0.120 |
� | +0.116 |
wise | +0.114 |
Neg logit contributions | |
CCC | -0.179 |
HEAD | -0.178 |
HQ | -0.172 |
CDC | -0.169 |
INTON | -0.165 |
Token | that |
Token ID | 326 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
mos | +0.610 |
rout | +0.582 |
onomy | +0.577 |
� | +0.576 |
wise | +0.557 |
Neg logit contributions | |
CCC | -0.742 |
HEAD | -0.739 |
HQ | -0.718 |
CDC | -0.700 |
INTON | -0.682 |
Token | pattern |
Token ID | 3912 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
CCC | +0.455 |
HEAD | +0.452 |
HQ | +0.437 |
CDC | +0.431 |
INTON | +0.416 |
Neg logit contributions | |
mos | -0.409 |
rout | -0.392 |
onomy | -0.391 |
� | -0.386 |
wise | -0.375 |
Token | hex |
Token ID | 17910 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
mos | +0.529 |
rout | +0.501 |
onomy | +0.494 |
� | +0.483 |
wise | +0.475 |
Neg logit contributions | |
CCC | -0.612 |
HEAD | -0.602 |
HQ | -0.584 |
CDC | -0.578 |
INTON | -0.559 |
Token | agon |
Token ID | 1840 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
mos | +1.518 |
onomy | +1.480 |
rout | +1.462 |
� | +1.456 |
wise | +1.415 |
Neg logit contributions | |
CCC | -0.881 |
HEAD | -0.868 |
HQ | -0.829 |
CDC | -0.803 |
INTON | -0.768 |
Token | - |
Token ID | 12 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
mos | +0.683 |
onomy | +0.657 |
rout | +0.655 |
� | +0.644 |
wise | +0.629 |
Neg logit contributions | |
CCC | -0.640 |
HEAD | -0.633 |
HQ | -0.612 |
CDC | -0.600 |
INTON | -0.582 |
Token | shaped |
Token ID | 16760 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
mos | +0.507 |
onomy | +0.492 |
rout | +0.486 |
� | +0.480 |
wise | +0.469 |
Neg logit contributions | |
CCC | -0.456 |
HEAD | -0.450 |
HQ | -0.437 |
CDC | -0.425 |
INTON | -0.417 |
Token | ep |
Token ID | 2462 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
mos | +0.223 |
rout | +0.211 |
onomy | +0.210 |
� | +0.205 |
wise | +0.202 |
Neg logit contributions | |
CCC | -0.261 |
HEAD | -0.257 |
HQ | -0.249 |
CDC | -0.246 |
INTON | -0.238 |
Token | oxy |
Token ID | 23536 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
CCC | +0.645 |
HEAD | +0.639 |
HQ | +0.617 |
CDC | +0.607 |
INTON | +0.591 |
Neg logit contributions | |
mos | -0.521 |
onomy | -0.506 |
rout | -0.494 |
� | -0.489 |
wise | -0.470 |
Token | resin |
Token ID | 36536 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
mos | +3.597 |
rout | +3.438 |
onomy | +3.360 |
wise | +3.259 |
� | +3.220 |
Neg logit contributions | |
CCC | -3.858 |
HEAD | -3.806 |
HQ | -3.681 |
CDC | -3.653 |
INTON | -3.535 |
Token | scaff |
Token ID | 41498 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
mos | +1.756 |
rout | +1.681 |
onomy | +1.674 |
� | +1.622 |
wise | +1.616 |
Neg logit contributions | |
CCC | -1.602 |
HEAD | -1.581 |
HQ | -1.515 |
CDC | -1.503 |
INTON | -1.438 |
Token | old |
Token ID | 727 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
mos | +0.147 |
onomy | +0.141 |
rout | +0.139 |
� | +0.138 |
wise | +0.132 |
Neg logit contributions | |
CCC | -0.208 |
HEAD | -0.207 |
HQ | -0.201 |
CDC | -0.197 |
INTON | -0.191 |
Token | that |
Token ID | 326 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
CCC | +0.661 |
HEAD | +0.655 |
HQ | +0.631 |
CDC | +0.618 |
INTON | +0.597 |
Neg logit contributions | |
mos | -0.786 |
onomy | -0.758 |
rout | -0.755 |
� | -0.743 |
wise | -0.725 |
Token | measures |
Token ID | 5260 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
mos | +0.174 |
rout | +0.166 |
onomy | +0.163 |
� | +0.160 |
wise | +0.157 |
Neg logit contributions | |
CCC | -0.217 |
HEAD | -0.215 |
HQ | -0.209 |
CDC | -0.205 |
INTON | -0.200 |
Token | from |
Token ID | 422 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
mos | +0.141 |
onomy | +0.135 |
rout | +0.135 |
� | +0.132 |
wise | +0.130 |
Neg logit contributions | |
CCC | -0.144 |
HEAD | -0.143 |
HQ | -0.137 |
CDC | -0.136 |
INTON | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
mos | +0.190 |
rout | +0.181 |
onomy | +0.181 |
� | +0.179 |
wise | +0.174 |
Neg logit contributions | |
CCC | -0.220 |
HEAD | -0.219 |
HQ | -0.211 |
CDC | -0.207 |
INTON | -0.201 |
Token | presidential |
Token ID | 4787 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
CCC | +0.060 |
HEAD | +0.060 |
HQ | +0.058 |
CDC | +0.057 |
INTON | +0.055 |
Neg logit contributions | |
mos | -0.049 |
onomy | -0.047 |
rout | -0.047 |
� | -0.046 |
wise | -0.044 |
Token | race |
Token ID | 3234 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
CCC | +0.115 |
HEAD | +0.115 |
HQ | +0.110 |
CDC | +0.109 |
INTON | +0.105 |
Neg logit contributions | |
mos | -0.102 |
onomy | -0.099 |
rout | -0.098 |
� | -0.097 |
wise | -0.093 |
Token | to |
Token ID | 284 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
CCC | +0.083 |
HEAD | +0.083 |
HQ | +0.079 |
CDC | +0.078 |
INTON | +0.076 |
Neg logit contributions | |
mos | -0.071 |
onomy | -0.068 |
rout | -0.068 |
� | -0.067 |
wise | -0.065 |
Token | lame |
Token ID | 30248 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
CCC | +0.064 |
HEAD | +0.064 |
HQ | +0.061 |
CDC | +0.060 |
INTON | +0.058 |
Neg logit contributions | |
mos | -0.057 |
onomy | -0.055 |
rout | -0.055 |
� | -0.054 |
wise | -0.052 |
Token | caric |
Token ID | 33674 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
mos | +3.410 |
rout | +3.265 |
onomy | +3.254 |
� | +3.219 |
wise | +3.135 |
Neg logit contributions | |
HEAD | -3.659 |
CCC | -3.625 |
HQ | -3.484 |
CDC | -3.440 |
INTON | -3.321 |
Token | atures |
Token ID | 6691 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
mos | +0.992 |
onomy | +0.954 |
rout | +0.940 |
� | +0.931 |
wise | +0.893 |
Neg logit contributions | |
CCC | -1.281 |
HEAD | -1.269 |
HQ | -1.229 |
CDC | -1.203 |
INTON | -1.172 |
Token | of |
Token ID | 286 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
mos | +0.428 |
onomy | +0.409 |
rout | +0.408 |
� | +0.404 |
wise | +0.390 |
Neg logit contributions | |
CCC | -0.532 |
HEAD | -0.528 |
HQ | -0.514 |
CDC | -0.502 |
INTON | -0.492 |
Token | Asians |
Token ID | 30852 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
mos | +0.173 |
onomy | +0.164 |
rout | +0.164 |
� | +0.163 |
wise | +0.158 |
Neg logit contributions | |
CCC | -0.203 |
HEAD | -0.202 |
HQ | -0.195 |
CDC | -0.191 |
INTON | -0.185 |
Token | mas |
Token ID | 12422 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
mos | +0.732 |
onomy | +0.703 |
rout | +0.701 |
� | +0.695 |
wise | +0.675 |
Neg logit contributions | |
CCC | -0.615 |
HEAD | -0.607 |
HQ | -0.586 |
CDC | -0.572 |
INTON | -0.554 |
Token | demand |
Token ID | 3512 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
mos | +0.036 |
rout | +0.035 |
onomy | +0.034 |
� | +0.033 |
wise | +0.033 |
Neg logit contributions | |
CCC | -0.049 |
HEAD | -0.048 |
HQ | -0.047 |
CDC | -0.046 |
INTON | -0.045 |
Token | that |
Token ID | 326 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
CCC | +0.450 |
HEAD | +0.445 |
HQ | +0.429 |
CDC | +0.424 |
INTON | +0.411 |
Neg logit contributions | |
mos | -0.388 |
onomy | -0.372 |
rout | -0.371 |
� | -0.365 |
wise | -0.354 |
Token | he |
Token ID | 339 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
CCC | +0.297 |
HEAD | +0.293 |
HQ | +0.283 |
CDC | +0.280 |
INTON | +0.270 |
Neg logit contributions | |
mos | -0.253 |
onomy | -0.241 |
rout | -0.241 |
� | -0.239 |
wise | -0.231 |
Token | commit |
Token ID | 4589 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
CCC | +0.300 |
HEAD | +0.295 |
HQ | +0.287 |
CDC | +0.283 |
INTON | +0.276 |
Neg logit contributions | |
mos | -0.223 |
rout | -0.215 |
onomy | -0.210 |
� | -0.205 |
wise | -0.202 |
Token | se |
Token ID | 384 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
CCC | +1.251 |
HEAD | +1.247 |
HQ | +1.202 |
CDC | +1.182 |
INTON | +1.149 |
Neg logit contributions | |
mos | -1.014 |
rout | -0.968 |
onomy | -0.965 |
� | -0.953 |
wise | -0.927 |
Token | pp |
Token ID | 381 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
CCC | +0.997 |
HEAD | +0.993 |
HQ | +0.965 |
CDC | +0.950 |
INTON | +0.926 |
Neg logit contributions | |
mos | -0.488 |
onomy | -0.463 |
rout | -0.456 |
� | -0.451 |
wise | -0.425 |
Token | uku |
Token ID | 33263 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
mos | +3.206 |
onomy | +3.181 |
rout | +3.128 |
� | +3.084 |
wise | +2.988 |
Neg logit contributions | |
HEAD | -3.789 |
CCC | -3.712 |
HQ | -3.607 |
CDC | -3.528 |
INTON | -3.490 |
Token | to |
Token ID | 284 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
CCC | +1.009 |
HEAD | +1.001 |
HQ | +0.963 |
CDC | +0.943 |
INTON | +0.910 |
Neg logit contributions | |
mos | -1.100 |
onomy | -1.063 |
rout | -1.055 |
� | -1.044 |
wise | -1.011 |
Token | regain |
Token ID | 21509 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
mos | +0.150 |
rout | +0.145 |
onomy | +0.143 |
� | +0.140 |
wise | +0.137 |
Neg logit contributions | |
CCC | -0.197 |
HEAD | -0.196 |
HQ | -0.189 |
CDC | -0.187 |
INTON | -0.182 |
Token | the |
Token ID | 262 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
mos | +0.486 |
rout | +0.467 |
onomy | +0.461 |
� | +0.453 |
wise | +0.446 |
Neg logit contributions | |
CCC | -0.612 |
HEAD | -0.609 |
HQ | -0.586 |
CDC | -0.584 |
INTON | -0.564 |
Token | honor |
Token ID | 7522 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
mos | +0.034 |
rout | +0.032 |
onomy | +0.032 |
� | +0.031 |
wise | +0.031 |
Neg logit contributions | |
CCC | -0.043 |
HEAD | -0.042 |
HQ | -0.041 |
CDC | -0.041 |
INTON | -0.039 |
Token | s |
Token ID | 82 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
mos | +0.039 |
onomy | +0.038 |
rout | +0.037 |
� | +0.037 |
wise | +0.036 |
Neg logit contributions | |
CCC | -0.040 |
HEAD | -0.040 |
HQ | -0.039 |
CDC | -0.038 |
INTON | -0.037 |
Token | event |
Token ID | 1785 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
CCC | +0.220 |
HEAD | +0.218 |
HQ | +0.210 |
CDC | +0.208 |
INTON | +0.201 |
Neg logit contributions | |
mos | -0.192 |
onomy | -0.183 |
rout | -0.183 |
� | -0.180 |
wise | -0.175 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
mos | +0.185 |
onomy | +0.178 |
rout | +0.176 |
� | +0.175 |
wise | +0.168 |
Neg logit contributions | |
CCC | -0.208 |
HEAD | -0.207 |
HQ | -0.200 |
CDC | -0.196 |
INTON | -0.191 |
Token | presented |
Token ID | 5545 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
mos | +0.503 |
onomy | +0.479 |
rout | +0.478 |
� | +0.474 |
wise | +0.458 |
Neg logit contributions | |
CCC | -0.578 |
HEAD | -0.574 |
HQ | -0.553 |
CDC | -0.545 |
INTON | -0.530 |
Token | by |
Token ID | 416 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
mos | +1.232 |
onomy | +1.182 |
� | +1.176 |
rout | +1.170 |
wise | +1.136 |
Neg logit contributions | |
CCC | -1.254 |
HEAD | -1.246 |
HQ | -1.193 |
CDC | -1.173 |
INTON | -1.144 |
Token | Kaiser |
Token ID | 32670 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
mos | +0.614 |
onomy | +0.588 |
rout | +0.584 |
� | +0.579 |
wise | +0.563 |
Neg logit contributions | |
CCC | -0.632 |
HEAD | -0.629 |
HQ | -0.604 |
CDC | -0.592 |
INTON | -0.579 |
Token | P |
Token ID | 350 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
mos | +3.255 |
onomy | +3.140 |
� | +3.119 |
rout | +3.049 |
wise | +2.979 |
Neg logit contributions | |
CCC | -3.451 |
HEAD | -3.356 |
HQ | -3.192 |
INTON | -3.181 |
CDC | -3.162 |
Token | erman |
Token ID | 2224 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
HEAD | +0.180 |
CCC | +0.177 |
HQ | +0.172 |
CDC | +0.169 |
INTON | +0.167 |
Neg logit contributions | |
mos | -0.135 |
� | -0.129 |
onomy | -0.128 |
rout | -0.125 |
wise | -0.124 |
Token | ente |
Token ID | 21872 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
CCC | +0.242 |
HEAD | +0.241 |
HQ | +0.235 |
CDC | +0.230 |
INTON | +0.227 |
Neg logit contributions | |
mos | -0.092 |
onomy | -0.087 |
� | -0.086 |
rout | -0.083 |
wise | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
CCC | +0.162 |
HEAD | +0.161 |
HQ | +0.153 |
CDC | +0.150 |
INTON | +0.147 |
Neg logit contributions | |
mos | -0.186 |
onomy | -0.180 |
� | -0.178 |
rout | -0.178 |
wise | -0.171 |
Token | starts |
Token ID | 4940 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
mos | +0.216 |
rout | +0.205 |
onomy | +0.205 |
� | +0.203 |
wise | +0.195 |
Neg logit contributions | |
CCC | -0.255 |
HEAD | -0.254 |
HQ | -0.244 |
CDC | -0.240 |
INTON | -0.235 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
CCC | +0.247 |
HEAD | +0.245 |
HQ | +0.238 |
CDC | +0.233 |
INTON | +0.226 |
Neg logit contributions | |
mos | -0.200 |
onomy | -0.192 |
rout | -0.190 |
� | -0.188 |
wise | -0.180 |
Token | Haw |
Token ID | 33055 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
CCC | +0.518 |
HEAD | +0.511 |
HQ | +0.490 |
CDC | +0.476 |
INTON | +0.463 |
Neg logit contributions | |
mos | -0.684 |
onomy | -0.670 |
� | -0.658 |
rout | -0.657 |
wise | -0.631 |
Token | aii |
Token ID | 42648 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
mos | +1.153 |
onomy | +1.114 |
� | +1.088 |
rout | +1.087 |
wise | +1.023 |
Neg logit contributions | |
CCC | -1.629 |
HEAD | -1.623 |
HQ | -1.556 |
CDC | -1.531 |
INTON | -1.501 |
Token | Congress |
Token ID | 3162 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
mos | +0.985 |
onomy | +0.949 |
rout | +0.947 |
� | +0.931 |
wise | +0.906 |
Neg logit contributions | |
CCC | -1.037 |
HEAD | -1.034 |
HQ | -0.991 |
CDC | -0.977 |
INTON | -0.952 |
Token | woman |
Token ID | 8580 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
mos | +0.629 |
onomy | +0.608 |
rout | +0.601 |
� | +0.593 |
wise | +0.569 |
Neg logit contributions | |
CCC | -0.785 |
HEAD | -0.782 |
HQ | -0.758 |
CDC | -0.745 |
INTON | -0.720 |
Token | Tuls |
Token ID | 33219 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
mos | +0.315 |
onomy | +0.300 |
rout | +0.298 |
� | +0.294 |
wise | +0.281 |
Neg logit contributions | |
CCC | -0.490 |
HEAD | -0.486 |
HQ | -0.473 |
CDC | -0.466 |
INTON | -0.453 |
Token | i |
Token ID | 72 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
mos | +2.934 |
onomy | +2.860 |
� | +2.815 |
rout | +2.801 |
wise | +2.630 |
Neg logit contributions | |
CCC | -3.766 |
HEAD | -3.743 |
HQ | -3.639 |
CDC | -3.556 |
INTON | -3.395 |
Token | G |
Token ID | 402 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
mos | +0.854 |
onomy | +0.823 |
rout | +0.816 |
� | +0.812 |
wise | +0.779 |
Neg logit contributions | |
CCC | -1.107 |
HEAD | -1.099 |
HQ | -1.066 |
CDC | -1.044 |
INTON | -1.022 |
Token | abb |
Token ID | 6485 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
mos | +0.560 |
onomy | +0.558 |
� | +0.539 |
rout | +0.538 |
wise | +0.509 |
Neg logit contributions | |
HEAD | -1.064 |
CCC | -1.052 |
HQ | -1.023 |
CDC | -0.999 |
INTON | -0.977 |
Token | ard |
Token ID | 446 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
CCC | +2.097 |
HEAD | +2.087 |
HQ | +2.018 |
CDC | +1.982 |
INTON | +1.924 |
Neg logit contributions | |
mos | -1.494 |
onomy | -1.436 |
rout | -1.418 |
� | -1.407 |
wise | -1.346 |
Token | is |
Token ID | 318 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
mos | +0.041 |
onomy | +0.040 |
rout | +0.040 |
� | +0.039 |
wise | +0.038 |
Neg logit contributions | |
CCC | -0.044 |
HEAD | -0.044 |
HQ | -0.043 |
CDC | -0.042 |
INTON | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
mos | +0.433 |
rout | +0.420 |
onomy | +0.411 |
� | +0.408 |
wise | +0.402 |
Neg logit contributions | |
CCC | -0.533 |
HEAD | -0.531 |
HQ | -0.512 |
CDC | -0.503 |
INTON | -0.495 |
Token | Soon |
Token ID | 15894 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
mos | +0.202 |
rout | +0.197 |
onomy | +0.194 |
� | +0.191 |
wise | +0.188 |
Neg logit contributions | |
CCC | -0.229 |
HEAD | -0.229 |
HQ | -0.220 |
CDC | -0.217 |
INTON | -0.214 |
Token | ers |
Token ID | 364 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
mos | +0.892 |
rout | +0.858 |
� | +0.855 |
onomy | +0.854 |
wise | +0.823 |
Neg logit contributions | |
HEAD | -0.690 |
CCC | -0.689 |
HQ | -0.648 |
CDC | -0.647 |
INTON | -0.615 |
Token | ' |
Token ID | 6 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
mos | +0.276 |
rout | +0.268 |
onomy | +0.264 |
� | +0.261 |
wise | +0.256 |
Neg logit contributions | |
HEAD | -0.253 |
CCC | -0.253 |
HQ | -0.241 |
CDC | -0.238 |
INTON | -0.233 |
Token | own |
Token ID | 898 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
mos | +0.470 |
rout | +0.459 |
onomy | +0.447 |
� | +0.438 |
wise | +0.437 |
Neg logit contributions | |
CCC | -0.583 |
HEAD | -0.583 |
HQ | -0.558 |
CDC | -0.551 |
INTON | -0.547 |
Token | inept |
Token ID | 43891 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
mos | +0.754 |
rout | +0.736 |
onomy | +0.721 |
wise | +0.702 |
� | +0.702 |
Neg logit contributions | |
HEAD | -0.919 |
CCC | -0.918 |
HQ | -0.880 |
CDC | -0.869 |
INTON | -0.858 |
Token | offense |
Token ID | 6907 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
mos | +2.474 |
onomy | +2.435 |
rout | +2.419 |
� | +2.359 |
wise | +2.260 |
Neg logit contributions | |
HEAD | -4.182 |
CCC | -4.103 |
HQ | -3.975 |
CDC | -3.939 |
INTON | -3.894 |
Token | and |
Token ID | 290 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
CCC | +0.672 |
HEAD | +0.668 |
HQ | +0.640 |
CDC | +0.627 |
INTON | +0.606 |
Neg logit contributions | |
mos | -0.763 |
onomy | -0.738 |
rout | -0.733 |
� | -0.725 |
wise | -0.705 |
Token | OU |
Token ID | 47070 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
mos | +0.273 |
rout | +0.263 |
onomy | +0.261 |
� | +0.257 |
wise | +0.251 |
Neg logit contributions | |
CCC | -0.316 |
HEAD | -0.314 |
HQ | -0.303 |
CDC | -0.298 |
INTON | -0.290 |
Token | 's |
Token ID | 338 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
mos | +1.092 |
onomy | +1.058 |
rout | +1.058 |
� | +1.045 |
wise | +1.017 |
Neg logit contributions | |
CCC | -0.838 |
HEAD | -0.834 |
HQ | -0.793 |
CDC | -0.779 |
INTON | -0.752 |
Token | front |
Token ID | 2166 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
mos | +0.187 |
rout | +0.182 |
onomy | +0.178 |
� | +0.175 |
wise | +0.173 |
Neg logit contributions | |
CCC | -0.227 |
HEAD | -0.227 |
HQ | -0.218 |
CDC | -0.215 |
INTON | -0.212 |
Token | good |
Token ID | 922 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
mos | +0.049 |
rout | +0.047 |
onomy | +0.046 |
� | +0.045 |
wise | +0.044 |
Neg logit contributions | |
CCC | -0.099 |
HEAD | -0.098 |
HQ | -0.096 |
CDC | -0.095 |
INTON | -0.093 |
Token | idea |
Token ID | 2126 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
CCC | +0.413 |
HEAD | +0.410 |
HQ | +0.395 |
CDC | +0.387 |
INTON | +0.375 |
Neg logit contributions | |
mos | -0.434 |
onomy | -0.418 |
rout | -0.416 |
� | -0.409 |
wise | -0.400 |
Token | to |
Token ID | 284 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
CCC | +0.152 |
HEAD | +0.151 |
HQ | +0.146 |
CDC | +0.143 |
INTON | +0.138 |
Neg logit contributions | |
mos | -0.127 |
onomy | -0.124 |
rout | -0.121 |
� | -0.121 |
wise | -0.115 |
Token | release |
Token ID | 2650 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
mos | +0.135 |
rout | +0.128 |
onomy | +0.126 |
� | +0.124 |
wise | +0.121 |
Neg logit contributions | |
CCC | -0.192 |
HEAD | -0.190 |
HQ | -0.185 |
CDC | -0.182 |
INTON | -0.178 |
Token | 100 |
Token ID | 1802 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
mos | +0.474 |
rout | +0.451 |
onomy | +0.450 |
� | +0.443 |
wise | +0.433 |
Neg logit contributions | |
CCC | -0.577 |
HEAD | -0.576 |
HQ | -0.553 |
CDC | -0.552 |
INTON | -0.532 |
Token | helium |
Token ID | 43142 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
mos | +0.205 |
onomy | +0.196 |
rout | +0.194 |
� | +0.193 |
wise | +0.187 |
Neg logit contributions | |
CCC | -0.188 |
HEAD | -0.187 |
HQ | -0.178 |
CDC | -0.176 |
INTON | -0.170 |
Token | - |
Token ID | 12 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
mos | +3.962 |
onomy | +3.759 |
rout | +3.751 |
� | +3.715 |
wise | +3.681 |
Neg logit contributions | |
CCC | -2.742 |
HEAD | -2.684 |
HQ | -2.538 |
CDC | -2.514 |
INTON | -2.436 |
Token | filled |
Token ID | 20286 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
CCC | +0.035 |
HEAD | +0.035 |
HQ | +0.034 |
CDC | +0.033 |
INTON | +0.032 |
Neg logit contributions | |
mos | -0.033 |
onomy | -0.031 |
rout | -0.031 |
� | -0.031 |
wise | -0.030 |
Token | balloons |
Token ID | 35485 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
CCC | +0.575 |
HEAD | +0.569 |
HQ | +0.542 |
CDC | +0.534 |
INTON | +0.514 |
Neg logit contributions | |
mos | -0.725 |
onomy | -0.691 |
rout | -0.690 |
� | -0.679 |
wise | -0.665 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
mos | +0.267 |
rout | +0.255 |
onomy | +0.254 |
� | +0.248 |
wise | +0.244 |
Neg logit contributions | |
CCC | -0.289 |
HEAD | -0.285 |
HQ | -0.277 |
CDC | -0.273 |
INTON | -0.266 |
Token | each |
Token ID | 1123 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
CCC | +0.298 |
HEAD | +0.295 |
HQ | +0.284 |
CDC | +0.281 |
INTON | +0.273 |
Neg logit contributions | |
mos | -0.259 |
onomy | -0.246 |
rout | -0.246 |
� | -0.242 |
wise | -0.236 |
Token | content |
Token ID | 2695 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
mos | +0.445 |
rout | +0.426 |
onomy | +0.425 |
� | +0.416 |
wise | +0.411 |
Neg logit contributions | |
CCC | -0.551 |
HEAD | -0.550 |
HQ | -0.529 |
CDC | -0.526 |
INTON | -0.505 |
Token | whose |
Token ID | 3025 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
CCC | +0.434 |
HEAD | +0.432 |
HQ | +0.415 |
CDC | +0.409 |
INTON | +0.398 |
Neg logit contributions | |
mos | -0.372 |
onomy | -0.359 |
rout | -0.356 |
� | -0.350 |
wise | -0.343 |
Token | quality |
Token ID | 3081 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
CCC | +0.433 |
HEAD | +0.429 |
HQ | +0.412 |
CDC | +0.409 |
INTON | +0.397 |
Neg logit contributions | |
mos | -0.340 |
rout | -0.326 |
onomy | -0.326 |
� | -0.319 |
wise | -0.311 |
Token | is |
Token ID | 318 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
mos | +0.772 |
onomy | +0.738 |
rout | +0.736 |
� | +0.723 |
wise | +0.706 |
Neg logit contributions | |
CCC | -0.928 |
HEAD | -0.923 |
HQ | -0.886 |
CDC | -0.872 |
INTON | -0.850 |
Token | undis |
Token ID | 24149 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
mos | +0.009 |
rout | +0.009 |
onomy | +0.009 |
� | +0.008 |
wise | +0.008 |
Neg logit contributions | |
CCC | -0.011 |
HEAD | -0.011 |
HQ | -0.011 |
CDC | -0.010 |
INTON | -0.010 |
Token | puted |
Token ID | 17128 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
mos | +0.519 |
onomy | +0.497 |
rout | +0.494 |
� | +0.489 |
wise | +0.467 |
Neg logit contributions | |
CCC | -0.686 |
HEAD | -0.682 |
HQ | -0.661 |
CDC | -0.649 |
INTON | -0.629 |
Token | will |
Token ID | 481 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
mos | +3.020 |
onomy | +2.941 |
rout | +2.932 |
� | +2.845 |
wise | +2.809 |
Neg logit contributions | |
CCC | -3.497 |
HEAD | -3.455 |
HQ | -3.332 |
CDC | -3.292 |
INTON | -3.202 |
Token | be |
Token ID | 307 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
CCC | +0.320 |
HEAD | +0.317 |
HQ | +0.308 |
CDC | +0.301 |
INTON | +0.293 |
Neg logit contributions | |
mos | -0.238 |
rout | -0.226 |
onomy | -0.225 |
� | -0.220 |
wise | -0.216 |
Token | more |
Token ID | 517 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
mos | +0.359 |
rout | +0.341 |
onomy | +0.339 |
� | +0.337 |
wise | +0.332 |
Neg logit contributions | |
CCC | -0.402 |
HEAD | -0.397 |
HQ | -0.385 |
CDC | -0.380 |
INTON | -0.368 |
Token | successful |
Token ID | 4388 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
CCC | +0.286 |
HEAD | +0.283 |
HQ | +0.274 |
CDC | +0.270 |
INTON | +0.262 |
Neg logit contributions | |
mos | -0.224 |
rout | -0.213 |
onomy | -0.212 |
� | -0.208 |
wise | -0.206 |
Token | and |
Token ID | 290 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
mos | +1.174 |
rout | +1.119 |
onomy | +1.117 |
wise | +1.102 |
� | +1.096 |
Neg logit contributions | |
CCC | -1.020 |
HEAD | -1.007 |
HQ | -0.961 |
CDC | -0.953 |
INTON | -0.913 |
Token | that |
Token ID | 326 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
mos | +0.618 |
rout | +0.594 |
onomy | +0.590 |
� | +0.585 |
wise | +0.570 |
Neg logit contributions | |
CCC | -0.635 |
HEAD | -0.628 |
HQ | -0.602 |
CDC | -0.598 |
INTON | -0.582 |
Token | can |
Token ID | 460 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
mos | +0.365 |
rout | +0.349 |
onomy | +0.344 |
� | +0.341 |
wise | +0.331 |
Neg logit contributions | |
CCC | -0.458 |
HEAD | -0.453 |
HQ | -0.438 |
CDC | -0.433 |
INTON | -0.418 |
Token | call |
Token ID | 869 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
mos | +0.263 |
rout | +0.254 |
onomy | +0.252 |
� | +0.247 |
wise | +0.242 |
Neg logit contributions | |
CCC | -0.261 |
HEAD | -0.259 |
HQ | -0.250 |
CDC | -0.244 |
INTON | -0.237 |
Token | on |
Token ID | 319 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
mos | +0.714 |
onomy | +0.679 |
rout | +0.676 |
� | +0.661 |
wise | +0.657 |
Neg logit contributions | |
CCC | -0.854 |
HEAD | -0.849 |
HQ | -0.817 |
CDC | -0.811 |
INTON | -0.785 |
Token | global |
Token ID | 3298 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
mos | +0.039 |
rout | +0.037 |
onomy | +0.037 |
� | +0.037 |
wise | +0.036 |
Neg logit contributions | |
CCC | -0.048 |
HEAD | -0.047 |
HQ | -0.046 |
CDC | -0.045 |
INTON | -0.044 |
Token | Muslim |
Token ID | 3765 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
mos | +0.578 |
rout | +0.550 |
onomy | +0.548 |
� | +0.534 |
wise | +0.526 |
Neg logit contributions | |
CCC | -0.707 |
HEAD | -0.705 |
HQ | -0.681 |
CDC | -0.670 |
INTON | -0.649 |
Token | support |
Token ID | 1104 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
mos | +2.913 |
rout | +2.777 |
onomy | +2.735 |
wise | +2.669 |
� | +2.655 |
Neg logit contributions | |
CCC | -3.592 |
HEAD | -3.542 |
HQ | -3.413 |
CDC | -3.410 |
INTON | -3.303 |
Token | when |
Token ID | 618 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
mos | +0.383 |
onomy | +0.370 |
rout | +0.367 |
� | +0.364 |
wise | +0.353 |
Neg logit contributions | |
CCC | -0.383 |
HEAD | -0.381 |
HQ | -0.366 |
CDC | -0.359 |
INTON | -0.349 |
Token | criticised |
Token ID | 23894 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
CCC | +0.716 |
HEAD | +0.713 |
HQ | +0.686 |
CDC | +0.675 |
INTON | +0.653 |
Neg logit contributions | |
mos | -0.604 |
onomy | -0.577 |
rout | -0.575 |
� | -0.571 |
wise | -0.551 |
Token | . |
Token ID | 13 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
mos | +0.072 |
onomy | +0.069 |
rout | +0.069 |
� | +0.068 |
wise | +0.066 |
Neg logit contributions | |
CCC | -0.075 |
HEAD | -0.074 |
HQ | -0.072 |
CDC | -0.070 |
INTON | -0.068 |
Token | Second |
Token ID | 5498 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
CCC | +0.141 |
HEAD | +0.140 |
HQ | +0.134 |
CDC | +0.132 |
INTON | +0.127 |
Neg logit contributions | |
mos | -0.143 |
onomy | -0.138 |
� | -0.137 |
rout | -0.136 |
wise | -0.131 |
Token | reporting |
Token ID | 6447 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
CCC | +0.391 |
HEAD | +0.389 |
HQ | +0.374 |
CDC | +0.367 |
INTON | +0.357 |
Neg logit contributions | |
mos | -0.332 |
onomy | -0.319 |
rout | -0.318 |
� | -0.314 |
wise | -0.304 |
Token | partnership |
Token ID | 10413 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
mos | +0.308 |
onomy | +0.300 |
rout | +0.295 |
� | +0.288 |
wise | +0.282 |
Neg logit contributions | |
HEAD | -0.374 |
CCC | -0.373 |
HQ | -0.358 |
CDC | -0.356 |
INTON | -0.345 |
Token | between |
Token ID | 1022 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
CCC | +0.393 |
HEAD | +0.393 |
HQ | +0.377 |
CDC | +0.369 |
INTON | +0.359 |
Neg logit contributions | |
mos | -0.400 |
onomy | -0.389 |
rout | -0.382 |
� | -0.381 |
wise | -0.370 |
Token | NPR |
Token ID | 17921 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
mos | +1.433 |
onomy | +1.358 |
rout | +1.352 |
� | +1.342 |
wise | +1.316 |
Neg logit contributions | |
HEAD | -1.401 |
CCC | -1.396 |
HQ | -1.329 |
CDC | -1.297 |
INTON | -1.297 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
mos | +1.603 |
onomy | +1.546 |
rout | +1.517 |
� | +1.513 |
wise | +1.484 |
Neg logit contributions | |
CCC | -1.551 |
HEAD | -1.530 |
INTON | -1.434 |
CDC | -1.429 |
HQ | -1.416 |
Token | Kaiser |
Token ID | 32670 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
HEAD | +0.181 |
CCC | +0.181 |
HQ | +0.173 |
CDC | +0.169 |
INTON | +0.166 |
Neg logit contributions | |
mos | -0.187 |
onomy | -0.179 |
rout | -0.177 |
� | -0.177 |
wise | -0.172 |
Token | Health |
Token ID | 3893 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
mos | +3.223 |
onomy | +3.133 |
� | +3.097 |
rout | +3.021 |
wise | +2.969 |
Neg logit contributions | |
CCC | -3.064 |
HEAD | -3.001 |
INTON | -2.841 |
HQ | -2.822 |
CDC | -2.787 |
Token | News |
Token ID | 3000 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
mos | +0.402 |
onomy | +0.388 |
� | +0.381 |
rout | +0.381 |
wise | +0.364 |
Neg logit contributions | |
CCC | -0.555 |
HEAD | -0.551 |
HQ | -0.528 |
CDC | -0.522 |
INTON | -0.511 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
CCC | +0.731 |
HEAD | +0.724 |
HQ | +0.679 |
CDC | +0.670 |
INTON | +0.655 |
Neg logit contributions | |
mos | -1.044 |
onomy | -1.019 |
� | -1.005 |
rout | -1.001 |
wise | -0.970 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
CCC | +0.020 |
HEAD | +0.019 |
HQ | +0.019 |
CDC | +0.018 |
INTON | +0.018 |
Neg logit contributions | |
mos | -0.018 |
onomy | -0.018 |
rout | -0.018 |
� | -0.017 |
wise | -0.017 |
Token | When |
Token ID | 2215 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
CCC | +0.645 |
HEAD | +0.637 |
HQ | +0.610 |
CDC | +0.594 |
INTON | +0.577 |
Neg logit contributions | |
mos | -0.853 |
onomy | -0.835 |
� | -0.820 |
rout | -0.819 |
wise | -0.787 |
Token | This |
Token ID | 770 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
CCC | +0.179 |
HEAD | +0.177 |
HQ | +0.170 |
CDC | +0.168 |
INTON | +0.162 |
Neg logit contributions | |
mos | -0.178 |
onomy | -0.171 |
rout | -0.169 |
� | -0.169 |
wise | -0.163 |
Token | time |
Token ID | 640 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
CCC | +0.295 |
HEAD | +0.291 |
HQ | +0.280 |
CDC | +0.279 |
INTON | +0.269 |
Neg logit contributions | |
mos | -0.284 |
rout | -0.274 |
onomy | -0.271 |
� | -0.266 |
wise | -0.265 |
Token | I |
Token ID | 314 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
mos | +0.661 |
rout | +0.633 |
onomy | +0.624 |
� | +0.624 |
wise | +0.614 |
Neg logit contributions | |
CCC | -0.719 |
HEAD | -0.710 |
HQ | -0.684 |
CDC | -0.680 |
INTON | -0.653 |
Token | used |
Token ID | 973 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
mos | +0.451 |
rout | +0.429 |
onomy | +0.421 |
� | +0.417 |
wise | +0.416 |
Neg logit contributions | |
CCC | -0.481 |
HEAD | -0.475 |
HQ | -0.460 |
CDC | -0.455 |
INTON | -0.443 |
Token | more |
Token ID | 517 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
mos | +0.290 |
rout | +0.278 |
onomy | +0.278 |
� | +0.273 |
wise | +0.267 |
Neg logit contributions | |
CCC | -0.306 |
HEAD | -0.305 |
HQ | -0.293 |
CDC | -0.289 |
INTON | -0.281 |
Token | rud |
Token ID | 28906 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
CCC | +0.141 |
HEAD | +0.139 |
HQ | +0.135 |
CDC | +0.133 |
INTON | +0.129 |
Neg logit contributions | |
mos | -0.118 |
rout | -0.113 |
onomy | -0.112 |
� | -0.110 |
wise | -0.108 |
Token | der |
Token ID | 1082 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
mos | +3.578 |
onomy | +3.492 |
rout | +3.468 |
� | +3.419 |
wise | +3.323 |
Neg logit contributions | |
CCC | -2.754 |
HEAD | -2.675 |
HQ | -2.557 |
CDC | -2.535 |
INTON | -2.452 |
Token | and |
Token ID | 290 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
mos | +0.374 |
onomy | +0.361 |
rout | +0.360 |
� | +0.354 |
wise | +0.346 |
Neg logit contributions | |
CCC | -0.390 |
HEAD | -0.382 |
HQ | -0.372 |
CDC | -0.366 |
INTON | -0.353 |
Token | less |
Token ID | 1342 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
mos | +0.252 |
rout | +0.239 |
onomy | +0.235 |
� | +0.234 |
wise | +0.230 |
Neg logit contributions | |
CCC | -0.317 |
HEAD | -0.311 |
HQ | -0.304 |
CDC | -0.300 |
INTON | -0.292 |
Token | a |
Token ID | 257 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
CCC | +0.311 |
HEAD | +0.307 |
HQ | +0.300 |
CDC | +0.297 |
INTON | +0.289 |
Neg logit contributions | |
mos | -0.194 |
rout | -0.183 |
onomy | -0.181 |
� | -0.179 |
wise | -0.174 |
Token | iler |
Token ID | 5329 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
CCC | +0.194 |
HEAD | +0.193 |
HQ | +0.188 |
CDC | +0.185 |
INTON | +0.181 |
Neg logit contributions | |
mos | -0.095 |
onomy | -0.090 |
rout | -0.089 |
� | -0.088 |
wise | -0.083 |
Token | But |
Token ID | 887 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
mos | +0.583 |
onomy | +0.566 |
rout | +0.557 |
� | +0.554 |
wise | +0.535 |
Neg logit contributions | |
CCC | -0.582 |
HEAD | -0.577 |
HQ | -0.554 |
CDC | -0.546 |
INTON | -0.529 |
Token | the |
Token ID | 262 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
mos | +0.705 |
rout | +0.679 |
onomy | +0.675 |
� | +0.661 |
wise | +0.651 |
Neg logit contributions | |
CCC | -0.781 |
HEAD | -0.779 |
HQ | -0.743 |
CDC | -0.741 |
INTON | -0.721 |
Token | five |
Token ID | 1936 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
CCC | +0.131 |
HEAD | +0.131 |
HQ | +0.125 |
CDC | +0.124 |
INTON | +0.120 |
Neg logit contributions | |
mos | -0.105 |
onomy | -0.101 |
rout | -0.101 |
� | -0.098 |
wise | -0.096 |
Token | Google |
Token ID | 3012 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
CCC | +0.477 |
HEAD | +0.474 |
HQ | +0.456 |
CDC | +0.447 |
INTON | +0.432 |
Neg logit contributions | |
mos | -0.463 |
onomy | -0.447 |
rout | -0.443 |
� | -0.439 |
wise | -0.424 |
Token | Android |
Token ID | 5565 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
mos | +1.233 |
onomy | +1.195 |
rout | +1.187 |
� | +1.162 |
wise | +1.135 |
Neg logit contributions | |
CCC | -1.213 |
HEAD | -1.203 |
HQ | -1.152 |
CDC | -1.141 |
INTON | -1.091 |
Token | Honey |
Token ID | 21788 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
mos | +1.116 |
onomy | +1.077 |
rout | +1.073 |
� | +1.048 |
wise | +1.036 |
Neg logit contributions | |
CCC | -1.084 |
HEAD | -1.073 |
HQ | -1.027 |
CDC | -1.018 |
INTON | -0.979 |
Token | comb |
Token ID | 24011 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
mos | +2.463 |
onomy | +2.379 |
rout | +2.313 |
� | +2.258 |
wise | +2.245 |
Neg logit contributions | |
CCC | -3.720 |
HEAD | -3.693 |
CDC | -3.531 |
HQ | -3.527 |
INTON | -3.439 |
Token | tablets |
Token ID | 17255 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
mos | +1.429 |
rout | +1.369 |
onomy | +1.364 |
� | +1.329 |
wise | +1.316 |
Neg logit contributions | |
CCC | -1.433 |
HEAD | -1.421 |
HQ | -1.354 |
CDC | -1.350 |
INTON | -1.299 |
Token | that |
Token ID | 326 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
CCC | +1.806 |
HEAD | +1.798 |
HQ | +1.733 |
CDC | +1.706 |
INTON | +1.655 |
Neg logit contributions | |
mos | -1.465 |
onomy | -1.407 |
rout | -1.398 |
� | -1.376 |
wise | -1.329 |
Token | have |
Token ID | 423 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
CCC | +0.073 |
HEAD | +0.073 |
HQ | +0.070 |
CDC | +0.069 |
INTON | +0.068 |
Neg logit contributions | |
mos | -0.062 |
rout | -0.059 |
onomy | -0.059 |
� | -0.058 |
wise | -0.056 |
Token | come |
Token ID | 1282 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
CCC | +0.456 |
HEAD | +0.454 |
HQ | +0.437 |
CDC | +0.431 |
INTON | +0.420 |
Neg logit contributions | |
mos | -0.393 |
rout | -0.373 |
onomy | -0.370 |
� | -0.367 |
wise | -0.357 |
Token | officers |
Token ID | 3790 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
mos | +1.257 |
rout | +1.221 |
onomy | +1.197 |
� | +1.189 |
wise | +1.172 |
Neg logit contributions | |
CCC | -1.318 |
HEAD | -1.307 |
HQ | -1.247 |
CDC | -1.243 |
INTON | -1.218 |
Token | and |
Token ID | 290 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
mos | +1.414 |
rout | +1.362 |
onomy | +1.325 |
wise | +1.311 |
� | +1.310 |
Neg logit contributions | |
CCC | -1.295 |
HEAD | -1.261 |
HQ | -1.222 |
CDC | -1.212 |
INTON | -1.184 |
Token | their |
Token ID | 511 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
mos | +0.017 |
rout | +0.016 |
onomy | +0.016 |
� | +0.016 |
wise | +0.016 |
Neg logit contributions | |
CCC | -0.020 |
HEAD | -0.019 |
HQ | -0.019 |
CDC | -0.018 |
INTON | -0.018 |
Token | German |
Token ID | 2679 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
mos | +0.333 |
rout | +0.318 |
onomy | +0.314 |
� | +0.309 |
wise | +0.304 |
Neg logit contributions | |
CCC | -0.452 |
HEAD | -0.447 |
HQ | -0.431 |
CDC | -0.426 |
INTON | -0.416 |
Token | she |
Token ID | 673 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
mos | +0.189 |
onomy | +0.182 |
rout | +0.181 |
� | +0.178 |
wise | +0.173 |
Neg logit contributions | |
CCC | -0.223 |
HEAD | -0.221 |
HQ | -0.212 |
CDC | -0.209 |
INTON | -0.204 |
Token | pher |
Token ID | 17042 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
CCC | +0.173 |
HEAD | +0.172 |
HQ | +0.167 |
CDC | +0.164 |
INTON | +0.159 |
Neg logit contributions | |
mos | -0.119 |
onomy | -0.114 |
rout | -0.113 |
� | -0.112 |
wise | -0.107 |
Token | ds |
Token ID | 9310 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
mos | +2.476 |
onomy | +2.372 |
rout | +2.367 |
� | +2.283 |
wise | +2.219 |
Neg logit contributions | |
CCC | -3.718 |
HEAD | -3.690 |
HQ | -3.599 |
CDC | -3.522 |
INTON | -3.419 |
Token | who |
Token ID | 508 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
mos | +1.282 |
rout | +1.236 |
onomy | +1.235 |
� | +1.217 |
wise | +1.201 |
Neg logit contributions | |
CCC | -0.974 |
HEAD | -0.946 |
HQ | -0.911 |
CDC | -0.898 |
INTON | -0.867 |
Token | leave |
Token ID | 2666 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
mos | +0.322 |
rout | +0.309 |
onomy | +0.304 |
� | +0.298 |
wise | +0.293 |
Neg logit contributions | |
CCC | -0.446 |
HEAD | -0.443 |
HQ | -0.428 |
CDC | -0.421 |
INTON | -0.412 |
Token | their |
Token ID | 511 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
mos | +0.035 |
rout | +0.034 |
onomy | +0.033 |
� | +0.033 |
wise | +0.033 |
Neg logit contributions | |
CCC | -0.040 |
HEAD | -0.039 |
CDC | -0.038 |
HQ | -0.038 |
INTON | -0.036 |
Token | dusty |
Token ID | 36972 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
mos | +0.593 |
rout | +0.571 |
onomy | +0.558 |
wise | +0.553 |
� | +0.552 |
Neg logit contributions | |
CCC | -0.523 |
HEAD | -0.512 |
CDC | -0.490 |
HQ | -0.489 |
INTON | -0.469 |
Token | chers |
Token ID | 3533 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
CCC | +0.742 |
HEAD | +0.736 |
HQ | +0.700 |
CDC | +0.680 |
INTON | +0.649 |
Neg logit contributions | |
mos | -1.221 |
onomy | -1.188 |
rout | -1.178 |
� | -1.171 |
wise | -1.137 |
Token | celebrating |
Token ID | 17499 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
mos | +1.221 |
rout | +1.168 |
onomy | +1.150 |
� | +1.124 |
wise | +1.101 |
Neg logit contributions | |
CCC | -1.422 |
HEAD | -1.401 |
HQ | -1.361 |
CDC | -1.343 |
INTON | -1.303 |
Token | Jerusalem |
Token ID | 10843 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
mos | +0.620 |
rout | +0.589 |
onomy | +0.586 |
� | +0.581 |
wise | +0.561 |
Neg logit contributions | |
CCC | -0.740 |
HEAD | -0.734 |
HQ | -0.708 |
CDC | -0.702 |
INTON | -0.681 |
Token | Day |
Token ID | 3596 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
CCC | +0.765 |
HEAD | +0.759 |
HQ | +0.726 |
CDC | +0.709 |
INTON | +0.681 |
Neg logit contributions | |
mos | -1.006 |
onomy | -0.977 |
rout | -0.969 |
� | -0.963 |
wise | -0.931 |
Token | generally |
Token ID | 4143 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
mos | +0.434 |
rout | +0.415 |
onomy | +0.411 |
� | +0.405 |
wise | +0.391 |
Neg logit contributions | |
CCC | -0.500 |
HEAD | -0.493 |
HQ | -0.476 |
CDC | -0.469 |
INTON | -0.457 |
Token | outnumbered |
Token ID | 46673 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
mos | +0.687 |
rout | +0.654 |
onomy | +0.647 |
� | +0.630 |
wise | +0.621 |
Neg logit contributions | |
CCC | -0.826 |
HEAD | -0.809 |
HQ | -0.788 |
CDC | -0.777 |
INTON | -0.752 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
mos | +2.826 |
rout | +2.664 |
onomy | +2.545 |
� | +2.542 |
wise | +2.542 |
Neg logit contributions | |
CCC | -3.446 |
HEAD | -3.407 |
CDC | -3.296 |
HQ | -3.263 |
INTON | -3.204 |
Token | protesters |
Token ID | 9584 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
mos | +0.189 |
rout | +0.178 |
onomy | +0.178 |
� | +0.175 |
wise | +0.169 |
Neg logit contributions | |
CCC | -0.241 |
HEAD | -0.239 |
HQ | -0.231 |
CDC | -0.228 |
INTON | -0.222 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
mos | +0.196 |
rout | +0.188 |
onomy | +0.187 |
� | +0.184 |
wise | +0.180 |
Neg logit contributions | |
CCC | -0.185 |
HEAD | -0.182 |
HQ | -0.176 |
CDC | -0.173 |
INTON | -0.168 |
Token | there |
Token ID | 612 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
CCC | +0.205 |
HEAD | +0.204 |
HQ | +0.197 |
CDC | +0.194 |
INTON | +0.188 |
Neg logit contributions | |
mos | -0.170 |
rout | -0.162 |
onomy | -0.161 |
� | -0.159 |
wise | -0.154 |
Token | were |
Token ID | 547 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
mos | +0.545 |
rout | +0.522 |
onomy | +0.521 |
� | +0.518 |
wise | +0.499 |
Neg logit contributions | |
CCC | -0.604 |
HEAD | -0.598 |
HQ | -0.581 |
CDC | -0.570 |
INTON | -0.551 |
Token | neoliberal |
Token ID | 31972 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
mos | +0.382 |
rout | +0.368 |
onomy | +0.367 |
� | +0.357 |
wise | +0.353 |
Neg logit contributions | |
CCC | -0.441 |
HEAD | -0.440 |
HQ | -0.424 |
CDC | -0.415 |
INTON | -0.404 |
Token | model |
Token ID | 2746 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
HEAD | +0.027 |
CCC | +0.027 |
HQ | +0.026 |
CDC | +0.025 |
INTON | +0.025 |
Neg logit contributions | |
mos | -0.026 |
onomy | -0.025 |
rout | -0.025 |
� | -0.025 |
wise | -0.024 |
Token | only |
Token ID | 691 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
mos | +0.199 |
onomy | +0.192 |
rout | +0.191 |
� | +0.189 |
wise | +0.183 |
Neg logit contributions | |
CCC | -0.239 |
HEAD | -0.238 |
HQ | -0.229 |
CDC | -0.225 |
INTON | -0.220 |
Token | after |
Token ID | 706 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
mos | +1.413 |
rout | +1.351 |
onomy | +1.335 |
� | +1.319 |
wise | +1.309 |
Neg logit contributions | |
CCC | -1.781 |
HEAD | -1.759 |
HQ | -1.702 |
CDC | -1.684 |
INTON | -1.639 |
Token | heter |
Token ID | 14445 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
mos | +0.533 |
rout | +0.511 |
onomy | +0.507 |
� | +0.501 |
wise | +0.489 |
Neg logit contributions | |
CCC | -0.641 |
HEAD | -0.641 |
HQ | -0.613 |
CDC | -0.606 |
INTON | -0.583 |
Token | odox |
Token ID | 11430 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
mos | +0.337 |
onomy | +0.335 |
rout | +0.276 |
� | +0.270 |
odox | +0.227 |
Neg logit contributions | |
CCC | -2.410 |
HEAD | -2.408 |
HQ | -2.343 |
CDC | -2.320 |
INTON | -2.272 |
Token | policies |
Token ID | 4788 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
mos | +3.192 |
onomy | +3.109 |
rout | +3.087 |
� | +3.043 |
wise | +3.002 |
Neg logit contributions | |
HEAD | -2.927 |
CCC | -2.905 |
HQ | -2.759 |
CDC | -2.728 |
INTON | -2.600 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
mos | +0.675 |
rout | +0.646 |
onomy | +0.643 |
� | +0.637 |
wise | +0.625 |
Neg logit contributions | |
CCC | -0.754 |
HEAD | -0.747 |
HQ | -0.721 |
CDC | -0.710 |
INTON | -0.690 |
Token | which |
Token ID | 543 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
mos | +0.209 |
rout | +0.201 |
onomy | +0.199 |
� | +0.196 |
wise | +0.193 |
Neg logit contributions | |
CCC | -0.231 |
HEAD | -0.230 |
HQ | -0.221 |
CDC | -0.218 |
INTON | -0.210 |
Token | he |
Token ID | 339 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
mos | +0.118 |
rout | +0.113 |
onomy | +0.112 |
� | +0.111 |
wise | +0.108 |
Neg logit contributions | |
HEAD | -0.141 |
CCC | -0.141 |
HQ | -0.135 |
CDC | -0.132 |
INTON | -0.128 |
Token | campaigned |
Token ID | 32853 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
CCC | +0.059 |
HEAD | +0.059 |
HQ | +0.057 |
CDC | +0.056 |
INTON | +0.054 |
Neg logit contributions | |
mos | -0.055 |
rout | -0.053 |
onomy | -0.053 |
� | -0.052 |
wise | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
mos | +0.028 |
rout | +0.027 |
onomy | +0.026 |
� | +0.026 |
wise | +0.025 |
Neg logit contributions | |
CCC | -0.033 |
HEAD | -0.033 |
HQ | -0.032 |
CDC | -0.031 |
INTON | -0.030 |
Token | awful |
Token ID | 12659 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
mos | +0.185 |
rout | +0.177 |
onomy | +0.177 |
� | +0.173 |
wise | +0.169 |
Neg logit contributions | |
HEAD | -0.220 |
CCC | -0.220 |
HQ | -0.211 |
CDC | -0.208 |
INTON | -0.203 |
Token | moment |
Token ID | 2589 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
mos | +1.049 |
rout | +1.006 |
onomy | +1.002 |
� | +0.978 |
wise | +0.961 |
Neg logit contributions | |
HEAD | -1.125 |
CCC | -1.123 |
HQ | -1.077 |
CDC | -1.070 |
INTON | -1.037 |
Token | when |
Token ID | 618 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
mos | +0.303 |
onomy | +0.290 |
rout | +0.289 |
� | +0.287 |
wise | +0.277 |
Neg logit contributions | |
CCC | -0.370 |
HEAD | -0.369 |
HQ | -0.357 |
CDC | -0.349 |
INTON | -0.339 |
Token | you |
Token ID | 345 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
CCC | +0.752 |
HEAD | +0.747 |
HQ | +0.722 |
CDC | +0.707 |
INTON | +0.683 |
Neg logit contributions | |
mos | -0.682 |
onomy | -0.652 |
rout | -0.651 |
� | -0.644 |
wise | -0.623 |
Token | administer |
Token ID | 21766 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
mos | +0.327 |
rout | +0.311 |
onomy | +0.305 |
� | +0.299 |
wise | +0.295 |
Neg logit contributions | |
CCC | -0.420 |
HEAD | -0.419 |
HQ | -0.405 |
CDC | -0.397 |
INTON | -0.389 |
Token | CPR |
Token ID | 42920 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
mos | +2.888 |
rout | +2.727 |
onomy | +2.645 |
wise | +2.641 |
� | +2.611 |
Neg logit contributions | |
HEAD | -3.246 |
CCC | -3.223 |
HQ | -3.149 |
CDC | -3.084 |
INTON | -3.034 |
Token | for |
Token ID | 329 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
mos | +2.194 |
rout | +2.094 |
onomy | +2.080 |
� | +2.057 |
wise | +2.028 |
Neg logit contributions | |
CCC | -2.212 |
HEAD | -2.187 |
HQ | -2.112 |
CDC | -2.070 |
INTON | -2.016 |
Token | the |
Token ID | 262 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
mos | +0.254 |
rout | +0.243 |
onomy | +0.242 |
� | +0.240 |
wise | +0.232 |
Neg logit contributions | |
HEAD | -0.289 |
CCC | -0.289 |
HQ | -0.279 |
CDC | -0.274 |
INTON | -0.265 |
Token | first |
Token ID | 717 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
mos | +0.095 |
onomy | +0.091 |
rout | +0.091 |
� | +0.090 |
wise | +0.088 |
Neg logit contributions | |
CCC | -0.101 |
HEAD | -0.101 |
HQ | -0.097 |
CDC | -0.096 |
INTON | -0.093 |
Token | time |
Token ID | 640 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
mos | +0.128 |
onomy | +0.123 |
rout | +0.122 |
� | +0.121 |
wise | +0.118 |
Neg logit contributions | |
CCC | -0.116 |
HEAD | -0.115 |
HQ | -0.110 |
CDC | -0.108 |
INTON | -0.104 |
Token | minerals |
Token ID | 21622 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
mos | +0.102 |
onomy | +0.096 |
rout | +0.096 |
� | +0.094 |
wise | +0.093 |
Neg logit contributions | |
CCC | -0.099 |
HEAD | -0.099 |
HQ | -0.095 |
CDC | -0.094 |
INTON | -0.090 |
Token | , |
Token ID | 11 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
CCC | +0.070 |
HEAD | +0.069 |
HQ | +0.066 |
CDC | +0.066 |
INTON | +0.063 |
Neg logit contributions | |
mos | -0.074 |
onomy | -0.071 |
rout | -0.071 |
� | -0.069 |
wise | -0.068 |
Token | especially |
Token ID | 2592 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
CCC | +0.582 |
HEAD | +0.578 |
HQ | +0.558 |
CDC | +0.549 |
INTON | +0.532 |
Neg logit contributions | |
mos | -0.507 |
onomy | -0.483 |
rout | -0.482 |
� | -0.472 |
wise | -0.462 |
Token | since |
Token ID | 1201 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
CCC | +0.555 |
HEAD | +0.551 |
HQ | +0.531 |
CDC | +0.523 |
INTON | +0.505 |
Neg logit contributions | |
mos | -0.535 |
onomy | -0.510 |
rout | -0.508 |
� | -0.500 |
wise | -0.486 |
Token | ep |
Token ID | 2462 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
mos | +1.068 |
rout | +1.007 |
onomy | +0.990 |
� | +0.971 |
wise | +0.964 |
Neg logit contributions | |
CCC | -1.281 |
HEAD | -1.267 |
HQ | -1.223 |
CDC | -1.209 |
INTON | -1.174 |
Token | oxy |
Token ID | 23536 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
CCC | +0.550 |
HEAD | +0.546 |
HQ | +0.516 |
CDC | +0.505 |
INTON | +0.484 |
Neg logit contributions | |
mos | -0.877 |
onomy | -0.855 |
rout | -0.843 |
� | -0.835 |
wise | -0.815 |
Token | resin |
Token ID | 36536 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
mos | +2.731 |
rout | +2.616 |
onomy | +2.546 |
wise | +2.459 |
� | +2.453 |
Neg logit contributions | |
CCC | -3.401 |
HEAD | -3.355 |
CDC | -3.224 |
HQ | -3.214 |
INTON | -3.136 |
Token | is |
Token ID | 318 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
mos | +0.864 |
rout | +0.823 |
onomy | +0.810 |
� | +0.788 |
wise | +0.781 |
Neg logit contributions | |
CCC | -1.069 |
HEAD | -1.056 |
HQ | -1.012 |
CDC | -1.010 |
INTON | -0.981 |
Token | " |
Token ID | 366 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
mos | +0.120 |
rout | +0.115 |
onomy | +0.113 |
� | +0.112 |
wise | +0.110 |
Neg logit contributions | |
CCC | -0.141 |
HEAD | -0.140 |
HQ | -0.135 |
CDC | -0.134 |
INTON | -0.130 |
Token | res |
Token ID | 411 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
CCC | +0.630 |
HEAD | +0.624 |
HQ | +0.601 |
CDC | +0.590 |
INTON | +0.574 |
Neg logit contributions | |
mos | -0.633 |
onomy | -0.613 |
rout | -0.604 |
� | -0.601 |
wise | -0.579 |
Token | il |
Token ID | 346 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
mos | +0.874 |
onomy | +0.846 |
rout | +0.834 |
� | +0.815 |
wise | +0.797 |
Neg logit contributions | |
CCC | -0.936 |
HEAD | -0.931 |
HQ | -0.892 |
CDC | -0.883 |
INTON | -0.848 |
Token | that |
Token ID | 326 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
mos | +0.799 |
rout | +0.763 |
onomy | +0.754 |
� | +0.745 |
wise | +0.730 |
Neg logit contributions | |
CCC | -0.916 |
HEAD | -0.913 |
HQ | -0.876 |
CDC | -0.865 |
INTON | -0.848 |
Token | a |
Token ID | 257 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
mos | +0.402 |
rout | +0.383 |
onomy | +0.380 |
� | +0.377 |
wise | +0.367 |
Neg logit contributions | |
CCC | -0.448 |
HEAD | -0.446 |
HQ | -0.428 |
CDC | -0.422 |
INTON | -0.415 |
Token | profile |
Token ID | 7034 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
mos | +0.347 |
rout | +0.330 |
onomy | +0.328 |
� | +0.326 |
wise | +0.317 |
Neg logit contributions | |
CCC | -0.424 |
HEAD | -0.417 |
HQ | -0.405 |
CDC | -0.399 |
INTON | -0.391 |
Token | will |
Token ID | 481 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
mos | +0.921 |
rout | +0.892 |
onomy | +0.882 |
� | +0.867 |
wise | +0.859 |
Neg logit contributions | |
CCC | -1.086 |
HEAD | -1.076 |
HQ | -1.038 |
CDC | -1.032 |
INTON | -1.013 |
Token | e |
Token ID | 304 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
mos | +0.116 |
rout | +0.111 |
onomy | +0.109 |
� | +0.107 |
wise | +0.106 |
Neg logit contributions | |
CCC | -0.159 |
HEAD | -0.158 |
HQ | -0.154 |
CDC | -0.150 |
INTON | -0.147 |
Token | ke |
Token ID | 365 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
mos | +0.083 |
onomy | +0.080 |
� | +0.079 |
rout | +0.079 |
wise | +0.076 |
Neg logit contributions | |
CCC | -0.071 |
HEAD | -0.071 |
HQ | -0.068 |
CDC | -0.066 |
INTON | -0.065 |
Token | out |
Token ID | 503 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
mos | +2.571 |
rout | +2.433 |
� | +2.427 |
onomy | +2.420 |
wise | +2.329 |
Neg logit contributions | |
CCC | -3.495 |
HEAD | -3.466 |
HQ | -3.318 |
CDC | -3.314 |
INTON | -3.226 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
mos | +0.712 |
rout | +0.679 |
onomy | +0.673 |
� | +0.670 |
wise | +0.648 |
Neg logit contributions | |
CCC | -0.885 |
HEAD | -0.878 |
HQ | -0.849 |
CDC | -0.842 |
INTON | -0.816 |
Token | bit |
Token ID | 1643 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
mos | +0.241 |
rout | +0.229 |
onomy | +0.229 |
� | +0.227 |
wise | +0.217 |
Neg logit contributions | |
CCC | -0.335 |
HEAD | -0.330 |
HQ | -0.321 |
CDC | -0.317 |
INTON | -0.309 |
Token | more |
Token ID | 517 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
mos | +0.912 |
rout | +0.871 |
� | +0.861 |
onomy | +0.859 |
wise | +0.831 |
Neg logit contributions | |
CCC | -1.169 |
HEAD | -1.148 |
HQ | -1.116 |
CDC | -1.109 |
INTON | -1.081 |
Token | performance |
Token ID | 2854 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
mos | +0.055 |
rout | +0.053 |
onomy | +0.052 |
� | +0.051 |
wise | +0.050 |
Neg logit contributions | |
CCC | -0.064 |
HEAD | -0.063 |
HQ | -0.061 |
CDC | -0.061 |
INTON | -0.059 |
Token | release |
Token ID | 2650 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
CCC | +0.277 |
HEAD | +0.276 |
HQ | +0.265 |
CDC | +0.263 |
INTON | +0.256 |
Neg logit contributions | |
mos | -0.236 |
onomy | -0.225 |
rout | -0.225 |
� | -0.222 |
wise | -0.216 |
Token | , |
Token ID | 11 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
CCC | +0.089 |
HEAD | +0.088 |
HQ | +0.084 |
CDC | +0.083 |
INTON | +0.080 |
Neg logit contributions | |
mos | -0.112 |
onomy | -0.108 |
rout | -0.107 |
� | -0.106 |
wise | -0.104 |
Token | with |
Token ID | 351 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
CCC | +0.677 |
HEAD | +0.670 |
HQ | +0.646 |
CDC | +0.638 |
INTON | +0.622 |
Neg logit contributions | |
mos | -0.641 |
rout | -0.613 |
onomy | -0.609 |
� | -0.604 |
wise | -0.592 |
Token | a |
Token ID | 257 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
CCC | +0.250 |
HEAD | +0.248 |
HQ | +0.240 |
CDC | +0.238 |
INTON | +0.231 |
Neg logit contributions | |
mos | -0.213 |
rout | -0.203 |
onomy | -0.201 |
� | -0.200 |
wise | -0.196 |
Token | second |
Token ID | 1218 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
CCC | +0.410 |
HEAD | +0.404 |
HQ | +0.392 |
CDC | +0.389 |
INTON | +0.379 |
Neg logit contributions | |
mos | -0.330 |
rout | -0.316 |
onomy | -0.313 |
� | -0.306 |
wise | -0.302 |
Token | print |
Token ID | 3601 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
CCC | +0.549 |
HEAD | +0.545 |
HQ | +0.526 |
CDC | +0.519 |
INTON | +0.506 |
Neg logit contributions | |
mos | -0.458 |
onomy | -0.438 |
rout | -0.437 |
� | -0.429 |
wise | -0.417 |
Token | due |
Token ID | 2233 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
CCC | +2.532 |
HEAD | +2.519 |
HQ | +2.435 |
CDC | +2.386 |
INTON | +2.309 |
Neg logit contributions | |
mos | -2.023 |
onomy | -1.948 |
rout | -1.920 |
� | -1.910 |
wise | -1.825 |
Token | in |
Token ID | 287 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
CCC | +1.175 |
HEAD | +1.168 |
HQ | +1.127 |
CDC | +1.104 |
INTON | +1.069 |
Neg logit contributions | |
mos | -1.068 |
onomy | -1.030 |
rout | -1.019 |
� | -1.011 |
wise | -0.973 |
Token | stores |
Token ID | 7000 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
CCC | +0.351 |
HEAD | +0.349 |
HQ | +0.338 |
CDC | +0.334 |
INTON | +0.325 |
Neg logit contributions | |
mos | -0.233 |
rout | -0.220 |
onomy | -0.220 |
� | -0.215 |
wise | -0.210 |
Token | on |
Token ID | 319 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
CCC | +0.230 |
HEAD | +0.229 |
HQ | +0.221 |
CDC | +0.218 |
INTON | +0.212 |
Neg logit contributions | |
mos | -0.213 |
onomy | -0.204 |
rout | -0.203 |
� | -0.199 |
wise | -0.195 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
CCC | +0.324 |
HEAD | +0.324 |
HQ | +0.314 |
CDC | +0.310 |
INTON | +0.306 |
Neg logit contributions | |
mos | -0.160 |
onomy | -0.150 |
rout | -0.150 |
� | -0.144 |
wise | -0.141 |
Token | programme |
Token ID | 11383 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
CCC | +1.127 |
HEAD | +1.119 |
HQ | +1.076 |
CDC | +1.054 |
INTON | +1.015 |
Neg logit contributions | |
mos | -1.265 |
onomy | -1.225 |
rout | -1.216 |
� | -1.201 |
wise | -1.165 |
Token | , |
Token ID | 11 |
Feature activation | +5.59e-02 |
Pos logit contributions | |
CCC | +0.401 |
HEAD | +0.399 |
HQ | +0.383 |
CDC | +0.377 |
INTON | +0.365 |
Neg logit contributions | |
mos | -0.431 |
onomy | -0.415 |
rout | -0.415 |
� | -0.406 |
wise | -0.398 |
Token | designed |
Token ID | 3562 |
Feature activation | -4.98e-03 |
Pos logit contributions | |
CCC | +0.108 |
HEAD | +0.108 |
HQ | +0.104 |
CDC | +0.103 |
INTON | +0.100 |
Neg logit contributions | |
mos | -0.088 |
rout | -0.085 |
onomy | -0.084 |
� | -0.082 |
wise | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
mos | +0.008 |
onomy | +0.007 |
rout | +0.007 |
� | +0.007 |
wise | +0.007 |
Neg logit contributions | |
CCC | -0.010 |
HEAD | -0.010 |
HQ | -0.009 |
CDC | -0.009 |
INTON | -0.009 |
Token | stimulate |
Token ID | 26020 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
CCC | +0.152 |
HEAD | +0.152 |
HQ | +0.147 |
CDC | +0.144 |
INTON | +0.141 |
Neg logit contributions | |
mos | -0.105 |
rout | -0.102 |
onomy | -0.099 |
� | -0.098 |
wise | -0.096 |
Token | lending |
Token ID | 20983 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
mos | +0.114 |
rout | +0.110 |
onomy | +0.110 |
� | +0.108 |
wise | +0.105 |
Neg logit contributions | |
CCC | -0.117 |
HEAD | -0.117 |
HQ | -0.111 |
CDC | -0.110 |
INTON | -0.106 |
Token | in |
Token ID | 287 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
CCC | +1.870 |
HEAD | +1.857 |
HQ | +1.782 |
CDC | +1.747 |
INTON | +1.682 |
Neg logit contributions | |
mos | -2.117 |
onomy | -2.046 |
rout | -2.035 |
� | -2.010 |
wise | -1.951 |
Token | the |
Token ID | 262 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
CCC | +0.475 |
HEAD | +0.473 |
HQ | +0.455 |
CDC | +0.450 |
INTON | +0.434 |
Neg logit contributions | |
mos | -0.424 |
rout | -0.408 |
onomy | -0.406 |
� | -0.400 |
wise | -0.389 |
Token | economy |
Token ID | 3773 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
CCC | +0.148 |
HEAD | +0.148 |
HQ | +0.142 |
CDC | +0.140 |
INTON | +0.135 |
Neg logit contributions | |
mos | -0.138 |
rout | -0.133 |
onomy | -0.133 |
� | -0.131 |
wise | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
CCC | +0.772 |
HEAD | +0.767 |
HQ | +0.733 |
CDC | +0.717 |
INTON | +0.688 |
Neg logit contributions | |
mos | -1.029 |
onomy | -0.998 |
rout | -0.991 |
� | -0.984 |
wise | -0.955 |
Token | beyond |
Token ID | 3675 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
CCC | +0.474 |
HEAD | +0.473 |
HQ | +0.455 |
CDC | +0.447 |
INTON | +0.433 |
Neg logit contributions | |
mos | -0.426 |
rout | -0.409 |
onomy | -0.409 |
� | -0.401 |
wise | -0.391 |
Token | multiple |
Token ID | 3294 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
CCC | +0.167 |
HEAD | +0.167 |
HQ | +0.159 |
CDC | +0.157 |
INTON | +0.153 |
Neg logit contributions | |
mos | -0.141 |
rout | -0.136 |
onomy | -0.135 |
� | -0.133 |
wise | -0.130 |
Token | sides |
Token ID | 5389 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
CCC | +0.177 |
HEAD | +0.176 |
HQ | +0.168 |
CDC | +0.166 |
INTON | +0.161 |
Neg logit contributions | |
mos | -0.155 |
onomy | -0.149 |
rout | -0.149 |
� | -0.146 |
wise | -0.143 |
Token | of |
Token ID | 286 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
mos | +0.054 |
onomy | +0.052 |
rout | +0.052 |
� | +0.051 |
wise | +0.049 |
Neg logit contributions | |
CCC | -0.070 |
HEAD | -0.069 |
HQ | -0.067 |
CDC | -0.066 |
INTON | -0.064 |
Token | important |
Token ID | 1593 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
mos | +0.021 |
onomy | +0.020 |
rout | +0.020 |
� | +0.019 |
wise | +0.019 |
Neg logit contributions | |
CCC | -0.024 |
HEAD | -0.024 |
HQ | -0.023 |
CDC | -0.023 |
INTON | -0.022 |
Token | issues |
Token ID | 2428 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
CCC | +0.326 |
HEAD | +0.325 |
HQ | +0.313 |
CDC | +0.309 |
INTON | +0.301 |
Neg logit contributions | |
mos | -0.208 |
onomy | -0.199 |
rout | -0.197 |
� | -0.193 |
wise | -0.187 |
Token | facing |
Token ID | 6476 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
mos | +1.418 |
onomy | +1.372 |
rout | +1.361 |
� | +1.349 |
wise | +1.328 |
Neg logit contributions | |
CCC | -1.308 |
HEAD | -1.298 |
HQ | -1.234 |
CDC | -1.219 |
INTON | -1.197 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
CCC | +2.185 |
HEAD | +2.173 |
HQ | +2.096 |
CDC | +2.054 |
INTON | +1.987 |
Neg logit contributions | |
mos | -1.959 |
onomy | -1.889 |
rout | -1.869 |
� | -1.856 |
wise | -1.785 |
Token | world |
Token ID | 995 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
CCC | +0.258 |
HEAD | +0.258 |
HQ | +0.248 |
CDC | +0.244 |
INTON | +0.236 |
Neg logit contributions | |
mos | -0.223 |
onomy | -0.215 |
rout | -0.214 |
� | -0.212 |
wise | -0.205 |
Token | , |
Token ID | 11 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
CCC | +0.910 |
HEAD | +0.903 |
HQ | +0.867 |
CDC | +0.849 |
INTON | +0.819 |
Neg logit contributions | |
mos | -1.050 |
onomy | -1.017 |
rout | -1.007 |
� | -1.000 |
wise | -0.971 |
Token | be |
Token ID | 307 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
CCC | +0.594 |
HEAD | +0.593 |
HQ | +0.568 |
CDC | +0.558 |
INTON | +0.540 |
Neg logit contributions | |
mos | -0.556 |
onomy | -0.536 |
rout | -0.533 |
� | -0.526 |
wise | -0.512 |
Token | that |
Token ID | 326 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
mos | +0.482 |
onomy | +0.465 |
rout | +0.460 |
� | +0.457 |
wise | +0.442 |
Neg logit contributions | |
CCC | -0.577 |
HEAD | -0.574 |
HQ | -0.554 |
CDC | -0.546 |
INTON | -0.529 |
Token | ( |
Token ID | 357 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
CCC | +0.102 |
HEAD | +0.102 |
HQ | +0.098 |
CDC | +0.096 |
INTON | +0.093 |
Neg logit contributions | |
mos | -0.086 |
onomy | -0.083 |
rout | -0.082 |
� | -0.081 |
wise | -0.078 |
Token | 1997 |
Token ID | 8309 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
CCC | +0.049 |
HEAD | +0.049 |
HQ | +0.047 |
CDC | +0.046 |
INTON | +0.045 |
Neg logit contributions | |
mos | -0.044 |
onomy | -0.043 |
rout | -0.042 |
� | -0.042 |
wise | -0.040 |
Token | ). |
Token ID | 6739 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
CCC | +0.064 |
HEAD | +0.063 |
HQ | +0.060 |
CDC | +0.058 |
INTON | +0.056 |
Neg logit contributions | |
mos | -0.104 |
onomy | -0.101 |
rout | -0.100 |
� | -0.099 |
wise | -0.096 |
Token | The |
Token ID | 383 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
mos | +0.054 |
onomy | +0.052 |
rout | +0.052 |
� | +0.052 |
wise | +0.050 |
Neg logit contributions | |
CCC | -0.055 |
HEAD | -0.055 |
HQ | -0.053 |
CDC | -0.052 |
INTON | -0.050 |
Token | familial |
Token ID | 48376 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
CCC | +0.546 |
HEAD | +0.544 |
HQ | +0.524 |
CDC | +0.513 |
INTON | +0.497 |
Neg logit contributions | |
mos | -0.479 |
onomy | -0.463 |
rout | -0.459 |
� | -0.454 |
wise | -0.438 |
Token | transmission |
Token ID | 11478 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
CCC | +2.458 |
HEAD | +2.443 |
HQ | +2.356 |
CDC | +2.310 |
INTON | +2.236 |
Neg logit contributions | |
mos | -2.177 |
onomy | -2.099 |
rout | -2.079 |
� | -2.058 |
wise | -1.983 |
Token | of |
Token ID | 286 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
CCC | +2.241 |
HEAD | +2.228 |
HQ | +2.152 |
CDC | +2.119 |
INTON | +2.043 |
Neg logit contributions | |
mos | -1.831 |
onomy | -1.756 |
rout | -1.735 |
� | -1.723 |
wise | -1.649 |
Token | criminal |
Token ID | 4301 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
CCC | +0.148 |
HEAD | +0.148 |
HQ | +0.143 |
CDC | +0.141 |
INTON | +0.137 |
Neg logit contributions | |
mos | -0.094 |
rout | -0.089 |
onomy | -0.089 |
� | -0.088 |
wise | -0.084 |
Token | convictions |
Token ID | 19131 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
CCC | +1.184 |
HEAD | +1.176 |
HQ | +1.136 |
CDC | +1.116 |
INTON | +1.082 |
Neg logit contributions | |
mos | -0.915 |
onomy | -0.879 |
rout | -0.870 |
� | -0.861 |
wise | -0.827 |
Token | . |
Token ID | 764 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
mos | +0.126 |
onomy | +0.122 |
rout | +0.122 |
� | +0.120 |
wise | +0.117 |
Neg logit contributions | |
CCC | -0.115 |
HEAD | -0.114 |
HQ | -0.109 |
CDC | -0.107 |
INTON | -0.104 |
Token | Crim |
Token ID | 9822 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
CCC | +0.546 |
HEAD | +0.546 |
HQ | +0.523 |
CDC | +0.512 |
INTON | +0.497 |
Neg logit contributions | |
mos | -0.529 |
onomy | -0.512 |
� | -0.506 |
rout | -0.506 |
wise | -0.484 |
Token | Americans |
Token ID | 3399 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
CCC | +1.258 |
HEAD | +1.251 |
HQ | +1.207 |
CDC | +1.182 |
INTON | +1.144 |
Neg logit contributions | |
mos | -1.128 |
onomy | -1.088 |
rout | -1.076 |
� | -1.069 |
wise | -1.026 |
Token | FX |
Token ID | 19534 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
CCC | +0.791 |
HEAD | +0.787 |
HQ | +0.757 |
CDC | +0.744 |
INTON | +0.725 |
Neg logit contributions | |
mos | -0.714 |
onomy | -0.688 |
rout | -0.679 |
� | -0.674 |
wise | -0.651 |
Token |
|
Token ID | 198 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
mos | +0.167 |
onomy | +0.161 |
rout | +0.158 |
� | +0.157 |
wise | +0.152 |
Neg logit contributions | |
HEAD | -0.205 |
CCC | -0.205 |
HQ | -0.196 |
CDC | -0.194 |
INTON | -0.189 |
Token |
|
Token ID | 198 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
CCC | +1.196 |
HEAD | +1.188 |
HQ | +1.149 |
CDC | +1.141 |
INTON | +1.117 |
Neg logit contributions | |
mos | -0.715 |
onomy | -0.685 |
rout | -0.677 |
� | -0.658 |
wise | -0.639 |
Token | Out |
Token ID | 7975 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
CCC | +0.695 |
HEAD | +0.690 |
HQ | +0.662 |
CDC | +0.646 |
INTON | +0.629 |
Neg logit contributions | |
mos | -0.816 |
onomy | -0.801 |
rout | -0.788 |
� | -0.783 |
wise | -0.754 |
Token | standing |
Token ID | 5646 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
CCC | +0.676 |
HEAD | +0.673 |
HQ | +0.651 |
CDC | +0.640 |
INTON | +0.621 |
Neg logit contributions | |
mos | -0.480 |
onomy | -0.460 |
rout | -0.455 |
� | -0.451 |
wise | -0.431 |
Token | Achievement |
Token ID | 45511 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
CCC | +2.210 |
HEAD | +2.195 |
HQ | +2.121 |
CDC | +2.070 |
INTON | +2.006 |
Neg logit contributions | |
mos | -1.978 |
onomy | -1.908 |
rout | -1.884 |
� | -1.875 |
wise | -1.793 |
Token | in |
Token ID | 287 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
CCC | +0.073 |
HEAD | +0.072 |
HQ | +0.070 |
CDC | +0.068 |
INTON | +0.065 |
Neg logit contributions | |
mos | -0.083 |
onomy | -0.081 |
rout | -0.080 |
� | -0.079 |
wise | -0.077 |
Token | Comedy |
Token ID | 22329 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
CCC | +0.951 |
HEAD | +0.946 |
HQ | +0.914 |
CDC | +0.899 |
INTON | +0.871 |
Neg logit contributions | |
mos | -0.731 |
onomy | -0.703 |
rout | -0.694 |
� | -0.688 |
wise | -0.660 |
Token |
|
Token ID | 198 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
CCC | +0.479 |
HEAD | +0.477 |
HQ | +0.461 |
CDC | +0.453 |
INTON | +0.439 |
Neg logit contributions | |
mos | -0.366 |
onomy | -0.352 |
rout | -0.348 |
� | -0.345 |
wise | -0.330 |
Token |
|
Token ID | 198 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
CCC | +1.135 |
HEAD | +1.126 |
HQ | +1.090 |
CDC | +1.079 |
INTON | +1.056 |
Neg logit contributions | |
mos | -0.685 |
onomy | -0.657 |
rout | -0.648 |
� | -0.632 |
wise | -0.614 |
Token | for |
Token ID | 329 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
mos | +0.440 |
onomy | +0.423 |
rout | +0.419 |
� | +0.410 |
wise | +0.403 |
Neg logit contributions | |
CCC | -0.407 |
HEAD | -0.404 |
HQ | -0.387 |
CDC | -0.381 |
INTON | -0.374 |
Token | evidence |
Token ID | 2370 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
mos | +0.152 |
rout | +0.145 |
onomy | +0.144 |
� | +0.143 |
wise | +0.140 |
Neg logit contributions | |
CCC | -0.149 |
HEAD | -0.148 |
HQ | -0.144 |
CDC | -0.140 |
INTON | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
mos | +0.911 |
rout | +0.865 |
onomy | +0.864 |
� | +0.859 |
wise | +0.840 |
Neg logit contributions | |
CCC | -0.913 |
HEAD | -0.906 |
HQ | -0.873 |
CDC | -0.864 |
INTON | -0.840 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
CCC | +0.146 |
HEAD | +0.145 |
HQ | +0.140 |
CDC | +0.137 |
INTON | +0.134 |
Neg logit contributions | |
mos | -0.116 |
onomy | -0.112 |
� | -0.110 |
rout | -0.110 |
wise | -0.105 |
Token | The |
Token ID | 464 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
CCC | +0.504 |
HEAD | +0.497 |
HQ | +0.477 |
CDC | +0.463 |
INTON | +0.451 |
Neg logit contributions | |
mos | -0.664 |
onomy | -0.650 |
� | -0.639 |
rout | -0.638 |
wise | -0.612 |
Token | cookies |
Token ID | 14746 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
mos | +0.053 |
onomy | +0.051 |
rout | +0.051 |
� | +0.050 |
wise | +0.049 |
Neg logit contributions | |
CCC | -0.058 |
HEAD | -0.057 |
HQ | -0.055 |
CDC | -0.054 |
INTON | -0.052 |
Token | baked |
Token ID | 22979 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
CCC | +0.837 |
HEAD | +0.832 |
HQ | +0.800 |
CDC | +0.787 |
INTON | +0.765 |
Neg logit contributions | |
mos | -0.718 |
onomy | -0.696 |
rout | -0.686 |
� | -0.679 |
wise | -0.654 |
Token | quickly |
Token ID | 2952 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
mos | +0.410 |
onomy | +0.396 |
rout | +0.392 |
� | +0.388 |
wise | +0.378 |
Neg logit contributions | |
CCC | -0.398 |
HEAD | -0.395 |
HQ | -0.378 |
CDC | -0.373 |
INTON | -0.359 |
Token | at |
Token ID | 379 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
CCC | +0.357 |
HEAD | +0.354 |
HQ | +0.339 |
CDC | +0.335 |
INTON | +0.324 |
Neg logit contributions | |
mos | -0.350 |
onomy | -0.338 |
rout | -0.335 |
� | -0.328 |
wise | -0.321 |
Token | 375 |
Token ID | 29414 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
mos | +0.252 |
onomy | +0.241 |
rout | +0.241 |
� | +0.236 |
wise | +0.231 |
Neg logit contributions | |
CCC | -0.274 |
HEAD | -0.274 |
HQ | -0.262 |
CDC | -0.260 |
INTON | -0.252 |
Token | , |
Token ID | 11 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
mos | +1.305 |
onomy | +1.247 |
� | +1.237 |
rout | +1.234 |
wise | +1.191 |
Neg logit contributions | |
HEAD | -1.263 |
CCC | -1.254 |
HQ | -1.186 |
CDC | -1.166 |
INTON | -1.149 |
Token | , |
Token ID | 11 |
Feature activation | -8.05e-03 |
Pos logit contributions | |
CCC | +0.309 |
HEAD | +0.304 |
HQ | +0.297 |
CDC | +0.292 |
INTON | +0.284 |
Neg logit contributions | |
mos | -0.287 |
onomy | -0.276 |
rout | -0.275 |
� | -0.270 |
wise | -0.266 |
Token | allowing |
Token ID | 5086 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
mos | +0.013 |
rout | +0.013 |
onomy | +0.013 |
� | +0.013 |
wise | +0.012 |
Neg logit contributions | |
CCC | -0.015 |
HEAD | -0.015 |
HQ | -0.014 |
CDC | -0.014 |
INTON | -0.014 |
Token | corner |
Token ID | 5228 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
CCC | +1.020 |
HEAD | +1.013 |
HQ | +0.983 |
CDC | +0.966 |
INTON | +0.939 |
Neg logit contributions | |
mos | -0.747 |
onomy | -0.714 |
rout | -0.712 |
� | -0.701 |
wise | -0.677 |
Token | backs |
Token ID | 10146 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
mos | +2.155 |
onomy | +2.108 |
rout | +2.106 |
� | +2.092 |
wise | +2.055 |
Neg logit contributions | |
CCC | -0.561 |
HEAD | -0.550 |
HQ | -0.503 |
CDC | -0.488 |
INTON | -0.444 |
Token | to |
Token ID | 284 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
CCC | +0.300 |
HEAD | +0.298 |
HQ | +0.288 |
CDC | +0.283 |
INTON | +0.275 |
Neg logit contributions | |
mos | -0.232 |
onomy | -0.222 |
rout | -0.220 |
� | -0.218 |
wise | -0.210 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
mos | +0.250 |
rout | +0.242 |
onomy | +0.233 |
� | +0.228 |
wise | +0.228 |
Neg logit contributions | |
CCC | -0.346 |
HEAD | -0.344 |
HQ | -0.334 |
CDC | -0.328 |
INTON | -0.320 |
Token | up |
Token ID | 510 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
CCC | +0.020 |
HEAD | +0.020 |
HQ | +0.019 |
CDC | +0.019 |
INTON | +0.018 |
Neg logit contributions | |
mos | -0.018 |
rout | -0.017 |
onomy | -0.017 |
� | -0.017 |
wise | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
mos | +0.074 |
rout | +0.072 |
onomy | +0.070 |
� | +0.070 |
wise | +0.068 |
Neg logit contributions | |
CCC | -0.087 |
HEAD | -0.086 |
HQ | -0.083 |
CDC | -0.082 |
INTON | -0.080 |
Token | cushion |
Token ID | 33579 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
mos | +0.121 |
rout | +0.117 |
onomy | +0.114 |
� | +0.113 |
wise | +0.111 |
Neg logit contributions | |
CCC | -0.150 |
HEAD | -0.149 |
HQ | -0.144 |
CDC | -0.142 |
INTON | -0.138 |
Token | he |
Token ID | 339 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
mos | +0.625 |
rout | +0.606 |
onomy | +0.603 |
� | +0.596 |
wise | +0.580 |
Neg logit contributions | |
CCC | -0.659 |
HEAD | -0.651 |
HQ | -0.634 |
CDC | -0.623 |
INTON | -0.606 |
Token | should |
Token ID | 815 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
CCC | +0.128 |
HEAD | +0.127 |
HQ | +0.124 |
CDC | +0.120 |
INTON | +0.118 |
Neg logit contributions | |
mos | -0.109 |
onomy | -0.105 |
rout | -0.104 |
� | -0.104 |
wise | -0.099 |
Token | next |
Token ID | 1306 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
CCC | +0.007 |
HEAD | +0.007 |
HQ | +0.007 |
CDC | +0.006 |
INTON | +0.006 |
Neg logit contributions | |
mos | -0.006 |
onomy | -0.005 |
rout | -0.005 |
� | -0.005 |
wise | -0.005 |
Token | month |
Token ID | 1227 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
CCC | +0.428 |
HEAD | +0.426 |
HQ | +0.410 |
CDC | +0.405 |
INTON | +0.392 |
Neg logit contributions | |
mos | -0.378 |
onomy | -0.360 |
rout | -0.360 |
� | -0.355 |
wise | -0.344 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
mos | +0.561 |
onomy | +0.541 |
� | +0.538 |
rout | +0.537 |
wise | +0.520 |
Neg logit contributions | |
CCC | -0.462 |
HEAD | -0.461 |
HQ | -0.441 |
CDC | -0.434 |
INTON | -0.423 |
Token | I |
Token ID | 314 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
CCC | +0.065 |
HEAD | +0.064 |
HQ | +0.062 |
CDC | +0.061 |
INTON | +0.059 |
Neg logit contributions | |
mos | -0.063 |
onomy | -0.061 |
� | -0.060 |
rout | -0.060 |
wise | -0.058 |
Token | see |
Token ID | 766 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
mos | +0.416 |
onomy | +0.398 |
rout | +0.395 |
� | +0.388 |
wise | +0.380 |
Neg logit contributions | |
CCC | -0.553 |
HEAD | -0.553 |
HQ | -0.532 |
CDC | -0.524 |
INTON | -0.516 |
Token | no |
Token ID | 645 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
mos | +0.862 |
rout | +0.820 |
� | +0.802 |
onomy | +0.799 |
wise | +0.793 |
Neg logit contributions | |
CCC | -1.021 |
HEAD | -1.019 |
HQ | -0.983 |
CDC | -0.978 |
INTON | -0.956 |
Token | other |
Token ID | 584 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
CCC | +0.589 |
HEAD | +0.586 |
HQ | +0.565 |
CDC | +0.559 |
INTON | +0.543 |
Neg logit contributions | |
mos | -0.455 |
rout | -0.434 |
onomy | -0.430 |
� | -0.424 |
wise | -0.416 |
Token | alternative |
Token ID | 5559 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
CCC | +0.388 |
HEAD | +0.385 |
HQ | +0.368 |
CDC | +0.365 |
INTON | +0.353 |
Neg logit contributions | |
mos | -0.366 |
rout | -0.351 |
onomy | -0.348 |
� | -0.342 |
wise | -0.339 |
Token | too |
Token ID | 1165 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
mos | +0.410 |
onomy | +0.394 |
rout | +0.394 |
� | +0.389 |
wise | +0.384 |
Neg logit contributions | |
CCC | -0.363 |
HEAD | -0.360 |
HQ | -0.343 |
CDC | -0.339 |
INTON | -0.328 |
Token | , |
Token ID | 11 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
mos | +0.929 |
onomy | +0.892 |
rout | +0.890 |
� | +0.887 |
wise | +0.867 |
Neg logit contributions | |
CCC | -0.780 |
HEAD | -0.773 |
HQ | -0.744 |
CDC | -0.732 |
INTON | -0.708 |
Token | but |
Token ID | 475 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
mos | +0.099 |
onomy | +0.095 |
rout | +0.094 |
� | +0.093 |
wise | +0.091 |
Neg logit contributions | |
CCC | -0.103 |
HEAD | -0.103 |
HQ | -0.099 |
CDC | -0.098 |
INTON | -0.095 |
Token | market |
Token ID | 1910 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
CCC | +0.075 |
HEAD | +0.075 |
HQ | +0.071 |
CDC | +0.070 |
INTON | +0.068 |
Neg logit contributions | |
mos | -0.062 |
rout | -0.060 |
onomy | -0.060 |
� | -0.059 |
wise | -0.057 |
Token | thinks |
Token ID | 6834 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
mos | +0.780 |
rout | +0.753 |
onomy | +0.747 |
� | +0.727 |
wise | +0.716 |
Neg logit contributions | |
HEAD | -1.040 |
CCC | -1.037 |
HQ | -0.995 |
CDC | -0.986 |
INTON | -0.956 |
Token | is |
Token ID | 318 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
CCC | +0.406 |
HEAD | +0.404 |
HQ | +0.389 |
CDC | +0.383 |
INTON | +0.371 |
Neg logit contributions | |
mos | -0.350 |
onomy | -0.337 |
rout | -0.335 |
� | -0.332 |
wise | -0.321 |
Token | too |
Token ID | 1165 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
CCC | +0.195 |
HEAD | +0.194 |
HQ | +0.188 |
CDC | +0.186 |
INTON | +0.181 |
Neg logit contributions | |
mos | -0.150 |
rout | -0.143 |
onomy | -0.142 |
� | -0.141 |
wise | -0.139 |
Token | high |
Token ID | 1029 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
mos | +0.300 |
rout | +0.286 |
onomy | +0.284 |
� | +0.282 |
wise | +0.275 |
Neg logit contributions | |
CCC | -0.397 |
HEAD | -0.393 |
HQ | -0.380 |
CDC | -0.379 |
INTON | -0.368 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
CCC | +0.957 |
HEAD | +0.951 |
HQ | +0.911 |
CDC | +0.890 |
INTON | +0.855 |
Neg logit contributions | |
mos | -1.192 |
onomy | -1.156 |
rout | -1.145 |
� | -1.138 |
wise | -1.102 |
Token | it |
Token ID | 340 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
CCC | +0.228 |
HEAD | +0.227 |
HQ | +0.218 |
CDC | +0.215 |
INTON | +0.208 |
Neg logit contributions | |
mos | -0.201 |
onomy | -0.194 |
rout | -0.194 |
� | -0.191 |
wise | -0.185 |
Token | will |
Token ID | 481 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
CCC | +0.344 |
HEAD | +0.342 |
HQ | +0.331 |
CDC | +0.325 |
INTON | +0.317 |
Neg logit contributions | |
mos | -0.263 |
rout | -0.252 |
onomy | -0.247 |
� | -0.244 |
wise | -0.238 |
Token | have |
Token ID | 423 |
Feature activation | -2.88e-04 |
Pos logit contributions | |
CCC | +0.385 |
HEAD | +0.382 |
HQ | +0.371 |
CDC | +0.364 |
INTON | +0.353 |
Neg logit contributions | |
mos | -0.290 |
rout | -0.280 |
onomy | -0.270 |
� | -0.266 |
wise | -0.265 |
Token | to |
Token ID | 284 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
mos | +0.000 |
rout | +0.000 |
onomy | +0.000 |
� | +0.000 |
wise | +0.000 |
Neg logit contributions | |
CCC | -0.001 |
HEAD | -0.001 |
HQ | -0.001 |
CDC | -0.001 |
INTON | -0.001 |
Token | increase |
Token ID | 2620 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
CCC | +0.222 |
HEAD | +0.221 |
HQ | +0.214 |
CDC | +0.211 |
INTON | +0.205 |
Neg logit contributions | |
mos | -0.161 |
rout | -0.155 |
onomy | -0.151 |
� | -0.148 |
wise | -0.147 |
Token | lawyer |
Token ID | 6853 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
CCC | +1.511 |
HEAD | +1.502 |
HQ | +1.443 |
CDC | +1.414 |
INTON | +1.365 |
Neg logit contributions | |
mos | -1.549 |
onomy | -1.498 |
rout | -1.483 |
� | -1.472 |
wise | -1.421 |
Token | representation |
Token ID | 10552 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
CCC | +0.376 |
HEAD | +0.375 |
HQ | +0.361 |
CDC | +0.355 |
INTON | +0.344 |
Neg logit contributions | |
mos | -0.324 |
onomy | -0.311 |
rout | -0.309 |
� | -0.306 |
wise | -0.296 |
Token | . |
Token ID | 13 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
HEAD | +0.400 |
CCC | +0.400 |
HQ | +0.382 |
CDC | +0.376 |
INTON | +0.366 |
Neg logit contributions | |
mos | -0.427 |
onomy | -0.410 |
rout | -0.409 |
� | -0.404 |
wise | -0.396 |
Token | For |
Token ID | 1114 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
CCC | +0.156 |
HEAD | +0.155 |
HQ | +0.149 |
CDC | +0.147 |
INTON | +0.142 |
Neg logit contributions | |
mos | -0.146 |
onomy | -0.141 |
rout | -0.139 |
� | -0.138 |
wise | -0.133 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
mos | +0.145 |
onomy | +0.139 |
rout | +0.138 |
� | +0.137 |
wise | +0.133 |
Neg logit contributions | |
HEAD | -0.152 |
CCC | -0.152 |
HQ | -0.146 |
CDC | -0.144 |
INTON | -0.139 |
Token | bike |
Token ID | 7161 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
CCC | +0.263 |
HEAD | +0.261 |
HQ | +0.252 |
CDC | +0.248 |
INTON | +0.241 |
Neg logit contributions | |
mos | -0.225 |
onomy | -0.216 |
rout | -0.215 |
� | -0.212 |
wise | -0.207 |
Token | path |
Token ID | 3108 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
CCC | +0.470 |
HEAD | +0.465 |
HQ | +0.448 |
CDC | +0.439 |
INTON | +0.427 |
Neg logit contributions | |
mos | -0.482 |
onomy | -0.468 |
rout | -0.467 |
� | -0.460 |
wise | -0.447 |
Token | ? |
Token ID | 30 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
CCC | +1.046 |
HEAD | +1.039 |
HQ | +1.000 |
CDC | +0.980 |
INTON | +0.949 |
Neg logit contributions | |
mos | -1.024 |
onomy | -0.987 |
rout | -0.981 |
� | -0.972 |
wise | -0.942 |
Token | A |
Token ID | 317 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
CCC | +0.079 |
HEAD | +0.078 |
HQ | +0.075 |
CDC | +0.074 |
INTON | +0.071 |
Neg logit contributions | |
mos | -0.080 |
onomy | -0.076 |
rout | -0.076 |
� | -0.075 |
wise | -0.073 |
Token | known |
Token ID | 1900 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
mos | +0.054 |
rout | +0.051 |
onomy | +0.051 |
� | +0.050 |
wise | +0.049 |
Neg logit contributions | |
CCC | -0.058 |
HEAD | -0.057 |
HQ | -0.056 |
CDC | -0.055 |
INTON | -0.053 |
Token | factor |
Token ID | 5766 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
CCC | +0.709 |
HEAD | +0.706 |
HQ | +0.680 |
CDC | +0.667 |
INTON | +0.646 |
Neg logit contributions | |
mos | -0.653 |
onomy | -0.629 |
rout | -0.625 |
� | -0.617 |
wise | -0.597 |
Token | S |
Token ID | 311 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
mos | +0.504 |
onomy | +0.477 |
rout | +0.476 |
� | +0.472 |
wise | +0.457 |
Neg logit contributions | |
CCC | -0.581 |
HEAD | -0.578 |
HQ | -0.558 |
CDC | -0.548 |
INTON | -0.536 |
Token | GC |
Token ID | 15916 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
mos | +0.342 |
onomy | +0.334 |
� | +0.328 |
rout | +0.327 |
wise | +0.316 |
Neg logit contributions | |
HEAD | -0.312 |
CCC | -0.309 |
HQ | -0.299 |
CDC | -0.293 |
INTON | -0.283 |
Token | afe |
Token ID | 8635 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
mos | +0.892 |
onomy | +0.867 |
� | +0.851 |
rout | +0.851 |
wise | +0.823 |
Neg logit contributions | |
HEAD | -0.832 |
CCC | -0.830 |
HQ | -0.791 |
CDC | -0.780 |
INTON | -0.749 |
Token | . |
Token ID | 13 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
CCC | +0.394 |
HEAD | +0.392 |
HQ | +0.374 |
CDC | +0.367 |
INTON | +0.356 |
Neg logit contributions | |
mos | -0.448 |
onomy | -0.434 |
rout | -0.428 |
� | -0.428 |
wise | -0.413 |
Token | Also |
Token ID | 4418 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
mos | +0.951 |
onomy | +0.915 |
rout | +0.901 |
� | +0.900 |
wise | +0.863 |
Neg logit contributions | |
CCC | -1.134 |
HEAD | -1.126 |
HQ | -1.085 |
CDC | -1.069 |
INTON | -1.035 |
Token | join |
Token ID | 4654 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
mos | +1.712 |
rout | +1.633 |
onomy | +1.630 |
� | +1.609 |
wise | +1.574 |
Neg logit contributions | |
CCC | -1.816 |
HEAD | -1.803 |
HQ | -1.744 |
CDC | -1.718 |
INTON | -1.669 |
Token | in |
Token ID | 287 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
mos | +0.276 |
onomy | +0.262 |
� | +0.261 |
rout | +0.261 |
wise | +0.252 |
Neg logit contributions | |
HEAD | -0.313 |
CCC | -0.312 |
HQ | -0.301 |
CDC | -0.297 |
INTON | -0.287 |
Token | on |
Token ID | 319 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
mos | +0.236 |
onomy | +0.226 |
rout | +0.224 |
� | +0.223 |
wise | +0.215 |
Neg logit contributions | |
CCC | -0.246 |
HEAD | -0.246 |
HQ | -0.236 |
CDC | -0.232 |
INTON | -0.225 |
Token | the |
Token ID | 262 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
mos | +0.427 |
onomy | +0.408 |
rout | +0.405 |
� | +0.404 |
wise | +0.389 |
Neg logit contributions | |
CCC | -0.465 |
HEAD | -0.464 |
HQ | -0.446 |
CDC | -0.441 |
INTON | -0.426 |
Token | community |
Token ID | 2055 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
mos | +0.618 |
onomy | +0.590 |
rout | +0.589 |
� | +0.581 |
wise | +0.565 |
Neg logit contributions | |
HEAD | -0.693 |
CCC | -0.693 |
HQ | -0.664 |
CDC | -0.655 |
INTON | -0.636 |
Token | � |
Token ID | 447 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
mos | +0.067 |
onomy | +0.065 |
rout | +0.065 |
� | +0.064 |
wise | +0.062 |
Neg logit contributions | |
CCC | -0.068 |
HEAD | -0.068 |
HQ | -0.065 |
CDC | -0.064 |
INTON | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
mos | +0.244 |
onomy | +0.233 |
rout | +0.230 |
� | +0.222 |
wise | +0.216 |
Neg logit contributions | |
CCC | -0.444 |
HEAD | -0.441 |
HQ | -0.427 |
CDC | -0.426 |
INTON | -0.419 |
Token | C |
Token ID | 34 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
mos | +0.290 |
onomy | +0.283 |
� | +0.279 |
rout | +0.277 |
wise | +0.265 |
Neg logit contributions | |
CCC | -0.230 |
HEAD | -0.226 |
HQ | -0.217 |
CDC | -0.214 |
INTON | -0.208 |
Token | onsequ |
Token ID | 40819 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
mos | +0.829 |
onomy | +0.797 |
rout | +0.783 |
� | +0.779 |
wise | +0.756 |
Neg logit contributions | |
CCC | -0.911 |
HEAD | -0.904 |
HQ | -0.873 |
CDC | -0.863 |
INTON | -0.835 |
Token | ence |
Token ID | 594 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
mos | +0.617 |
onomy | +0.593 |
rout | +0.583 |
� | +0.582 |
wise | +0.558 |
Neg logit contributions | |
CCC | -0.822 |
HEAD | -0.817 |
HQ | -0.790 |
CDC | -0.778 |
INTON | -0.751 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
mos | +0.715 |
onomy | +0.687 |
rout | +0.679 |
� | +0.676 |
wise | +0.655 |
Neg logit contributions | |
CCC | -0.814 |
HEAD | -0.808 |
HQ | -0.777 |
CDC | -0.770 |
INTON | -0.745 |
Token | Sound |
Token ID | 9506 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
mos | +0.192 |
onomy | +0.182 |
rout | +0.182 |
� | +0.179 |
wise | +0.174 |
Neg logit contributions | |
CCC | -0.222 |
HEAD | -0.220 |
HQ | -0.212 |
CDC | -0.210 |
INTON | -0.203 |
Token | reports |
Token ID | 3136 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
mos | +0.089 |
onomy | +0.086 |
rout | +0.086 |
� | +0.085 |
wise | +0.082 |
Neg logit contributions | |
CCC | -0.090 |
HEAD | -0.088 |
HQ | -0.085 |
CDC | -0.084 |
INTON | -0.081 |
Token | that |
Token ID | 326 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
mos | +0.484 |
onomy | +0.467 |
rout | +0.461 |
� | +0.460 |
wise | +0.446 |
Neg logit contributions | |
CCC | -0.467 |
HEAD | -0.460 |
HQ | -0.445 |
CDC | -0.438 |
INTON | -0.423 |
Token | Vernon |
Token ID | 27820 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
mos | +0.467 |
onomy | +0.443 |
rout | +0.441 |
� | +0.438 |
wise | +0.424 |
Neg logit contributions | |
CCC | -0.531 |
HEAD | -0.523 |
HQ | -0.508 |
CDC | -0.502 |
INTON | -0.484 |
Token | joined |
Token ID | 5399 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
CCC | +0.010 |
HEAD | +0.010 |
HQ | +0.010 |
CDC | +0.010 |
INTON | +0.009 |
Neg logit contributions | |
mos | -0.010 |
rout | -0.009 |
onomy | -0.009 |
� | -0.009 |
wise | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
CCC | +1.052 |
HEAD | +1.041 |
HQ | +1.006 |
CDC | +0.992 |
INTON | +0.959 |
Neg logit contributions | |
mos | -0.972 |
onomy | -0.933 |
rout | -0.924 |
� | -0.919 |
wise | -0.887 |
Token | pressure |
Token ID | 3833 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
mos | +0.465 |
rout | +0.446 |
onomy | +0.444 |
� | +0.438 |
wise | +0.428 |
Neg logit contributions | |
CCC | -0.570 |
HEAD | -0.566 |
HQ | -0.549 |
CDC | -0.544 |
INTON | -0.523 |
Token | of |
Token ID | 286 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
mos | +0.102 |
onomy | +0.098 |
rout | +0.097 |
� | +0.096 |
wise | +0.092 |
Neg logit contributions | |
CCC | -0.125 |
HEAD | -0.124 |
HQ | -0.120 |
CDC | -0.118 |
INTON | -0.114 |
Token | her |
Token ID | 607 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
mos | +0.136 |
onomy | +0.130 |
rout | +0.130 |
� | +0.128 |
wise | +0.124 |
Neg logit contributions | |
CCC | -0.158 |
HEAD | -0.158 |
HQ | -0.152 |
CDC | -0.151 |
INTON | -0.145 |
Token | verse |
Token ID | 18527 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
mos | +0.052 |
rout | +0.050 |
onomy | +0.050 |
� | +0.049 |
wise | +0.048 |
Neg logit contributions | |
CCC | -0.058 |
HEAD | -0.058 |
HQ | -0.056 |
CDC | -0.055 |
INTON | -0.053 |
Token | exceeds |
Token ID | 21695 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
CCC | +0.505 |
HEAD | +0.501 |
HQ | +0.482 |
CDC | +0.475 |
INTON | +0.459 |
Neg logit contributions | |
mos | -0.446 |
onomy | -0.430 |
rout | -0.426 |
� | -0.421 |
wise | -0.406 |
Token | her |
Token ID | 607 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
CCC | +0.318 |
HEAD | +0.316 |
HQ | +0.304 |
CDC | +0.299 |
INTON | +0.288 |
Neg logit contributions | |
mos | -0.296 |
onomy | -0.285 |
rout | -0.283 |
� | -0.280 |
wise | -0.270 |
Token | ability |
Token ID | 2694 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
mos | +0.113 |
rout | +0.108 |
onomy | +0.108 |
� | +0.106 |
wise | +0.103 |
Neg logit contributions | |
CCC | -0.147 |
HEAD | -0.146 |
HQ | -0.140 |
CDC | -0.139 |
INTON | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
CCC | +1.145 |
HEAD | +1.137 |
HQ | +1.102 |
CDC | +1.076 |
INTON | +1.040 |
Neg logit contributions | |
mos | -1.004 |
onomy | -0.966 |
rout | -0.954 |
� | -0.949 |
wise | -0.907 |
Token | make |
Token ID | 787 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
mos | +0.092 |
rout | +0.088 |
onomy | +0.087 |
� | +0.085 |
wise | +0.084 |
Neg logit contributions | |
CCC | -0.125 |
HEAD | -0.125 |
HQ | -0.120 |
CDC | -0.118 |
INTON | -0.115 |
Token | memorable |
Token ID | 18078 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
CCC | +0.390 |
HEAD | +0.387 |
HQ | +0.375 |
CDC | +0.372 |
INTON | +0.358 |
Neg logit contributions | |
mos | -0.285 |
rout | -0.271 |
onomy | -0.270 |
� | -0.265 |
wise | -0.261 |
Token | phrases |
Token ID | 20144 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
mos | +1.567 |
rout | +1.510 |
onomy | +1.474 |
wise | +1.453 |
� | +1.452 |
Neg logit contributions | |
CCC | -1.694 |
HEAD | -1.670 |
CDC | -1.621 |
HQ | -1.620 |
INTON | -1.532 |
Token | i |
Token ID | 72 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
mos | +0.177 |
onomy | +0.171 |
rout | +0.169 |
� | +0.167 |
wise | +0.161 |
Neg logit contributions | |
CCC | -0.212 |
HEAD | -0.210 |
HQ | -0.204 |
CDC | -0.201 |
INTON | -0.194 |
Token | tw |
Token ID | 665 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
mos | +0.034 |
onomy | +0.033 |
rout | +0.033 |
� | +0.033 |
wise | +0.032 |
Neg logit contributions | |
CCC | -0.031 |
HEAD | -0.030 |
HQ | -0.029 |
CDC | -0.029 |
INTON | -0.028 |
Token | = |
Token ID | 28 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
mos | +0.817 |
onomy | +0.795 |
rout | +0.784 |
� | +0.779 |
wise | +0.756 |
Neg logit contributions | |
CCC | -0.712 |
HEAD | -0.710 |
HQ | -0.679 |
CDC | -0.668 |
INTON | -0.642 |
Token | 75 |
Token ID | 2425 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
mos | +0.338 |
onomy | +0.329 |
rout | +0.324 |
� | +0.323 |
wise | +0.312 |
Neg logit contributions | |
CCC | -0.267 |
HEAD | -0.265 |
HQ | -0.255 |
CDC | -0.249 |
INTON | -0.241 |
Token | : |
Token ID | 25 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
mos | +0.601 |
onomy | +0.579 |
rout | +0.573 |
� | +0.567 |
wise | +0.549 |
Neg logit contributions | |
CCC | -0.627 |
HEAD | -0.624 |
HQ | -0.601 |
CDC | -0.591 |
INTON | -0.572 |
Token | */ |
Token ID | 9466 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
mos | +0.396 |
onomy | +0.384 |
rout | +0.379 |
� | +0.378 |
wise | +0.364 |
Neg logit contributions | |
CCC | -0.387 |
HEAD | -0.385 |
HQ | -0.371 |
CDC | -0.365 |
INTON | -0.353 |
Token | The |
Token ID | 383 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
mos | +0.090 |
onomy | +0.087 |
rout | +0.086 |
� | +0.085 |
wise | +0.082 |
Neg logit contributions | |
CCC | -0.110 |
HEAD | -0.109 |
HQ | -0.105 |
CDC | -0.104 |
INTON | -0.100 |
Token | white |
Token ID | 2330 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
CCC | +0.520 |
HEAD | +0.517 |
HQ | +0.502 |
CDC | +0.492 |
INTON | +0.477 |
Neg logit contributions | |
mos | -0.417 |
onomy | -0.403 |
rout | -0.398 |
� | -0.393 |
wise | -0.379 |
Token | space |
Token ID | 2272 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
mos | +0.322 |
onomy | +0.310 |
rout | +0.307 |
� | +0.303 |
wise | +0.291 |
Neg logit contributions | |
CCC | -0.427 |
HEAD | -0.424 |
HQ | -0.411 |
CDC | -0.405 |
INTON | -0.393 |
Token | before |
Token ID | 878 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
mos | +0.189 |
onomy | +0.183 |
rout | +0.181 |
� | +0.178 |
wise | +0.173 |
Neg logit contributions | |
CCC | -0.221 |
HEAD | -0.220 |
HQ | -0.213 |
CDC | -0.209 |
INTON | -0.202 |
Token | { |
Token ID | 1391 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
CCC | +0.180 |
HEAD | +0.179 |
HQ | +0.173 |
CDC | +0.170 |
INTON | +0.164 |
Neg logit contributions | |
mos | -0.164 |
onomy | -0.158 |
rout | -0.157 |
� | -0.155 |
wise | -0.150 |
Token | the |
Token ID | 262 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
mos | +0.055 |
rout | +0.053 |
onomy | +0.052 |
� | +0.052 |
wise | +0.051 |
Neg logit contributions | |
CCC | -0.063 |
HEAD | -0.063 |
HQ | -0.060 |
CDC | -0.059 |
INTON | -0.058 |
Token | economy |
Token ID | 3773 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
mos | +0.102 |
rout | +0.097 |
onomy | +0.097 |
� | +0.096 |
wise | +0.093 |
Neg logit contributions | |
HEAD | -0.121 |
CCC | -0.121 |
HQ | -0.116 |
CDC | -0.114 |
INTON | -0.111 |
Token | of |
Token ID | 286 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
mos | +0.440 |
rout | +0.423 |
onomy | +0.423 |
� | +0.418 |
wise | +0.410 |
Neg logit contributions | |
CCC | -0.471 |
HEAD | -0.470 |
HQ | -0.451 |
CDC | -0.444 |
INTON | -0.430 |
Token | the |
Token ID | 262 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
mos | +0.165 |
rout | +0.156 |
onomy | +0.156 |
� | +0.154 |
wise | +0.151 |
Neg logit contributions | |
CCC | -0.189 |
HEAD | -0.189 |
HQ | -0.183 |
CDC | -0.179 |
INTON | -0.173 |
Token | state |
Token ID | 1181 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
CCC | +0.048 |
HEAD | +0.048 |
HQ | +0.046 |
CDC | +0.046 |
INTON | +0.044 |
Neg logit contributions | |
mos | -0.040 |
onomy | -0.038 |
rout | -0.038 |
� | -0.038 |
wise | -0.037 |
Token | that |
Token ID | 326 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
CCC | +1.480 |
HEAD | +1.473 |
HQ | +1.415 |
CDC | +1.389 |
INTON | +1.340 |
Neg logit contributions | |
mos | -1.476 |
onomy | -1.428 |
rout | -1.414 |
� | -1.404 |
wise | -1.359 |
Token | they |
Token ID | 484 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
mos | +0.155 |
rout | +0.148 |
onomy | +0.146 |
� | +0.144 |
wise | +0.142 |
Neg logit contributions | |
CCC | -0.194 |
HEAD | -0.193 |
HQ | -0.185 |
CDC | -0.183 |
INTON | -0.177 |
Token | don |
Token ID | 836 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
mos | +0.075 |
rout | +0.071 |
onomy | +0.070 |
� | +0.068 |
wise | +0.068 |
Neg logit contributions | |
CCC | -0.109 |
HEAD | -0.108 |
HQ | -0.105 |
CDC | -0.103 |
INTON | -0.100 |
Token | � |
Token ID | 447 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
mos | +0.180 |
onomy | +0.175 |
rout | +0.174 |
� | +0.172 |
wise | +0.169 |
Neg logit contributions | |
CCC | -0.089 |
HEAD | -0.088 |
HQ | -0.082 |
CDC | -0.081 |
INTON | -0.079 |
Token | � |
Token ID | 247 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
mos | +0.253 |
� | +0.249 |
onomy | +0.242 |
rout | +0.237 |
wise | +0.221 |
Neg logit contributions | |
HEAD | -0.519 |
CCC | -0.518 |
HQ | -0.505 |
CDC | -0.496 |
INTON | -0.486 |
Token | t |
Token ID | 83 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
CCC | +0.103 |
HEAD | +0.103 |
HQ | +0.099 |
CDC | +0.097 |
INTON | +0.094 |
Neg logit contributions | |
mos | -0.107 |
onomy | -0.103 |
rout | -0.102 |
� | -0.102 |
wise | -0.098 |
Token | them |
Token ID | 606 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
mos | +0.395 |
onomy | +0.375 |
rout | +0.374 |
� | +0.370 |
wise | +0.359 |
Neg logit contributions | |
CCC | -0.513 |
HEAD | -0.510 |
HQ | -0.494 |
CDC | -0.485 |
INTON | -0.472 |
Token | that |
Token ID | 326 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
mos | +0.043 |
onomy | +0.041 |
rout | +0.041 |
� | +0.040 |
wise | +0.039 |
Neg logit contributions | |
CCC | -0.052 |
HEAD | -0.052 |
HQ | -0.050 |
CDC | -0.049 |
INTON | -0.048 |
Token | you |
Token ID | 345 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
mos | +0.323 |
rout | +0.305 |
onomy | +0.305 |
� | +0.301 |
wise | +0.291 |
Neg logit contributions | |
HEAD | -0.446 |
CCC | -0.446 |
HQ | -0.432 |
CDC | -0.426 |
INTON | -0.412 |
Token | � |
Token ID | 447 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
mos | +0.133 |
onomy | +0.128 |
rout | +0.126 |
� | +0.126 |
wise | +0.120 |
Neg logit contributions | |
HEAD | -0.174 |
CCC | -0.174 |
HQ | -0.167 |
CDC | -0.164 |
INTON | -0.160 |
Token | � |
Token ID | 247 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
mos | +0.158 |
� | +0.155 |
onomy | +0.149 |
rout | +0.145 |
wise | +0.131 |
Neg logit contributions | |
CCC | -0.473 |
HEAD | -0.472 |
HQ | -0.460 |
CDC | -0.455 |
INTON | -0.444 |
Token | re |
Token ID | 260 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
mos | +0.243 |
onomy | +0.234 |
rout | +0.231 |
� | +0.231 |
wise | +0.221 |
Neg logit contributions | |
CCC | -0.264 |
HEAD | -0.264 |
HQ | -0.253 |
CDC | -0.249 |
INTON | -0.241 |
Token | not |
Token ID | 407 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
mos | +2.048 |
rout | +1.930 |
wise | +1.914 |
� | +1.905 |
onomy | +1.899 |
Neg logit contributions | |
CCC | -2.493 |
HEAD | -2.480 |
HQ | -2.390 |
CDC | -2.373 |
INTON | -2.316 |
Token | going |
Token ID | 1016 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
mos | +0.110 |
rout | +0.105 |
onomy | +0.104 |
� | +0.103 |
wise | +0.101 |
Neg logit contributions | |
CCC | -0.129 |
HEAD | -0.128 |
HQ | -0.123 |
CDC | -0.122 |
INTON | -0.118 |
Token | to |
Token ID | 284 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
mos | +0.731 |
onomy | +0.706 |
rout | +0.695 |
� | +0.690 |
wise | +0.660 |
Neg logit contributions | |
CCC | -0.894 |
HEAD | -0.889 |
HQ | -0.858 |
CDC | -0.842 |
INTON | -0.817 |
Token | push |
Token ID | 4574 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
mos | +0.133 |
rout | +0.126 |
onomy | +0.124 |
� | +0.121 |
wise | +0.119 |
Neg logit contributions | |
CCC | -0.190 |
HEAD | -0.189 |
HQ | -0.183 |
CDC | -0.180 |
INTON | -0.176 |
Token | them |
Token ID | 606 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
CCC | +0.629 |
HEAD | +0.625 |
HQ | +0.599 |
CDC | +0.588 |
INTON | +0.564 |
Neg logit contributions | |
mos | -0.730 |
onomy | -0.704 |
rout | -0.699 |
� | -0.693 |
wise | -0.675 |
Token | he |
Token ID | 339 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
CCC | +0.016 |
HEAD | +0.016 |
HQ | +0.015 |
CDC | +0.015 |
INTON | +0.015 |
Neg logit contributions | |
mos | -0.013 |
onomy | -0.013 |
rout | -0.013 |
� | -0.012 |
wise | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
CCC | +0.127 |
HEAD | +0.125 |
HQ | +0.121 |
CDC | +0.119 |
INTON | +0.115 |
Neg logit contributions | |
mos | -0.115 |
rout | -0.111 |
onomy | -0.110 |
� | -0.108 |
wise | -0.106 |
Token | � |
Token ID | 564 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
mos | +0.182 |
rout | +0.174 |
onomy | +0.173 |
� | +0.172 |
wise | +0.169 |
Neg logit contributions | |
CCC | -0.204 |
HEAD | -0.202 |
HQ | -0.196 |
CDC | -0.192 |
INTON | -0.186 |
Token | � |
Token ID | 250 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
mos | +0.215 |
� | +0.204 |
onomy | +0.201 |
rout | +0.197 |
wise | +0.182 |
Neg logit contributions | |
CCC | -0.604 |
HEAD | -0.602 |
HQ | -0.588 |
CDC | -0.580 |
INTON | -0.567 |
Token | a |
Token ID | 64 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
mos | +0.125 |
onomy | +0.122 |
� | +0.120 |
rout | +0.120 |
wise | +0.116 |
Neg logit contributions | |
CCC | -0.113 |
HEAD | -0.111 |
HQ | -0.107 |
CDC | -0.105 |
INTON | -0.102 |
Token | little |
Token ID | 1310 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
mos | +0.039 |
onomy | +0.038 |
rout | +0.037 |
� | +0.037 |
wise | +0.036 |
Neg logit contributions | |
CCC | -0.054 |
HEAD | -0.054 |
HQ | -0.052 |
CDC | -0.051 |
INTON | -0.050 |
Token | concerned |
Token ID | 5213 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
mos | +2.235 |
rout | +2.136 |
onomy | +2.123 |
� | +2.112 |
wise | +2.074 |
Neg logit contributions | |
CCC | -2.697 |
HEAD | -2.644 |
HQ | -2.588 |
CDC | -2.565 |
INTON | -2.472 |
Token | about |
Token ID | 546 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
mos | +1.129 |
onomy | +1.087 |
� | +1.079 |
rout | +1.078 |
wise | +1.038 |
Neg logit contributions | |
CCC | -1.193 |
HEAD | -1.191 |
HQ | -1.144 |
CDC | -1.123 |
INTON | -1.091 |
Token | some |
Token ID | 617 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
mos | +0.057 |
onomy | +0.055 |
rout | +0.054 |
� | +0.054 |
wise | +0.052 |
Neg logit contributions | |
CCC | -0.065 |
HEAD | -0.065 |
HQ | -0.062 |
CDC | -0.061 |
INTON | -0.059 |
Token | of |
Token ID | 286 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
CCC | +0.606 |
HEAD | +0.603 |
HQ | +0.583 |
CDC | +0.572 |
INTON | +0.555 |
Neg logit contributions | |
mos | -0.485 |
onomy | -0.467 |
rout | -0.461 |
� | -0.458 |
wise | -0.440 |
Token | the |
Token ID | 262 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
mos | +0.146 |
onomy | +0.141 |
� | +0.140 |
rout | +0.139 |
wise | +0.133 |
Neg logit contributions | |
CCC | -0.162 |
HEAD | -0.162 |
HQ | -0.156 |
CDC | -0.153 |
INTON | -0.148 |
Token | according |
Token ID | 1864 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
CCC | +0.470 |
HEAD | +0.469 |
HQ | +0.450 |
CDC | +0.437 |
INTON | +0.432 |
Neg logit contributions | |
mos | -0.412 |
rout | -0.396 |
� | -0.390 |
onomy | -0.388 |
wise | -0.377 |
Token | to |
Token ID | 284 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
CCC | +0.073 |
HEAD | +0.073 |
HQ | +0.070 |
CDC | +0.069 |
INTON | +0.068 |
Neg logit contributions | |
mos | -0.049 |
rout | -0.047 |
onomy | -0.047 |
� | -0.047 |
wise | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
CCC | +0.392 |
HEAD | +0.392 |
HQ | +0.376 |
CDC | +0.364 |
INTON | +0.357 |
Neg logit contributions | |
mos | -0.376 |
rout | -0.361 |
onomy | -0.361 |
� | -0.357 |
wise | -0.346 |
Token | 2007 |
Token ID | 4343 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
CCC | +0.295 |
HEAD | +0.294 |
HQ | +0.283 |
CDC | +0.275 |
INTON | +0.270 |
Neg logit contributions | |
mos | -0.259 |
onomy | -0.250 |
rout | -0.249 |
� | -0.243 |
wise | -0.238 |
Token | World |
Token ID | 2159 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
HEAD | +0.006 |
CCC | +0.006 |
HQ | +0.006 |
CDC | +0.006 |
INTON | +0.006 |
Neg logit contributions | |
mos | -0.006 |
onomy | -0.006 |
rout | -0.006 |
� | -0.006 |
wise | -0.005 |
Token | Bank |
Token ID | 5018 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
HEAD | +0.392 |
CCC | +0.391 |
HQ | +0.374 |
CDC | +0.358 |
INTON | +0.357 |
Neg logit contributions | |
mos | -0.446 |
onomy | -0.435 |
� | -0.430 |
rout | -0.429 |
wise | -0.416 |
Token | study |
Token ID | 2050 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
onomy | +2.003 |
mos | +2.001 |
rout | +1.986 |
� | +1.924 |
wise | +1.899 |
Neg logit contributions | |
HEAD | -2.608 |
CCC | -2.571 |
HQ | -2.481 |
CDC | -2.432 |
INTON | -2.399 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
mos | +1.631 |
onomy | +1.605 |
rout | +1.584 |
� | +1.580 |
wise | +1.527 |
Neg logit contributions | |
CCC | -1.274 |
HEAD | -1.271 |
HQ | -1.212 |
CDC | -1.167 |
INTON | -1.145 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
CCC | +0.379 |
HEAD | +0.377 |
HQ | +0.363 |
CDC | +0.354 |
INTON | +0.347 |
Neg logit contributions | |
mos | -0.310 |
onomy | -0.297 |
rout | -0.294 |
� | -0.294 |
wise | -0.280 |
Token |
|
Token ID | 198 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
mos | +0.200 |
onomy | +0.191 |
rout | +0.190 |
� | +0.181 |
wise | +0.178 |
Neg logit contributions | |
CCC | -0.366 |
HEAD | -0.362 |
HQ | -0.351 |
CDC | -0.348 |
INTON | -0.343 |
Token | Y |
Token ID | 56 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
mos | +0.117 |
onomy | +0.116 |
� | +0.114 |
rout | +0.113 |
wise | +0.108 |
Neg logit contributions | |
CCC | -0.086 |
HEAD | -0.085 |
HQ | -0.081 |
INTON | -0.078 |
CDC | -0.078 |
Token | be |
Token ID | 307 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
mos | +0.794 |
rout | +0.763 |
onomy | +0.753 |
� | +0.729 |
wise | +0.720 |
Neg logit contributions | |
CCC | -1.095 |
HEAD | -1.089 |
HQ | -1.061 |
CDC | -1.037 |
INTON | -1.012 |
Token | prevented |
Token ID | 13351 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
mos | +0.398 |
onomy | +0.382 |
rout | +0.381 |
� | +0.375 |
wise | +0.364 |
Neg logit contributions | |
CCC | -0.468 |
HEAD | -0.465 |
HQ | -0.449 |
CDC | -0.442 |
INTON | -0.430 |
Token | under |
Token ID | 739 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
CCC | +0.549 |
HEAD | +0.546 |
HQ | +0.526 |
CDC | +0.516 |
INTON | +0.500 |
Neg logit contributions | |
mos | -0.505 |
onomy | -0.486 |
rout | -0.484 |
� | -0.478 |
wise | -0.464 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
CCC | +0.573 |
HEAD | +0.570 |
HQ | +0.550 |
CDC | +0.539 |
INTON | +0.521 |
Neg logit contributions | |
mos | -0.520 |
onomy | -0.502 |
rout | -0.496 |
� | -0.492 |
wise | -0.474 |
Token | proposed |
Token ID | 5150 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
mos | +0.246 |
onomy | +0.239 |
rout | +0.236 |
� | +0.231 |
wise | +0.227 |
Neg logit contributions | |
CCC | -0.277 |
HEAD | -0.275 |
HQ | -0.265 |
CDC | -0.263 |
INTON | -0.255 |
Token | rules |
Token ID | 3173 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
CCC | +0.185 |
HEAD | +0.183 |
HQ | +0.177 |
CDC | +0.176 |
INTON | +0.170 |
Neg logit contributions | |
mos | -0.159 |
onomy | -0.154 |
rout | -0.153 |
� | -0.150 |
wise | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
mos | +2.178 |
onomy | +2.120 |
rout | +2.117 |
� | +2.075 |
wise | +2.020 |
Neg logit contributions | |
CCC | -2.112 |
HEAD | -2.089 |
HQ | -2.017 |
CDC | -1.997 |
INTON | -1.917 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
CCC | +0.502 |
HEAD | +0.496 |
HQ | +0.482 |
CDC | +0.477 |
INTON | +0.469 |
Neg logit contributions | |
mos | -0.296 |
onomy | -0.283 |
rout | -0.280 |
� | -0.271 |
wise | -0.264 |
Token | All |
Token ID | 3237 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
CCC | +0.228 |
HEAD | +0.224 |
HQ | +0.215 |
CDC | +0.211 |
INTON | +0.205 |
Neg logit contributions | |
mos | -0.294 |
onomy | -0.290 |
rout | -0.285 |
� | -0.284 |
wise | -0.272 |
Token | you |
Token ID | 345 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
mos | +0.181 |
onomy | +0.175 |
rout | +0.174 |
� | +0.171 |
wise | +0.166 |
Neg logit contributions | |
CCC | -0.206 |
HEAD | -0.202 |
HQ | -0.196 |
CDC | -0.194 |
INTON | -0.188 |
Token | need |
Token ID | 761 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
mos | +0.323 |
onomy | +0.306 |
rout | +0.305 |
� | +0.305 |
wise | +0.299 |
Neg logit contributions | |
CCC | -0.363 |
HEAD | -0.358 |
HQ | -0.343 |
CDC | -0.342 |
INTON | -0.331 |
Token | physical |
Token ID | 3518 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
mos | +0.261 |
rout | +0.250 |
onomy | +0.247 |
wise | +0.243 |
� | +0.243 |
Neg logit contributions | |
CCC | -0.310 |
HEAD | -0.309 |
HQ | -0.300 |
CDC | -0.294 |
INTON | -0.289 |
Token | and |
Token ID | 290 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
mos | +0.452 |
rout | +0.437 |
onomy | +0.434 |
wise | +0.424 |
� | +0.419 |
Neg logit contributions | |
CCC | -0.411 |
HEAD | -0.406 |
HQ | -0.392 |
CDC | -0.383 |
INTON | -0.375 |
Token | re |
Token ID | 302 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
mos | +0.191 |
rout | +0.182 |
onomy | +0.181 |
� | +0.176 |
wise | +0.173 |
Neg logit contributions | |
CCC | -0.276 |
HEAD | -0.274 |
HQ | -0.266 |
CDC | -0.261 |
INTON | -0.255 |
Token | - |
Token ID | 12 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
mos | +1.255 |
onomy | +1.225 |
rout | +1.203 |
� | +1.195 |
wise | +1.155 |
Neg logit contributions | |
CCC | -1.245 |
HEAD | -1.239 |
HQ | -1.195 |
CDC | -1.166 |
INTON | -1.133 |
Token | route |
Token ID | 38629 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
mos | +0.397 |
onomy | +0.385 |
rout | +0.379 |
� | +0.374 |
wise | +0.361 |
Neg logit contributions | |
CCC | -0.523 |
HEAD | -0.519 |
HQ | -0.504 |
CDC | -0.493 |
INTON | -0.484 |
Token | Baldwin |
Token ID | 26402 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
mos | +0.920 |
rout | +0.897 |
wise | +0.868 |
onomy | +0.863 |
� | +0.857 |
Neg logit contributions | |
CCC | -1.010 |
HEAD | -0.995 |
HQ | -0.972 |
CDC | -0.960 |
INTON | -0.937 |
Token | to |
Token ID | 284 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
mos | +2.121 |
rout | +2.067 |
wise | +2.019 |
onomy | +1.982 |
� | +1.949 |
Neg logit contributions | |
CCC | -2.189 |
HEAD | -2.145 |
HQ | -2.119 |
CDC | -2.102 |
INTON | -2.047 |
Token | throw |
Token ID | 3714 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
mos | +0.234 |
rout | +0.227 |
onomy | +0.226 |
� | +0.221 |
wise | +0.216 |
Neg logit contributions | |
HEAD | -0.285 |
CCC | -0.285 |
HQ | -0.276 |
CDC | -0.271 |
INTON | -0.263 |
Token | the |
Token ID | 262 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
CCC | +0.201 |
HEAD | +0.199 |
HQ | +0.193 |
CDC | +0.190 |
INTON | +0.184 |
Neg logit contributions | |
mos | -0.176 |
rout | -0.170 |
onomy | -0.168 |
� | -0.165 |
wise | -0.163 |
Token | timing |
Token ID | 10576 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
mos | +0.108 |
rout | +0.104 |
onomy | +0.102 |
� | +0.100 |
wise | +0.098 |
Neg logit contributions | |
CCC | -0.170 |
HEAD | -0.170 |
HQ | -0.166 |
CDC | -0.163 |
INTON | -0.159 |
Token | off |
Token ID | 572 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
mos | +0.660 |
rout | +0.642 |
onomy | +0.626 |
wise | +0.613 |
� | +0.610 |
Neg logit contributions | |
CCC | -0.757 |
HEAD | -0.750 |
HQ | -0.730 |
CDC | -0.723 |
INTON | -0.695 |