Token | mess |
Token ID | 2085 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
banter | +0.900 |
puter | +0.882 |
egu | +0.874 |
dop | +0.841 |
ottesville | +0.841 |
Neg logit contributions | |
ONS | -0.994 |
EMS | -0.964 |
LIST | -0.964 |
Kind | -0.955 |
ALS | -0.924 |
Token | seriously |
Token ID | 6411 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
ONS | +0.553 |
EMS | +0.534 |
LIST | +0.530 |
Kind | +0.527 |
Imper | +0.511 |
Neg logit contributions | |
banter | -0.577 |
puter | -0.574 |
egu | -0.567 |
ottesville | -0.547 |
ousy | -0.545 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ONS | +0.698 |
EMS | +0.675 |
LIST | +0.671 |
Kind | +0.667 |
Imper | +0.647 |
Neg logit contributions | |
banter | -0.656 |
puter | -0.652 |
egu | -0.644 |
ottesville | -0.620 |
ousy | -0.618 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
banter | +0.835 |
egu | +0.818 |
puter | +0.807 |
ousy | +0.780 |
dop | +0.772 |
Neg logit contributions | |
ONS | -0.981 |
EMS | -0.954 |
LIST | -0.941 |
Kind | -0.934 |
Imper | -0.915 |
Token | Article |
Token ID | 14906 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
puter | +1.098 |
egu | +1.098 |
banter | +1.097 |
ousy | +1.067 |
ottesville | +1.059 |
Neg logit contributions | |
ONS | -0.415 |
EMS | -0.388 |
LIST | -0.380 |
Kind | -0.375 |
Imper | -0.374 |
Token | Continued |
Token ID | 22168 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
banter | +0.527 |
egu | +0.513 |
puter | +0.512 |
ottesville | +0.487 |
ousy | +0.482 |
Neg logit contributions | |
ONS | -0.654 |
EMS | -0.640 |
Kind | -0.629 |
LIST | -0.626 |
Imper | -0.611 |
Token | Below |
Token ID | 10383 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
banter | +3.657 |
egu | +3.109 |
ousy | +3.050 |
REUTERS | +3.025 |
crunch | +2.993 |
Neg logit contributions | |
ONS | -7.424 |
exha | -7.282 |
EMS | -7.270 |
IOR | -7.235 |
Kind | -7.197 |
Token |
|
Token ID | 198 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
banter | +3.183 |
egu | +3.083 |
ousy | +2.932 |
puter | +2.928 |
dop | +2.868 |
Neg logit contributions | |
ONS | -4.428 |
EMS | -4.287 |
Kind | -4.199 |
LIST | -4.194 |
exha | -4.174 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
banter | +0.656 |
egu | +0.642 |
puter | +0.635 |
ousy | +0.613 |
dop | +0.609 |
Neg logit contributions | |
ONS | -0.768 |
EMS | -0.744 |
LIST | -0.734 |
Kind | -0.729 |
Imper | -0.714 |
Token | � |
Token ID | 447 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
puter | +0.912 |
egu | +0.911 |
banter | +0.911 |
ousy | +0.881 |
ottesville | +0.873 |
Neg logit contributions | |
ONS | -0.628 |
EMS | -0.598 |
LIST | -0.590 |
Kind | -0.585 |
Imper | -0.583 |
Token | � |
Token ID | 250 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
banter | +1.008 |
puter | +1.002 |
egu | +0.997 |
ottesville | +0.961 |
ousy | +0.958 |
Neg logit contributions | |
ONS | -0.623 |
EMS | -0.596 |
Kind | -0.587 |
LIST | -0.586 |
Imper | -0.562 |
Token | scrap |
Token ID | 15881 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ONS | +0.312 |
EMS | +0.299 |
LIST | +0.298 |
Kind | +0.296 |
ALS | +0.286 |
Neg logit contributions | |
banter | -0.369 |
puter | -0.365 |
egu | -0.362 |
ottesville | -0.349 |
ousy | -0.349 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ONS | +1.505 |
EMS | +1.466 |
LIST | +1.454 |
Kind | +1.441 |
Imper | +1.403 |
Neg logit contributions | |
banter | -1.353 |
puter | -1.344 |
egu | -1.330 |
ottesville | -1.282 |
ousy | -1.274 |
Token |
|
Token ID | 198 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
ONS | +0.994 |
EMS | +0.961 |
LIST | +0.953 |
Kind | +0.949 |
Imper | +0.918 |
Neg logit contributions | |
banter | -0.947 |
puter | -0.938 |
egu | -0.930 |
ousy | -0.892 |
ottesville | -0.891 |
Token |
|
Token ID | 198 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
ONS | +0.651 |
EMS | +0.630 |
LIST | +0.624 |
Kind | +0.621 |
Imper | +0.604 |
Neg logit contributions | |
banter | -0.621 |
puter | -0.614 |
egu | -0.610 |
ottesville | -0.585 |
ousy | -0.584 |
Token | Article |
Token ID | 14906 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ONS | +0.435 |
EMS | +0.416 |
LIST | +0.411 |
Kind | +0.410 |
Imper | +0.401 |
Neg logit contributions | |
banter | -0.617 |
puter | -0.617 |
egu | -0.612 |
ousy | -0.590 |
ottesville | -0.590 |
Token | Continued |
Token ID | 22168 |
Feature activation | +7.72e+00 |
Pos logit contributions | |
banter | +0.294 |
puter | +0.289 |
egu | +0.287 |
ottesville | +0.274 |
ousy | +0.272 |
Neg logit contributions | |
ONS | -0.343 |
EMS | -0.334 |
Kind | -0.330 |
LIST | -0.327 |
Imper | -0.320 |
Token | Below |
Token ID | 10383 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
banter | +3.578 |
egu | +3.019 |
ousy | +2.969 |
REUTERS | +2.939 |
crunch | +2.924 |
Neg logit contributions | |
ONS | -7.297 |
exha | -7.183 |
EMS | -7.148 |
IOR | -7.122 |
Kind | -7.092 |
Token |
|
Token ID | 198 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
banter | +3.112 |
egu | +3.013 |
ousy | +2.885 |
puter | +2.871 |
dop | +2.805 |
Neg logit contributions | |
ONS | -4.369 |
EMS | -4.216 |
Kind | -4.135 |
exha | -4.128 |
LIST | -4.118 |
Token |
|
Token ID | 198 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
banter | +0.647 |
egu | +0.634 |
puter | +0.627 |
ousy | +0.605 |
dop | +0.601 |
Neg logit contributions | |
ONS | -0.752 |
EMS | -0.728 |
LIST | -0.718 |
Kind | -0.714 |
Imper | -0.700 |
Token | The |
Token ID | 464 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
egu | +0.789 |
puter | +0.789 |
banter | +0.787 |
ousy | +0.760 |
dop | +0.750 |
Neg logit contributions | |
ONS | -0.609 |
EMS | -0.578 |
Imper | -0.572 |
LIST | -0.572 |
Kind | -0.569 |
Token | T |
Token ID | 309 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
ONS | +0.444 |
EMS | +0.429 |
LIST | +0.427 |
Kind | +0.425 |
ALS | +0.410 |
Neg logit contributions | |
banter | -0.421 |
puter | -0.416 |
egu | -0.412 |
ousy | -0.396 |
ottesville | -0.395 |
Token | in |
Token ID | 287 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
ONS | +0.042 |
EMS | +0.040 |
LIST | +0.040 |
Kind | +0.040 |
Imper | +0.039 |
Neg logit contributions | |
banter | -0.046 |
puter | -0.046 |
egu | -0.045 |
ottesville | -0.044 |
ousy | -0.044 |
Token | human |
Token ID | 1692 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
banter | +0.613 |
puter | +0.598 |
egu | +0.591 |
dop | +0.567 |
ottesville | +0.559 |
Neg logit contributions | |
ONS | -0.731 |
EMS | -0.709 |
LIST | -0.705 |
Kind | -0.697 |
ALS | -0.682 |
Token | rights |
Token ID | 2489 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
banter | +1.247 |
puter | +1.220 |
egu | +1.209 |
dop | +1.156 |
ottesville | +1.153 |
Neg logit contributions | |
ONS | -1.538 |
EMS | -1.497 |
LIST | -1.486 |
Kind | -1.457 |
ALS | -1.432 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
banter | +0.307 |
puter | +0.304 |
egu | +0.301 |
ottesville | +0.288 |
dop | +0.287 |
Neg logit contributions | |
ONS | -0.368 |
EMS | -0.358 |
LIST | -0.355 |
Kind | -0.352 |
ALS | -0.343 |
Token | The |
Token ID | 383 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ONS | +0.108 |
EMS | +0.105 |
LIST | +0.104 |
Kind | +0.103 |
ALS | +0.100 |
Neg logit contributions | |
banter | -0.102 |
puter | -0.101 |
egu | -0.100 |
ottesville | -0.096 |
ousy | -0.096 |
Token | latter |
Token ID | 6846 |
Feature activation | +7.08e+00 |
Pos logit contributions | |
banter | +0.208 |
puter | +0.204 |
egu | +0.201 |
dop | +0.194 |
ottesville | +0.194 |
Neg logit contributions | |
ONS | -0.244 |
EMS | -0.237 |
LIST | -0.235 |
Kind | -0.234 |
ALS | -0.227 |
Token | two |
Token ID | 734 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
banter | +4.470 |
dop | +4.184 |
puter | +4.113 |
egu | +4.093 |
dissip | +4.042 |
Neg logit contributions | |
ONS | -5.700 |
EMS | -5.531 |
LIST | -5.504 |
Kind | -5.416 |
ALS | -5.326 |
Token | were |
Token ID | 547 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
banter | +0.507 |
puter | +0.499 |
egu | +0.494 |
dop | +0.474 |
ottesville | +0.473 |
Neg logit contributions | |
ONS | -0.594 |
EMS | -0.576 |
LIST | -0.573 |
Kind | -0.570 |
ALS | -0.553 |
Token | very |
Token ID | 845 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
banter | +0.179 |
puter | +0.177 |
egu | +0.175 |
ottesville | +0.168 |
ousy | +0.167 |
Neg logit contributions | |
ONS | -0.234 |
EMS | -0.227 |
LIST | -0.226 |
Kind | -0.224 |
Imper | -0.218 |
Token | much |
Token ID | 881 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
banter | +0.612 |
puter | +0.599 |
egu | +0.597 |
dop | +0.572 |
ottesville | +0.569 |
Neg logit contributions | |
ONS | -0.775 |
EMS | -0.751 |
LIST | -0.745 |
Kind | -0.742 |
ALS | -0.722 |
Token | to |
Token ID | 284 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
ONS | +2.178 |
EMS | +2.098 |
LIST | +2.093 |
Kind | +2.078 |
Imper | +2.032 |
Neg logit contributions | |
puter | -2.036 |
banter | -2.015 |
egu | -2.013 |
ottesville | -1.946 |
ousy | -1.939 |
Token | last |
Token ID | 938 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ONS | +0.483 |
EMS | +0.470 |
LIST | +0.467 |
Kind | +0.464 |
Imper | +0.451 |
Neg logit contributions | |
banter | -0.353 |
puter | -0.346 |
egu | -0.342 |
dop | -0.327 |
ottesville | -0.326 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ONS | +0.216 |
EMS | +0.209 |
LIST | +0.209 |
Kind | +0.208 |
Imper | +0.201 |
Neg logit contributions | |
banter | -0.168 |
puter | -0.165 |
egu | -0.164 |
dop | -0.157 |
ottesville | -0.156 |
Token |
|
Token ID | 198 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
ONS | +0.987 |
EMS | +0.955 |
LIST | +0.947 |
Kind | +0.943 |
Imper | +0.913 |
Neg logit contributions | |
banter | -0.960 |
puter | -0.952 |
egu | -0.942 |
ottesville | -0.907 |
ousy | -0.904 |
Token |
|
Token ID | 198 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
ONS | +0.637 |
EMS | +0.616 |
LIST | +0.611 |
Kind | +0.608 |
Imper | +0.591 |
Neg logit contributions | |
banter | -0.606 |
puter | -0.599 |
egu | -0.595 |
ottesville | -0.570 |
ousy | -0.570 |
Token | Article |
Token ID | 14906 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ONS | +0.480 |
EMS | +0.464 |
LIST | +0.460 |
Kind | +0.458 |
Imper | +0.450 |
Neg logit contributions | |
banter | -0.408 |
puter | -0.406 |
egu | -0.401 |
ottesville | -0.385 |
ousy | -0.383 |
Token | Continued |
Token ID | 22168 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
ONS | +0.292 |
EMS | +0.283 |
LIST | +0.281 |
Kind | +0.280 |
Imper | +0.272 |
Neg logit contributions | |
banter | -0.233 |
puter | -0.232 |
egu | -0.229 |
ottesville | -0.219 |
ousy | -0.219 |
Token | Below |
Token ID | 10383 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
banter | +3.408 |
egu | +2.964 |
ousy | +2.850 |
puter | +2.842 |
crunch | +2.825 |
Neg logit contributions | |
ONS | -6.613 |
EMS | -6.440 |
Kind | -6.419 |
IOR | -6.402 |
LIST | -6.328 |
Token |
|
Token ID | 198 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
banter | +2.823 |
egu | +2.731 |
puter | +2.610 |
ousy | +2.603 |
dop | +2.559 |
Neg logit contributions | |
ONS | -3.861 |
EMS | -3.738 |
Kind | -3.658 |
LIST | -3.650 |
exha | -3.597 |
Token |
|
Token ID | 198 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
banter | +0.063 |
egu | +0.062 |
puter | +0.061 |
ousy | +0.059 |
dop | +0.059 |
Neg logit contributions | |
ONS | -0.071 |
EMS | -0.068 |
LIST | -0.067 |
Kind | -0.067 |
Imper | -0.065 |
Token | T |
Token ID | 51 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
banter | +0.178 |
puter | +0.177 |
egu | +0.176 |
ousy | +0.170 |
ottesville | +0.169 |
Neg logit contributions | |
ONS | -0.145 |
EMS | -0.140 |
LIST | -0.137 |
Kind | -0.137 |
Imper | -0.136 |
Token | od |
Token ID | 375 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
ONS | +0.137 |
EMS | +0.132 |
LIST | +0.131 |
Kind | +0.130 |
Imper | +0.126 |
Neg logit contributions | |
banter | -0.171 |
puter | -0.170 |
egu | -0.168 |
ottesville | -0.163 |
ousy | -0.162 |
Token | � |
Token ID | 447 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
banter | +0.497 |
puter | +0.489 |
egu | +0.483 |
ousy | +0.463 |
ottesville | +0.463 |
Neg logit contributions | |
ONS | -0.577 |
EMS | -0.560 |
Kind | -0.555 |
LIST | -0.550 |
Imper | -0.537 |
Token | � |
Token ID | 247 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
banter | +0.138 |
puter | +0.137 |
egu | +0.135 |
ottesville | +0.130 |
ousy | +0.129 |
Neg logit contributions | |
ONS | -0.156 |
EMS | -0.151 |
LIST | -0.150 |
Kind | -0.149 |
Imper | -0.145 |
Token | s |
Token ID | 82 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
banter | +0.151 |
puter | +0.150 |
egu | +0.149 |
ottesville | +0.144 |
ousy | +0.144 |
Neg logit contributions | |
ONS | -0.101 |
EMS | -0.097 |
LIST | -0.096 |
Kind | -0.096 |
Imper | -0.092 |
Token | Matt |
Token ID | 4705 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
banter | +0.594 |
puter | +0.580 |
egu | +0.574 |
dop | +0.557 |
ousy | +0.555 |
Neg logit contributions | |
ONS | -0.602 |
EMS | -0.583 |
Kind | -0.577 |
LIST | -0.576 |
ALS | -0.556 |
Token | L |
Token ID | 406 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
ONS | +0.472 |
EMS | +0.457 |
LIST | +0.454 |
Kind | +0.450 |
ALS | +0.440 |
Neg logit contributions | |
banter | -0.358 |
puter | -0.352 |
egu | -0.350 |
ousy | -0.340 |
ottesville | -0.337 |
Token | auer |
Token ID | 16261 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
egu | +1.704 |
banter | +1.690 |
ousy | +1.648 |
puter | +1.612 |
ottesville | +1.562 |
Neg logit contributions | |
ONS | -3.602 |
LIST | -3.565 |
EMS | -3.558 |
Kind | -3.551 |
Imper | -3.505 |
Token | that |
Token ID | 326 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
banter | +4.175 |
puter | +3.965 |
egu | +3.946 |
dop | +3.844 |
ousy | +3.810 |
Neg logit contributions | |
ONS | -5.839 |
EMS | -5.678 |
Kind | -5.625 |
LIST | -5.532 |
ALS | -5.414 |
Token | he |
Token ID | 339 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
ONS | +0.187 |
EMS | +0.181 |
Kind | +0.179 |
LIST | +0.179 |
Imper | +0.172 |
Neg logit contributions | |
banter | -0.179 |
puter | -0.176 |
egu | -0.174 |
dop | -0.168 |
ousy | -0.167 |
Token | he |
Token ID | 339 |
Feature activation | +7.34e-03 |
Pos logit contributions | |
banter | +0.289 |
puter | +0.285 |
egu | +0.283 |
dop | +0.270 |
ottesville | +0.270 |
Neg logit contributions | |
ONS | -0.348 |
EMS | -0.337 |
LIST | -0.334 |
Kind | -0.333 |
Imper | -0.324 |
Token | might |
Token ID | 1244 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
banter | +0.005 |
puter | +0.005 |
egu | +0.005 |
ottesville | +0.005 |
ousy | +0.005 |
Neg logit contributions | |
ONS | -0.006 |
EMS | -0.006 |
LIST | -0.006 |
Kind | -0.006 |
Imper | -0.005 |
Token | hire |
Token ID | 11078 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
ONS | +0.986 |
EMS | +0.955 |
LIST | +0.950 |
Kind | +0.944 |
Imper | +0.918 |
Neg logit contributions | |
banter | -0.838 |
puter | -0.833 |
egu | -0.823 |
ottesville | -0.791 |
ousy | -0.787 |
Token | security |
Token ID | 2324 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
banter | +0.156 |
puter | +0.154 |
egu | +0.152 |
dop | +0.145 |
ottesville | +0.145 |
Neg logit contributions | |
ONS | -0.196 |
EMS | -0.190 |
LIST | -0.189 |
Kind | -0.188 |
ALS | -0.183 |
Token | . |
Token ID | 13 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
banter | +0.152 |
puter | +0.150 |
egu | +0.149 |
ottesville | +0.142 |
dop | +0.141 |
Neg logit contributions | |
ONS | -0.194 |
EMS | -0.189 |
LIST | -0.188 |
Kind | -0.187 |
Imper | -0.181 |
Token |
|
Token ID | 198 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
ONS | +0.365 |
EMS | +0.353 |
LIST | +0.351 |
Kind | +0.348 |
Imper | +0.339 |
Neg logit contributions | |
banter | -0.356 |
puter | -0.355 |
egu | -0.350 |
ottesville | -0.337 |
ousy | -0.336 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ONS | +0.032 |
EMS | +0.031 |
LIST | +0.030 |
Kind | +0.030 |
Imper | +0.030 |
Neg logit contributions | |
banter | -0.029 |
egu | -0.028 |
puter | -0.028 |
ousy | -0.027 |
dop | -0.027 |
Token | The |
Token ID | 464 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
banter | +0.153 |
egu | +0.153 |
puter | +0.153 |
ottesville | +0.147 |
ousy | +0.146 |
Neg logit contributions | |
ONS | -0.116 |
EMS | -0.111 |
Kind | -0.110 |
LIST | -0.109 |
Imper | -0.109 |
Token | latter |
Token ID | 6846 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
banter | +0.078 |
puter | +0.077 |
egu | +0.076 |
ottesville | +0.073 |
dop | +0.073 |
Neg logit contributions | |
ONS | -0.087 |
EMS | -0.084 |
LIST | -0.084 |
Kind | -0.083 |
ALS | -0.081 |
Token | is |
Token ID | 318 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
banter | +4.239 |
egu | +3.973 |
dop | +3.889 |
crunch | +3.882 |
puter | +3.826 |
Neg logit contributions | |
ONS | -5.367 |
Kind | -5.237 |
EMS | -5.151 |
LIST | -5.135 |
ALS | -5.009 |
Token | an |
Token ID | 281 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
ONS | +0.875 |
EMS | +0.848 |
LIST | +0.843 |
Kind | +0.838 |
Imper | +0.815 |
Neg logit contributions | |
banter | -0.724 |
puter | -0.718 |
egu | -0.710 |
ottesville | -0.681 |
ousy | -0.678 |
Token | issue |
Token ID | 2071 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ONS | +0.543 |
EMS | +0.526 |
LIST | +0.525 |
Kind | +0.525 |
ALS | +0.505 |
Neg logit contributions | |
banter | -0.588 |
egu | -0.574 |
puter | -0.572 |
ousy | -0.552 |
dop | -0.552 |
Token | of |
Token ID | 286 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
banter | +0.726 |
puter | +0.711 |
egu | +0.705 |
dop | +0.680 |
ousy | +0.675 |
Neg logit contributions | |
ONS | -0.878 |
EMS | -0.856 |
Kind | -0.848 |
LIST | -0.844 |
ALS | -0.816 |
Token | particularly |
Token ID | 3573 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
banter | +1.377 |
egu | +1.321 |
puter | +1.300 |
dop | +1.280 |
ousy | +1.242 |
Neg logit contributions | |
ONS | -1.496 |
EMS | -1.449 |
LIST | -1.431 |
Kind | -1.426 |
ALS | -1.385 |
Token | The |
Token ID | 383 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
banter | +0.150 |
puter | +0.148 |
egu | +0.146 |
ousy | +0.141 |
dop | +0.140 |
Neg logit contributions | |
ONS | -0.164 |
EMS | -0.159 |
LIST | -0.158 |
Kind | -0.156 |
ALS | -0.152 |
Token | opening |
Token ID | 4756 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ONS | +0.304 |
EMS | +0.295 |
LIST | +0.293 |
Kind | +0.291 |
Imper | +0.283 |
Neg logit contributions | |
banter | -0.234 |
puter | -0.232 |
egu | -0.229 |
ottesville | -0.219 |
ousy | -0.218 |
Token | mission |
Token ID | 4365 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
banter | +1.158 |
puter | +1.115 |
egu | +1.104 |
dop | +1.070 |
ousy | +1.051 |
Neg logit contributions | |
ONS | -1.542 |
EMS | -1.493 |
LIST | -1.490 |
Kind | -1.478 |
ALS | -1.440 |
Token | of |
Token ID | 286 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
banter | +2.052 |
puter | +2.006 |
egu | +1.971 |
dop | +1.910 |
ousy | +1.887 |
Neg logit contributions | |
ONS | -2.544 |
EMS | -2.466 |
LIST | -2.442 |
Kind | -2.422 |
ALS | -2.371 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
banter | +0.185 |
puter | +0.183 |
egu | +0.181 |
ottesville | +0.174 |
ousy | +0.174 |
Neg logit contributions | |
ONS | -0.194 |
EMS | -0.187 |
LIST | -0.186 |
Kind | -0.185 |
Imper | -0.179 |
Token | latter |
Token ID | 6846 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
banter | +0.148 |
puter | +0.146 |
egu | +0.144 |
ottesville | +0.139 |
dop | +0.138 |
Neg logit contributions | |
ONS | -0.177 |
EMS | -0.171 |
LIST | -0.171 |
Kind | -0.169 |
ALS | -0.164 |
Token | title |
Token ID | 3670 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
banter | +4.120 |
puter | +3.988 |
dop | +3.878 |
egu | +3.854 |
comed | +3.746 |
Neg logit contributions | |
ONS | -5.321 |
LIST | -5.109 |
EMS | -5.090 |
Kind | -4.997 |
ALS | -4.964 |
Token | is |
Token ID | 318 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
banter | +0.630 |
puter | +0.624 |
egu | +0.615 |
ottesville | +0.590 |
dop | +0.588 |
Neg logit contributions | |
ONS | -0.786 |
EMS | -0.761 |
LIST | -0.757 |
Kind | -0.752 |
ALS | -0.731 |
Token | especially |
Token ID | 2592 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
banter | +0.258 |
puter | +0.256 |
egu | +0.252 |
ottesville | +0.242 |
dop | +0.241 |
Neg logit contributions | |
ONS | -0.316 |
EMS | -0.306 |
LIST | -0.304 |
Kind | -0.302 |
Imper | -0.294 |
Token | appealing |
Token ID | 16403 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
ONS | +0.099 |
EMS | +0.096 |
LIST | +0.095 |
Kind | +0.095 |
ALS | +0.092 |
Neg logit contributions | |
banter | -0.081 |
puter | -0.080 |
egu | -0.078 |
dop | -0.076 |
ottesville | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ONS | +0.403 |
EMS | +0.391 |
LIST | +0.389 |
Kind | +0.386 |
Imper | +0.376 |
Neg logit contributions | |
banter | -0.336 |
puter | -0.335 |
egu | -0.331 |
ottesville | -0.319 |
ousy | -0.316 |
Token | Gaza |
Token ID | 11010 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
banter | +2.051 |
puter | +1.996 |
egu | +1.995 |
dop | +1.925 |
ottesville | +1.899 |
Neg logit contributions | |
ONS | -1.937 |
EMS | -1.877 |
LIST | -1.867 |
Kind | -1.845 |
ALS | -1.794 |
Token | in |
Token ID | 287 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
banter | +0.116 |
puter | +0.115 |
egu | +0.114 |
ottesville | +0.109 |
ousy | +0.109 |
Neg logit contributions | |
ONS | -0.131 |
EMS | -0.127 |
LIST | -0.126 |
Kind | -0.125 |
Imper | -0.122 |
Token | 2005 |
Token ID | 5075 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
banter | +0.443 |
puter | +0.430 |
egu | +0.428 |
dop | +0.411 |
ousy | +0.404 |
Neg logit contributions | |
ONS | -0.619 |
EMS | -0.605 |
LIST | -0.600 |
Kind | -0.592 |
ALS | -0.580 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ONS | +0.158 |
EMS | +0.153 |
LIST | +0.152 |
Kind | +0.151 |
Imper | +0.147 |
Neg logit contributions | |
banter | -0.127 |
puter | -0.126 |
egu | -0.124 |
ottesville | -0.119 |
ousy | -0.119 |
Token | The |
Token ID | 383 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
banter | +0.173 |
egu | +0.169 |
puter | +0.169 |
ousy | +0.163 |
ottesville | +0.161 |
Neg logit contributions | |
ONS | -0.186 |
EMS | -0.181 |
LIST | -0.178 |
Kind | -0.177 |
ALS | -0.172 |
Token | latter |
Token ID | 6846 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
ONS | +0.292 |
EMS | +0.284 |
LIST | +0.281 |
Kind | +0.279 |
ALS | +0.271 |
Neg logit contributions | |
banter | -0.267 |
puter | -0.262 |
egu | -0.260 |
dop | -0.249 |
ottesville | -0.248 |
Token | created |
Token ID | 2727 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
banter | +4.109 |
puter | +3.942 |
egu | +3.920 |
dop | +3.860 |
dissip | +3.818 |
Neg logit contributions | |
ONS | -5.014 |
EMS | -4.886 |
LIST | -4.831 |
Kind | -4.763 |
ALS | -4.661 |
Token | a |
Token ID | 257 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
ONS | +0.587 |
EMS | +0.569 |
LIST | +0.563 |
Kind | +0.560 |
ALS | +0.542 |
Neg logit contributions | |
banter | -0.634 |
puter | -0.625 |
egu | -0.620 |
dop | -0.597 |
ottesville | -0.596 |
Token | sense |
Token ID | 2565 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
ONS | +0.692 |
EMS | +0.670 |
LIST | +0.664 |
Kind | +0.661 |
ALS | +0.642 |
Neg logit contributions | |
banter | -0.621 |
puter | -0.615 |
egu | -0.609 |
ottesville | -0.582 |
dop | -0.582 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ONS | +1.859 |
LIST | +1.794 |
EMS | +1.793 |
Kind | +1.779 |
Imper | +1.730 |
Neg logit contributions | |
banter | -1.768 |
puter | -1.766 |
egu | -1.737 |
ottesville | -1.685 |
ousy | -1.657 |
Token | victory |
Token ID | 5373 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
banter | +0.775 |
puter | +0.750 |
egu | +0.744 |
dop | +0.728 |
ottesville | +0.719 |
Neg logit contributions | |
ONS | -0.786 |
EMS | -0.760 |
Kind | -0.747 |
LIST | -0.746 |
ALS | -0.727 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
banter | +0.287 |
puter | +0.285 |
egu | +0.280 |
dop | +0.267 |
ottesville | +0.267 |
Neg logit contributions | |
ONS | -0.397 |
EMS | -0.385 |
LIST | -0.382 |
Kind | -0.380 |
Imper | -0.370 |
Token | The |
Token ID | 383 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
banter | +0.104 |
puter | +0.103 |
egu | +0.102 |
ousy | +0.098 |
ottesville | +0.098 |
Neg logit contributions | |
ONS | -0.108 |
EMS | -0.105 |
LIST | -0.104 |
Kind | -0.103 |
Imper | -0.100 |
Token | BBC |
Token ID | 7823 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
banter | +0.082 |
puter | +0.081 |
egu | +0.081 |
dop | +0.077 |
ottesville | +0.077 |
Neg logit contributions | |
ONS | -0.093 |
EMS | -0.090 |
LIST | -0.090 |
Kind | -0.089 |
ALS | -0.086 |
Token | 's |
Token ID | 338 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
ONS | +0.174 |
EMS | +0.169 |
LIST | +0.168 |
Kind | +0.167 |
Imper | +0.162 |
Neg logit contributions | |
banter | -0.129 |
puter | -0.128 |
egu | -0.126 |
ottesville | -0.121 |
dop | -0.120 |
Token | Rupert |
Token ID | 34315 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
banter | +2.827 |
puter | +2.709 |
egu | +2.700 |
dop | +2.660 |
ottesville | +2.595 |
Neg logit contributions | |
ONS | -2.567 |
EMS | -2.510 |
LIST | -2.472 |
Kind | -2.461 |
ALS | -2.393 |
Token | Wing |
Token ID | 13405 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
banter | +1.100 |
egu | +1.057 |
puter | +1.051 |
ottesville | +1.017 |
dop | +1.016 |
Neg logit contributions | |
ONS | -1.077 |
EMS | -1.055 |
LIST | -1.046 |
Kind | -1.019 |
ALS | -1.000 |
Token | field |
Token ID | 3245 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
banter | +5.899 |
puter | +5.584 |
egu | +5.500 |
ousy | +5.490 |
crunch | +5.475 |
Neg logit contributions | |
EMS | -3.264 |
ONS | -3.254 |
LIST | -3.239 |
Kind | -2.931 |
IOR | -2.929 |
Token | - |
Token ID | 12 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
banter | +0.188 |
puter | +0.186 |
egu | +0.184 |
ottesville | +0.176 |
ousy | +0.175 |
Neg logit contributions | |
ONS | -0.254 |
EMS | -0.246 |
LIST | -0.245 |
Kind | -0.244 |
Imper | -0.237 |
Token | Hay |
Token ID | 31306 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
puter | +0.530 |
banter | +0.529 |
egu | +0.522 |
ousy | +0.509 |
dop | +0.508 |
Neg logit contributions | |
ONS | -0.334 |
EMS | -0.328 |
LIST | -0.319 |
Imper | -0.313 |
ALS | -0.303 |
Token | es |
Token ID | 274 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
banter | +0.925 |
puter | +0.920 |
egu | +0.913 |
ottesville | +0.889 |
ousy | +0.886 |
Neg logit contributions | |
ONS | -0.420 |
EMS | -0.398 |
LIST | -0.393 |
Kind | -0.390 |
Imper | -0.370 |
Token | , |
Token ID | 11 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
ONS | +0.705 |
EMS | +0.684 |
LIST | +0.681 |
Kind | +0.677 |
Imper | +0.660 |
Neg logit contributions | |
banter | -0.520 |
puter | -0.519 |
egu | -0.511 |
ottesville | -0.488 |
ousy | -0.487 |
Token | Silver |
Token ID | 7698 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
banter | +0.598 |
puter | +0.590 |
egu | +0.584 |
dop | +0.558 |
ottesville | +0.557 |
Neg logit contributions | |
ONS | -0.721 |
EMS | -0.700 |
LIST | -0.696 |
Kind | -0.692 |
ALS | -0.671 |
Token | Phantom |
Token ID | 14407 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
banter | +0.115 |
puter | +0.114 |
egu | +0.113 |
ottesville | +0.109 |
ousy | +0.108 |
Neg logit contributions | |
ONS | -0.129 |
EMS | -0.125 |
LIST | -0.124 |
Kind | -0.124 |
Imper | -0.120 |
Token | falls |
Token ID | 8953 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
banter | +1.420 |
puter | +1.407 |
egu | +1.385 |
dop | +1.325 |
ottesville | +1.324 |
Neg logit contributions | |
ONS | -1.743 |
EMS | -1.694 |
LIST | -1.680 |
Kind | -1.672 |
Imper | -1.620 |
Token | into |
Token ID | 656 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ONS | +0.684 |
EMS | +0.662 |
LIST | +0.658 |
Kind | +0.655 |
Imper | +0.636 |
Neg logit contributions | |
banter | -0.625 |
puter | -0.621 |
egu | -0.614 |
ottesville | -0.590 |
ousy | -0.588 |
Token | the |
Token ID | 262 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ONS | +1.551 |
EMS | +1.503 |
LIST | +1.496 |
Kind | +1.489 |
Imper | +1.449 |
Neg logit contributions | |
banter | -1.303 |
puter | -1.297 |
egu | -1.281 |
ottesville | -1.232 |
ousy | -1.224 |
Token | latter |
Token ID | 6846 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
banter | +0.215 |
puter | +0.212 |
egu | +0.209 |
ottesville | +0.201 |
dop | +0.200 |
Neg logit contributions | |
ONS | -0.279 |
EMS | -0.271 |
LIST | -0.269 |
Kind | -0.267 |
ALS | -0.260 |
Token | category |
Token ID | 6536 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
banter | +4.211 |
egu | +4.014 |
dop | +3.977 |
puter | +3.953 |
ottesville | +3.913 |
Neg logit contributions | |
ONS | -4.753 |
EMS | -4.622 |
LIST | -4.508 |
Kind | -4.459 |
ALS | -4.445 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ONS | +1.063 |
EMS | +1.030 |
LIST | +1.026 |
Kind | +1.019 |
Imper | +0.991 |
Neg logit contributions | |
banter | -0.921 |
puter | -0.919 |
egu | -0.909 |
ottesville | -0.872 |
ousy | -0.866 |
Token | I |
Token ID | 314 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
banter | +0.101 |
puter | +0.100 |
egu | +0.099 |
ousy | +0.095 |
ottesville | +0.094 |
Neg logit contributions | |
ONS | -0.112 |
EMS | -0.108 |
LIST | -0.108 |
Kind | -0.107 |
ALS | -0.103 |
Token | � |
Token ID | 447 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
ONS | +0.952 |
EMS | +0.921 |
LIST | +0.914 |
Kind | +0.910 |
Imper | +0.887 |
Neg logit contributions | |
banter | -0.741 |
puter | -0.740 |
egu | -0.731 |
ottesville | -0.704 |
ousy | -0.698 |
Token | � |
Token ID | 247 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
banter | +0.059 |
puter | +0.058 |
egu | +0.058 |
ottesville | +0.055 |
ousy | +0.055 |
Neg logit contributions | |
ONS | -0.082 |
EMS | -0.079 |
LIST | -0.079 |
Kind | -0.078 |
Imper | -0.076 |
Token | across |
Token ID | 1973 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
banter | +0.559 |
puter | +0.551 |
egu | +0.547 |
dop | +0.523 |
ottesville | +0.523 |
Neg logit contributions | |
ONS | -0.662 |
EMS | -0.641 |
LIST | -0.639 |
Kind | -0.636 |
ALS | -0.616 |
Token | the |
Token ID | 262 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
ONS | +0.578 |
EMS | +0.557 |
LIST | +0.554 |
Kind | +0.550 |
Imper | +0.532 |
Neg logit contributions | |
banter | -0.674 |
puter | -0.670 |
egu | -0.663 |
ottesville | -0.641 |
ousy | -0.638 |
Token | globe |
Token ID | 13342 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
ONS | +0.540 |
EMS | +0.520 |
LIST | +0.517 |
Kind | +0.514 |
ALS | +0.496 |
Neg logit contributions | |
banter | -0.594 |
puter | -0.589 |
egu | -0.583 |
ottesville | -0.563 |
ousy | -0.560 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
ONS | +0.615 |
EMS | +0.595 |
LIST | +0.592 |
Kind | +0.588 |
Imper | +0.572 |
Neg logit contributions | |
banter | -0.545 |
puter | -0.543 |
egu | -0.536 |
ottesville | -0.515 |
ousy | -0.513 |
Token | The |
Token ID | 383 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
ONS | +0.258 |
EMS | +0.250 |
LIST | +0.248 |
Kind | +0.246 |
ALS | +0.239 |
Neg logit contributions | |
banter | -0.239 |
puter | -0.235 |
egu | -0.234 |
ottesville | -0.225 |
ousy | -0.225 |
Token | latter |
Token ID | 6846 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
ONS | +0.465 |
EMS | +0.450 |
LIST | +0.448 |
Kind | +0.445 |
ALS | +0.432 |
Neg logit contributions | |
banter | -0.406 |
puter | -0.401 |
egu | -0.397 |
ottesville | -0.382 |
dop | -0.380 |
Token | two |
Token ID | 734 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
banter | +3.964 |
egu | +3.739 |
puter | +3.713 |
dop | +3.693 |
crunch | +3.582 |
Neg logit contributions | |
ONS | -5.033 |
EMS | -4.855 |
Kind | -4.854 |
LIST | -4.833 |
ALS | -4.675 |
Token | problems |
Token ID | 2761 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
banter | +0.355 |
puter | +0.350 |
egu | +0.347 |
ottesville | +0.333 |
dop | +0.332 |
Neg logit contributions | |
ONS | -0.393 |
EMS | -0.380 |
LIST | -0.377 |
Kind | -0.377 |
ALS | -0.364 |
Token | — |
Token ID | 851 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
ONS | +0.642 |
EMS | +0.622 |
LIST | +0.618 |
Kind | +0.615 |
Imper | +0.598 |
Neg logit contributions | |
banter | -0.533 |
puter | -0.529 |
egu | -0.523 |
ottesville | -0.502 |
ousy | -0.499 |
Token | how |
Token ID | 703 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
ONS | +0.573 |
EMS | +0.555 |
LIST | +0.551 |
Kind | +0.549 |
ALS | +0.532 |
Neg logit contributions | |
banter | -0.521 |
puter | -0.516 |
egu | -0.510 |
ottesville | -0.491 |
ousy | -0.489 |
Token | to |
Token ID | 284 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
banter | +0.535 |
puter | +0.528 |
egu | +0.525 |
ottesville | +0.504 |
dop | +0.503 |
Neg logit contributions | |
ONS | -0.621 |
EMS | -0.602 |
LIST | -0.599 |
Kind | -0.597 |
ALS | -0.581 |
Token | 's |
Token ID | 338 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ONS | +0.849 |
EMS | +0.825 |
LIST | +0.817 |
Kind | +0.815 |
Imper | +0.795 |
Neg logit contributions | |
banter | -0.766 |
puter | -0.765 |
egu | -0.756 |
ottesville | -0.731 |
ousy | -0.720 |
Token | Fargo |
Token ID | 28125 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
banter | +1.321 |
puter | +1.293 |
egu | +1.278 |
dop | +1.234 |
ousy | +1.228 |
Neg logit contributions | |
ONS | -1.438 |
EMS | -1.390 |
LIST | -1.390 |
Kind | -1.373 |
ALS | -1.331 |
Token | and |
Token ID | 290 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
banter | +2.429 |
puter | +2.369 |
egu | +2.365 |
dop | +2.273 |
ousy | +2.224 |
Neg logit contributions | |
ONS | -3.146 |
EMS | -3.037 |
LIST | -3.019 |
Kind | -3.003 |
ALS | -2.905 |
Token | HBO |
Token ID | 18804 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
banter | +0.274 |
puter | +0.270 |
egu | +0.267 |
ousy | +0.256 |
dop | +0.256 |
Neg logit contributions | |
ONS | -0.291 |
EMS | -0.282 |
LIST | -0.280 |
Kind | -0.278 |
ALS | -0.269 |
Token | 's |
Token ID | 338 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ONS | +0.089 |
EMS | +0.086 |
LIST | +0.085 |
Kind | +0.085 |
Imper | +0.082 |
Neg logit contributions | |
banter | -0.079 |
puter | -0.079 |
egu | -0.078 |
ottesville | -0.075 |
ousy | -0.074 |
Token | True |
Token ID | 6407 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
banter | +1.686 |
puter | +1.633 |
egu | +1.623 |
dop | +1.556 |
ousy | +1.553 |
Neg logit contributions | |
ONS | -1.963 |
LIST | -1.901 |
EMS | -1.897 |
Kind | -1.863 |
ALS | -1.819 |
Token | Detective |
Token ID | 20220 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
egu | +3.270 |
banter | +3.270 |
comed | +3.126 |
Nurse | +3.105 |
puter | +3.047 |
Neg logit contributions | |
ONS | -5.361 |
LIST | -5.334 |
EMS | -5.178 |
IOR | -5.025 |
ALS | -4.995 |
Token | each |
Token ID | 1123 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
banter | +2.665 |
egu | +2.562 |
puter | +2.556 |
dop | +2.452 |
comed | +2.412 |
Neg logit contributions | |
ONS | -3.431 |
EMS | -3.349 |
LIST | -3.328 |
Kind | -3.317 |
ALS | -3.192 |
Token | had |
Token ID | 550 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
banter | +1.112 |
puter | +1.083 |
egu | +1.081 |
dop | +1.031 |
ousy | +1.019 |
Neg logit contributions | |
ONS | -1.332 |
EMS | -1.296 |
Kind | -1.289 |
LIST | -1.284 |
ALS | -1.233 |
Token | the |
Token ID | 262 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
ONS | +0.051 |
EMS | +0.049 |
LIST | +0.049 |
Kind | +0.049 |
ALS | +0.047 |
Neg logit contributions | |
banter | -0.048 |
puter | -0.047 |
egu | -0.047 |
dop | -0.045 |
ousy | -0.045 |
Token | benefit |
Token ID | 4414 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
banter | +0.555 |
puter | +0.538 |
egu | +0.537 |
dop | +0.519 |
ousy | +0.514 |
Neg logit contributions | |
ONS | -0.602 |
LIST | -0.580 |
EMS | -0.579 |
Kind | -0.574 |
ALS | -0.555 |
Token | vocal |
Token ID | 12435 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
banter | +0.270 |
puter | +0.266 |
egu | +0.263 |
dop | +0.253 |
ottesville | +0.252 |
Neg logit contributions | |
ONS | -0.289 |
EMS | -0.280 |
LIST | -0.279 |
Kind | -0.277 |
ALS | -0.268 |
Token | ists |
Token ID | 1023 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
ONS | +0.570 |
EMS | +0.553 |
LIST | +0.550 |
Kind | +0.546 |
Imper | +0.536 |
Neg logit contributions | |
banter | -0.386 |
puter | -0.385 |
egu | -0.380 |
ottesville | -0.365 |
ousy | -0.361 |
Token | Mir |
Token ID | 7381 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ONS | +0.623 |
EMS | +0.601 |
LIST | +0.597 |
Kind | +0.594 |
Imper | +0.576 |
Neg logit contributions | |
banter | -0.660 |
puter | -0.657 |
egu | -0.649 |
ottesville | -0.627 |
ousy | -0.623 |
Token | ja |
Token ID | 6592 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ONS | +0.979 |
EMS | +0.944 |
LIST | +0.936 |
Kind | +0.933 |
Imper | +0.901 |
Neg logit contributions | |
banter | -1.194 |
puter | -1.187 |
egu | -1.174 |
ottesville | -1.138 |
ousy | -1.131 |
Token | M |
Token ID | 337 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
banter | +1.034 |
puter | +1.023 |
egu | +1.017 |
ottesville | +0.975 |
ousy | +0.974 |
Neg logit contributions | |
ONS | -1.004 |
EMS | -0.969 |
LIST | -0.963 |
Kind | -0.950 |
ALS | -0.922 |
Token | ä |
Token ID | 11033 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
banter | +0.382 |
puter | +0.381 |
egu | +0.378 |
ottesville | +0.362 |
ousy | +0.362 |
Neg logit contributions | |
ONS | -0.433 |
EMS | -0.420 |
LIST | -0.419 |
Kind | -0.416 |
Imper | -0.404 |
Token | kel |
Token ID | 7750 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
puter | +3.800 |
egu | +3.744 |
banter | +3.736 |
dop | +3.522 |
ousy | +3.495 |
Neg logit contributions | |
ONS | -4.977 |
EMS | -4.892 |
LIST | -4.779 |
Kind | -4.743 |
Imper | -4.691 |
Token | ä |
Token ID | 11033 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
ONS | +0.141 |
EMS | +0.137 |
LIST | +0.136 |
Kind | +0.136 |
Imper | +0.132 |
Neg logit contributions | |
banter | -0.087 |
puter | -0.086 |
egu | -0.085 |
ottesville | -0.081 |
ousy | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
banter | +2.220 |
puter | +2.198 |
egu | +2.165 |
dop | +2.062 |
ousy | +2.050 |
Neg logit contributions | |
ONS | -2.890 |
EMS | -2.825 |
LIST | -2.789 |
Kind | -2.784 |
ALS | -2.695 |
Token | E |
Token ID | 412 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
ONS | +1.003 |
EMS | +0.967 |
LIST | +0.960 |
Kind | +0.955 |
Imper | +0.926 |
Neg logit contributions | |
banter | -1.114 |
puter | -1.109 |
egu | -1.096 |
ottesville | -1.060 |
ousy | -1.055 |
Token | e |
Token ID | 68 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
banter | +0.486 |
puter | +0.484 |
egu | +0.480 |
ottesville | +0.459 |
ousy | +0.459 |
Neg logit contributions | |
ONS | -0.555 |
EMS | -0.538 |
LIST | -0.535 |
Kind | -0.531 |
Imper | -0.516 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
banter | +0.444 |
puter | +0.438 |
egu | +0.429 |
dop | +0.411 |
ottesville | +0.411 |
Neg logit contributions | |
ONS | -0.599 |
EMS | -0.582 |
LIST | -0.579 |
Kind | -0.576 |
Imper | -0.561 |
Token | but |
Token ID | 475 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
banter | +0.672 |
puter | +0.662 |
egu | +0.652 |
dop | +0.626 |
ousy | +0.626 |
Neg logit contributions | |
ONS | -0.879 |
EMS | -0.855 |
LIST | -0.848 |
Kind | -0.844 |
Imper | -0.821 |
Token | typically |
Token ID | 6032 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
banter | +0.548 |
puter | +0.540 |
egu | +0.531 |
dop | +0.511 |
ousy | +0.510 |
Neg logit contributions | |
ONS | -0.689 |
EMS | -0.668 |
LIST | -0.663 |
Kind | -0.659 |
Imper | -0.643 |
Token | got |
Token ID | 1392 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
banter | +1.325 |
puter | +1.292 |
egu | +1.271 |
dop | +1.248 |
ousy | +1.222 |
Neg logit contributions | |
ONS | -1.618 |
EMS | -1.569 |
LIST | -1.556 |
Kind | -1.550 |
ALS | -1.513 |
Token | his |
Token ID | 465 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
banter | +0.078 |
puter | +0.077 |
egu | +0.076 |
dop | +0.073 |
ousy | +0.073 |
Neg logit contributions | |
ONS | -0.089 |
EMS | -0.087 |
LIST | -0.086 |
Kind | -0.086 |
Imper | -0.083 |
Token | best |
Token ID | 1266 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
banter | +0.660 |
puter | +0.644 |
egu | +0.637 |
dop | +0.613 |
ousy | +0.607 |
Neg logit contributions | |
ONS | -0.946 |
EMS | -0.920 |
LIST | -0.917 |
Kind | -0.912 |
Imper | -0.889 |
Token | results |
Token ID | 2482 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
banter | +3.543 |
egu | +3.293 |
puter | +3.289 |
dop | +3.268 |
comed | +3.163 |
Neg logit contributions | |
ONS | -5.205 |
LIST | -5.090 |
EMS | -5.051 |
Kind | -5.035 |
Imper | -4.946 |
Token | at |
Token ID | 379 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
banter | +0.491 |
puter | +0.486 |
egu | +0.479 |
dop | +0.460 |
ousy | +0.460 |
Neg logit contributions | |
ONS | -0.561 |
EMS | -0.543 |
LIST | -0.540 |
Kind | -0.538 |
Imper | -0.522 |
Token | night |
Token ID | 1755 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
banter | +1.098 |
puter | +1.082 |
egu | +1.068 |
ousy | +1.025 |
dop | +1.024 |
Neg logit contributions | |
ONS | -1.481 |
EMS | -1.438 |
LIST | -1.433 |
Kind | -1.422 |
Imper | -1.385 |
Token | when |
Token ID | 618 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
banter | +1.069 |
puter | +1.060 |
egu | +1.036 |
dop | +1.000 |
ousy | +1.000 |
Neg logit contributions | |
ONS | -1.344 |
EMS | -1.299 |
LIST | -1.296 |
Kind | -1.291 |
Imper | -1.260 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
banter | +0.017 |
puter | +0.016 |
egu | +0.016 |
ottesville | +0.016 |
ousy | +0.016 |
Neg logit contributions | |
ONS | -0.018 |
EMS | -0.018 |
LIST | -0.017 |
Kind | -0.017 |
Imper | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ONS | +0.659 |
EMS | +0.637 |
LIST | +0.632 |
Kind | +0.629 |
Imper | +0.610 |
Neg logit contributions | |
banter | -0.674 |
puter | -0.670 |
egu | -0.663 |
ottesville | -0.639 |
ousy | -0.636 |
Token | royalty |
Token ID | 29359 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ONS | +0.457 |
EMS | +0.443 |
LIST | +0.441 |
Kind | +0.438 |
Imper | +0.426 |
Neg logit contributions | |
banter | -0.372 |
puter | -0.369 |
egu | -0.365 |
ottesville | -0.350 |
ousy | -0.348 |
Token | free |
Token ID | 1479 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ONS | +1.776 |
EMS | +1.710 |
Kind | +1.704 |
LIST | +1.701 |
Imper | +1.650 |
Neg logit contributions | |
banter | -1.488 |
puter | -1.483 |
egu | -1.467 |
ottesville | -1.414 |
ousy | -1.408 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
banter | +0.176 |
puter | +0.174 |
egu | +0.172 |
ottesville | +0.165 |
ousy | +0.164 |
Neg logit contributions | |
ONS | -0.201 |
EMS | -0.195 |
LIST | -0.194 |
Kind | -0.193 |
Imper | -0.187 |
Token | J |
Token ID | 41 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ONS | +0.706 |
EMS | +0.678 |
LIST | +0.672 |
Kind | +0.667 |
Imper | +0.645 |
Neg logit contributions | |
banter | -0.983 |
puter | -0.978 |
egu | -0.969 |
ottesville | -0.938 |
ousy | -0.935 |
Token | ür |
Token ID | 25151 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
ONS | +0.070 |
EMS | +0.067 |
LIST | +0.067 |
Kind | +0.067 |
Imper | +0.065 |
Neg logit contributions | |
banter | -0.078 |
egu | -0.078 |
puter | -0.077 |
ousy | -0.075 |
ottesville | -0.075 |
Token | gen |
Token ID | 5235 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
banter | +4.958 |
egu | +4.939 |
puter | +4.859 |
ousy | +4.778 |
dop | +4.727 |
Neg logit contributions | |
ONS | -3.733 |
EMS | -3.630 |
LIST | -3.582 |
Kind | -3.466 |
ALS | -3.390 |
Token | Klopp |
Token ID | 43461 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
ONS | +2.034 |
EMS | +1.946 |
LIST | +1.946 |
Kind | +1.937 |
Imper | +1.878 |
Neg logit contributions | |
puter | -2.560 |
banter | -2.555 |
egu | -2.524 |
ottesville | -2.453 |
ousy | -2.427 |
Token | believes |
Token ID | 5804 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
banter | +2.453 |
egu | +2.347 |
puter | +2.320 |
dop | +2.234 |
ottesville | +2.224 |
Neg logit contributions | |
ONS | -3.022 |
EMS | -2.952 |
LIST | -2.916 |
Kind | -2.890 |
ALS | -2.831 |
Token | Liverpool |
Token ID | 11761 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
ONS | +0.475 |
EMS | +0.459 |
LIST | +0.455 |
Kind | +0.453 |
ALS | +0.438 |
Neg logit contributions | |
banter | -0.459 |
puter | -0.446 |
egu | -0.443 |
dop | -0.430 |
ottesville | -0.426 |
Token | would |
Token ID | 561 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ONS | +0.003 |
EMS | +0.003 |
LIST | +0.003 |
Kind | +0.003 |
Imper | +0.003 |
Neg logit contributions | |
banter | -0.002 |
puter | -0.002 |
egu | -0.002 |
dop | -0.002 |
ottesville | -0.002 |
Token | Gaza |
Token ID | 11010 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
banter | +1.133 |
puter | +1.103 |
egu | +1.102 |
dop | +1.055 |
ousy | +1.042 |
Neg logit contributions | |
ONS | -1.360 |
EMS | -1.323 |
LIST | -1.315 |
Kind | -1.305 |
ALS | -1.264 |
Token | internally |
Token ID | 20947 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ONS | +1.294 |
EMS | +1.255 |
LIST | +1.246 |
Kind | +1.242 |
Imper | +1.210 |
Neg logit contributions | |
banter | -1.000 |
puter | -0.995 |
egu | -0.981 |
ottesville | -0.943 |
ousy | -0.934 |
Token | but |
Token ID | 475 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ONS | +0.421 |
EMS | +0.408 |
LIST | +0.406 |
Kind | +0.404 |
Imper | +0.393 |
Neg logit contributions | |
banter | -0.315 |
puter | -0.313 |
egu | -0.309 |
ottesville | -0.296 |
ousy | -0.294 |
Token | views |
Token ID | 5009 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ONS | +0.084 |
EMS | +0.081 |
LIST | +0.080 |
Kind | +0.080 |
ALS | +0.078 |
Neg logit contributions | |
banter | -0.067 |
puter | -0.066 |
egu | -0.065 |
ottesville | -0.062 |
dop | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
ONS | +0.270 |
EMS | +0.262 |
LIST | +0.260 |
Kind | +0.258 |
ALS | +0.251 |
Neg logit contributions | |
banter | -0.228 |
puter | -0.226 |
egu | -0.224 |
ottesville | -0.214 |
ousy | -0.213 |
Token | latter |
Token ID | 6846 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
banter | +0.034 |
puter | +0.034 |
egu | +0.033 |
ottesville | +0.032 |
dop | +0.032 |
Neg logit contributions | |
ONS | -0.037 |
EMS | -0.036 |
LIST | -0.035 |
Kind | -0.035 |
ALS | -0.034 |
Token | as |
Token ID | 355 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
banter | +3.561 |
puter | +3.375 |
egu | +3.336 |
dop | +3.315 |
ousy | +3.232 |
Neg logit contributions | |
ONS | -5.056 |
EMS | -4.931 |
LIST | -4.837 |
Kind | -4.757 |
ALS | -4.697 |
Token | part |
Token ID | 636 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ONS | +1.422 |
EMS | +1.376 |
LIST | +1.367 |
Kind | +1.360 |
Imper | +1.320 |
Neg logit contributions | |
banter | -1.321 |
puter | -1.313 |
egu | -1.297 |
ottesville | -1.248 |
ousy | -1.242 |
Token | of |
Token ID | 286 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ONS | +0.911 |
LIST | +0.877 |
EMS | +0.877 |
Kind | +0.871 |
Imper | +0.848 |
Neg logit contributions | |
banter | -0.843 |
puter | -0.839 |
egu | -0.829 |
ottesville | -0.799 |
ousy | -0.792 |
Token | the |
Token ID | 262 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
ONS | +0.815 |
EMS | +0.787 |
LIST | +0.780 |
Kind | +0.776 |
Imper | +0.750 |
Neg logit contributions | |
banter | -0.922 |
puter | -0.916 |
egu | -0.907 |
ottesville | -0.876 |
ousy | -0.872 |
Token | state |
Token ID | 1181 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ONS | +0.470 |
EMS | +0.458 |
LIST | +0.452 |
Kind | +0.451 |
ALS | +0.437 |
Neg logit contributions | |
banter | -0.413 |
puter | -0.405 |
egu | -0.401 |
dop | -0.385 |
ottesville | -0.384 |
Token | deal |
Token ID | 1730 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
banter | +0.226 |
puter | +0.223 |
egu | +0.221 |
ottesville | +0.212 |
dop | +0.212 |
Neg logit contributions | |
ONS | -0.256 |
EMS | -0.248 |
LIST | -0.246 |
Kind | -0.245 |
Imper | -0.238 |
Token | to |
Token ID | 284 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
ONS | +2.566 |
EMS | +2.478 |
LIST | +2.470 |
Kind | +2.450 |
Imper | +2.387 |
Neg logit contributions | |
banter | -2.356 |
puter | -2.354 |
egu | -2.331 |
ottesville | -2.242 |
ousy | -2.228 |
Token | save |
Token ID | 3613 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
ONS | +0.775 |
EMS | +0.751 |
LIST | +0.747 |
Kind | +0.743 |
Imper | +0.724 |
Neg logit contributions | |
banter | -0.599 |
puter | -0.597 |
egu | -0.587 |
ottesville | -0.566 |
ousy | -0.560 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ONS | +0.736 |
EMS | +0.711 |
LIST | +0.707 |
Kind | +0.702 |
Imper | +0.683 |
Neg logit contributions | |
banter | -0.704 |
puter | -0.700 |
egu | -0.691 |
ottesville | -0.667 |
ousy | -0.663 |
Token | Def |
Token ID | 2896 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ONS | +0.124 |
EMS | +0.120 |
LIST | +0.119 |
Kind | +0.118 |
Imper | +0.114 |
Neg logit contributions | |
banter | -0.117 |
puter | -0.116 |
egu | -0.115 |
ottesville | -0.110 |
ousy | -0.110 |
Token | erred |
Token ID | 17436 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
egu | +1.565 |
banter | +1.556 |
puter | +1.548 |
ousy | +1.484 |
dop | +1.462 |
Neg logit contributions | |
ONS | -1.880 |
EMS | -1.827 |
LIST | -1.820 |
Kind | -1.799 |
Imper | -1.770 |
Token | Action |
Token ID | 7561 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
egu | +4.440 |
banter | +4.395 |
puter | +4.266 |
dop | +4.148 |
ottesville | +4.042 |
Neg logit contributions | |
ONS | -4.100 |
EMS | -4.062 |
LIST | -4.035 |
Kind | -4.016 |
ALS | -3.917 |
Token | for |
Token ID | 329 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
banter | +2.437 |
puter | +2.410 |
egu | +2.410 |
ottesville | +2.307 |
ousy | +2.304 |
Neg logit contributions | |
ONS | -2.075 |
EMS | -2.011 |
LIST | -1.988 |
Kind | -1.986 |
ALS | -1.904 |
Token | Childhood |
Token ID | 40992 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
banter | +0.210 |
puter | +0.209 |
egu | +0.204 |
ottesville | +0.200 |
dop | +0.198 |
Neg logit contributions | |
ONS | -0.194 |
EMS | -0.186 |
LIST | -0.184 |
Kind | -0.183 |
Imper | -0.179 |
Token | Arri |
Token ID | 27350 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
banter | +1.677 |
egu | +1.666 |
puter | +1.641 |
ousy | +1.558 |
ottesville | +1.549 |
Neg logit contributions | |
ONS | -2.449 |
EMS | -2.376 |
LIST | -2.354 |
Kind | -2.352 |
ALS | -2.271 |
Token | vals |
Token ID | 12786 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
egu | +2.976 |
banter | +2.936 |
puter | +2.887 |
ottesville | +2.796 |
ousy | +2.781 |
Neg logit contributions | |
ONS | -3.203 |
LIST | -3.080 |
EMS | -3.050 |
Kind | -3.044 |
Imper | -2.951 |
Token | of |
Token ID | 286 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
ONS | +0.122 |
EMS | +0.118 |
LIST | +0.117 |
Kind | +0.116 |
ALS | +0.113 |
Neg logit contributions | |
banter | -0.099 |
puter | -0.097 |
egu | -0.097 |
ousy | -0.092 |
ottesville | -0.092 |
Token | Transportation |
Token ID | 15198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ONS | +0.271 |
EMS | +0.262 |
LIST | +0.261 |
Kind | +0.259 |
Imper | +0.250 |
Neg logit contributions | |
banter | -0.275 |
puter | -0.272 |
egu | -0.270 |
dop | -0.258 |
ousy | -0.258 |
Token | . |
Token ID | 13 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
puter | +0.924 |
banter | +0.919 |
egu | +0.899 |
ousy | +0.861 |
dop | +0.860 |
Neg logit contributions | |
ONS | -1.125 |
EMS | -1.090 |
LIST | -1.088 |
Kind | -1.086 |
Imper | -1.043 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ONS | +0.553 |
EMS | +0.535 |
LIST | +0.531 |
Kind | +0.528 |
ALS | +0.510 |
Neg logit contributions | |
banter | -0.521 |
puter | -0.516 |
egu | -0.511 |
ousy | -0.491 |
ottesville | -0.490 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ONS | +0.083 |
EMS | +0.080 |
LIST | +0.079 |
Kind | +0.079 |
Imper | +0.077 |
Neg logit contributions | |
banter | -0.076 |
puter | -0.075 |
egu | -0.075 |
ousy | -0.072 |
ottesville | -0.072 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
puter | +0.127 |
banter | +0.127 |
egu | +0.126 |
ousy | +0.121 |
ottesville | +0.121 |
Neg logit contributions | |
ONS | -0.094 |
EMS | -0.089 |
LIST | -0.089 |
Kind | -0.088 |
Imper | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
banter | +3.858 |
egu | +3.788 |
puter | +3.749 |
ottesville | +3.581 |
ousy | +3.567 |
Neg logit contributions | |
ONS | -4.712 |
EMS | -4.571 |
Kind | -4.553 |
LIST | -4.483 |
Imper | -4.407 |
Token |
|
Token ID | 198 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
banter | +0.600 |
egu | +0.587 |
puter | +0.582 |
ousy | +0.560 |
dop | +0.558 |
Neg logit contributions | |
ONS | -0.683 |
EMS | -0.662 |
LIST | -0.655 |
Kind | -0.650 |
Imper | -0.636 |
Token | � |
Token ID | 447 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
puter | +0.754 |
banter | +0.751 |
egu | +0.751 |
ousy | +0.723 |
dop | +0.719 |
Neg logit contributions | |
ONS | -0.572 |
EMS | -0.544 |
Imper | -0.538 |
LIST | -0.537 |
Kind | -0.534 |
Token | � |
Token ID | 250 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
puter | +1.947 |
banter | +1.944 |
egu | +1.933 |
ottesville | +1.870 |
dop | +1.849 |
Neg logit contributions | |
ONS | -1.422 |
EMS | -1.365 |
Kind | -1.356 |
LIST | -1.336 |
Imper | -1.301 |
Token | If |
Token ID | 1532 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ONS | +0.273 |
EMS | +0.264 |
LIST | +0.263 |
Kind | +0.261 |
Imper | +0.254 |
Neg logit contributions | |
banter | -0.255 |
puter | -0.254 |
egu | -0.251 |
ottesville | -0.241 |
ousy | -0.240 |
Token | lez |
Token ID | 36858 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
banter | +1.841 |
egu | +1.832 |
puter | +1.824 |
ousy | +1.759 |
dop | +1.754 |
Neg logit contributions | |
ONS | -1.510 |
EMS | -1.460 |
LIST | -1.450 |
Kind | -1.437 |
Imper | -1.408 |
Token | al |
Token ID | 282 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
banter | +0.265 |
egu | +0.262 |
puter | +0.260 |
ousy | +0.254 |
ottesville | +0.253 |
Neg logit contributions | |
ONS | -0.154 |
LIST | -0.147 |
EMS | -0.146 |
Kind | -0.145 |
Imper | -0.140 |
Token | told |
Token ID | 1297 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
banter | +0.239 |
puter | +0.235 |
egu | +0.233 |
dop | +0.223 |
ottesville | +0.222 |
Neg logit contributions | |
ONS | -0.323 |
EMS | -0.314 |
LIST | -0.312 |
Kind | -0.310 |
ALS | -0.301 |
Token | Matt |
Token ID | 4705 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
ONS | +1.011 |
EMS | +0.979 |
LIST | +0.972 |
Kind | +0.967 |
Imper | +0.939 |
Neg logit contributions | |
banter | -0.972 |
puter | -0.968 |
egu | -0.957 |
ottesville | -0.924 |
ousy | -0.916 |
Token | L |
Token ID | 406 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ONS | +0.591 |
EMS | +0.572 |
LIST | +0.567 |
Kind | +0.562 |
ALS | +0.547 |
Neg logit contributions | |
banter | -0.533 |
puter | -0.527 |
egu | -0.523 |
ousy | -0.507 |
ottesville | -0.504 |
Token | auer |
Token ID | 16261 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
egu | +1.316 |
banter | +1.308 |
puter | +1.261 |
ousy | +1.261 |
ottesville | +1.222 |
Neg logit contributions | |
ONS | -2.606 |
LIST | -2.566 |
EMS | -2.559 |
Kind | -2.552 |
Imper | -2.510 |
Token | in |
Token ID | 287 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
banter | +3.718 |
puter | +3.589 |
egu | +3.526 |
dop | +3.450 |
ousy | +3.446 |
Neg logit contributions | |
ONS | -4.924 |
EMS | -4.773 |
Kind | -4.695 |
LIST | -4.675 |
Imper | -4.533 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ONS | +0.399 |
EMS | +0.386 |
LIST | +0.384 |
Kind | +0.382 |
Imper | +0.371 |
Neg logit contributions | |
banter | -0.361 |
puter | -0.359 |
egu | -0.355 |
ottesville | -0.342 |
ousy | -0.340 |
Token | that |
Token ID | 326 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ONS | +0.266 |
EMS | +0.257 |
LIST | +0.256 |
Kind | +0.254 |
Imper | +0.247 |
Neg logit contributions | |
banter | -0.230 |
puter | -0.229 |
egu | -0.226 |
ottesville | -0.218 |
ousy | -0.216 |
Token | she |
Token ID | 673 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
banter | +0.518 |
puter | +0.509 |
egu | +0.505 |
dop | +0.485 |
ousy | +0.483 |
Neg logit contributions | |
ONS | -0.603 |
EMS | -0.585 |
LIST | -0.579 |
Kind | -0.577 |
Imper | -0.558 |
Token | � |
Token ID | 564 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
banter | +0.247 |
puter | +0.242 |
egu | +0.240 |
dop | +0.232 |
ottesville | +0.229 |
Neg logit contributions | |
ONS | -0.281 |
EMS | -0.271 |
LIST | -0.269 |
Kind | -0.268 |
ALS | -0.259 |
Token |
|
Token ID | 198 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
ONS | +0.006 |
EMS | +0.006 |
LIST | +0.006 |
Kind | +0.006 |
ALS | +0.005 |
Neg logit contributions | |
banter | -0.005 |
puter | -0.005 |
egu | -0.005 |
ottesville | -0.005 |
ousy | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
ONS | +0.025 |
EMS | +0.025 |
LIST | +0.024 |
Kind | +0.024 |
Imper | +0.024 |
Neg logit contributions | |
banter | -0.023 |
puter | -0.023 |
egu | -0.023 |
ousy | -0.022 |
ottesville | -0.022 |
Token | It |
Token ID | 1026 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
banter | +0.069 |
puter | +0.069 |
egu | +0.069 |
ottesville | +0.066 |
ousy | +0.066 |
Neg logit contributions | |
ONS | -0.051 |
EMS | -0.049 |
LIST | -0.048 |
Kind | -0.048 |
Imper | -0.047 |
Token | is |
Token ID | 318 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
banter | +0.180 |
puter | +0.177 |
egu | +0.176 |
ottesville | +0.169 |
dop | +0.168 |
Neg logit contributions | |
ONS | -0.210 |
EMS | -0.202 |
LIST | -0.202 |
Kind | -0.200 |
Imper | -0.195 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ONS | +0.596 |
EMS | +0.578 |
LIST | +0.574 |
Kind | +0.572 |
Imper | +0.556 |
Neg logit contributions | |
banter | -0.471 |
puter | -0.469 |
egu | -0.463 |
ottesville | -0.445 |
ousy | -0.442 |
Token | latter |
Token ID | 6846 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
ONS | +0.917 |
EMS | +0.888 |
LIST | +0.883 |
Kind | +0.878 |
Imper | +0.853 |
Neg logit contributions | |
banter | -0.809 |
puter | -0.803 |
egu | -0.794 |
ottesville | -0.763 |
ousy | -0.759 |
Token | case |
Token ID | 1339 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
banter | +3.850 |
puter | +3.600 |
dop | +3.580 |
egu | +3.545 |
crunch | +3.506 |
Neg logit contributions | |
ONS | -4.833 |
EMS | -4.676 |
LIST | -4.598 |
Kind | -4.510 |
ALS | -4.465 |
Token | that |
Token ID | 326 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
ONS | +0.001 |
EMS | +0.001 |
LIST | +0.001 |
Kind | +0.001 |
Imper | +0.001 |
Neg logit contributions | |
banter | -0.001 |
puter | -0.001 |
egu | -0.001 |
ottesville | -0.001 |
ousy | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ONS | +0.617 |
EMS | +0.598 |
LIST | +0.594 |
Kind | +0.591 |
Imper | +0.574 |
Neg logit contributions | |
banter | -0.539 |
puter | -0.535 |
egu | -0.529 |
ottesville | -0.508 |
ousy | -0.506 |
Token | already |
Token ID | 1541 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
banter | +0.714 |
puter | +0.699 |
egu | +0.690 |
dop | +0.664 |
ottesville | +0.656 |
Neg logit contributions | |
ONS | -0.992 |
EMS | -0.964 |
LIST | -0.958 |
Kind | -0.953 |
ALS | -0.927 |
Token | causing |
Token ID | 6666 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
ONS | +0.598 |
EMS | +0.580 |
LIST | +0.578 |
Kind | +0.574 |
Imper | +0.560 |
Neg logit contributions | |
banter | -0.447 |
puter | -0.446 |
egu | -0.440 |
ottesville | -0.422 |
ousy | -0.420 |
Token | through |
Token ID | 832 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
ONS | +1.195 |
EMS | +1.157 |
LIST | +1.149 |
Kind | +1.146 |
Imper | +1.113 |
Neg logit contributions | |
banter | -1.066 |
puter | -1.059 |
egu | -1.046 |
ottesville | -1.007 |
ousy | -1.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
banter | +0.357 |
puter | +0.349 |
egu | +0.346 |
ousy | +0.333 |
dop | +0.333 |
Neg logit contributions | |
ONS | -0.340 |
EMS | -0.329 |
LIST | -0.326 |
Kind | -0.323 |
ALS | -0.314 |
Token | portal |
Token ID | 17898 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
banter | +0.130 |
puter | +0.128 |
egu | +0.126 |
ottesville | +0.121 |
ousy | +0.121 |
Neg logit contributions | |
ONS | -0.142 |
EMS | -0.138 |
LIST | -0.137 |
Kind | -0.135 |
ALS | -0.132 |
Token | , |
Token ID | 11 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
banter | +1.347 |
puter | +1.323 |
egu | +1.291 |
dop | +1.240 |
ousy | +1.234 |
Neg logit contributions | |
ONS | -1.684 |
EMS | -1.636 |
LIST | -1.621 |
Kind | -1.615 |
ALS | -1.559 |
Token | laying |
Token ID | 16299 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
banter | +0.377 |
puter | +0.370 |
egu | +0.365 |
dop | +0.350 |
ottesville | +0.346 |
Neg logit contributions | |
ONS | -0.503 |
EMS | -0.490 |
LIST | -0.484 |
Kind | -0.482 |
ALS | -0.469 |
Token | waste |
Token ID | 7030 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
banter | +1.046 |
puter | +1.028 |
egu | +1.013 |
dop | +0.978 |
ottesville | +0.965 |
Neg logit contributions | |
ONS | -1.167 |
EMS | -1.141 |
LIST | -1.126 |
Kind | -1.105 |
ALS | -1.088 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ONS | +4.519 |
LIST | +4.320 |
Kind | +4.289 |
EMS | +4.254 |
Imper | +4.217 |
Neg logit contributions | |
puter | -5.496 |
banter | -5.470 |
egu | -5.403 |
ottesville | -5.316 |
ousy | -5.282 |
Token | everything |
Token ID | 2279 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ONS | +0.952 |
EMS | +0.920 |
LIST | +0.915 |
Kind | +0.911 |
Imper | +0.888 |
Neg logit contributions | |
banter | -0.898 |
puter | -0.896 |
egu | -0.884 |
ottesville | -0.854 |
ousy | -0.848 |
Token | in |
Token ID | 287 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
banter | +1.411 |
puter | +1.378 |
egu | +1.371 |
dop | +1.330 |
ottesville | +1.306 |
Neg logit contributions | |
ONS | -1.656 |
EMS | -1.604 |
LIST | -1.587 |
Kind | -1.575 |
ALS | -1.536 |
Token | sight |
Token ID | 6504 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ONS | +0.602 |
EMS | +0.583 |
LIST | +0.577 |
Kind | +0.573 |
ALS | +0.556 |
Neg logit contributions | |
banter | -0.591 |
puter | -0.584 |
egu | -0.581 |
ottesville | -0.557 |
dop | -0.554 |
Token |
|
Token ID | 198 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ONS | +0.894 |
EMS | +0.866 |
LIST | +0.860 |
Kind | +0.855 |
Imper | +0.830 |
Neg logit contributions | |
banter | -0.787 |
puter | -0.781 |
egu | -0.771 |
ottesville | -0.742 |
ousy | -0.738 |
Token | to |
Token ID | 284 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
banter | +0.090 |
puter | +0.088 |
egu | +0.087 |
dop | +0.084 |
ottesville | +0.084 |
Neg logit contributions | |
ONS | -0.104 |
EMS | -0.101 |
LIST | -0.100 |
Kind | -0.100 |
Imper | -0.097 |
Token | Dh |
Token ID | 20529 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
ONS | +0.105 |
EMS | +0.101 |
LIST | +0.101 |
Kind | +0.100 |
Imper | +0.097 |
Neg logit contributions | |
banter | -0.101 |
puter | -0.100 |
egu | -0.099 |
dop | -0.095 |
ousy | -0.095 |
Token | oni |
Token ID | 14651 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
ONS | +0.690 |
EMS | +0.669 |
LIST | +0.664 |
Kind | +0.661 |
Imper | +0.643 |
Neg logit contributions | |
banter | -0.566 |
puter | -0.562 |
egu | -0.554 |
ottesville | -0.532 |
ousy | -0.529 |
Token | . |
Token ID | 13 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
banter | +0.050 |
puter | +0.050 |
egu | +0.049 |
ottesville | +0.047 |
ousy | +0.047 |
Neg logit contributions | |
ONS | -0.061 |
EMS | -0.059 |
LIST | -0.058 |
Kind | -0.058 |
Imper | -0.056 |
Token | Oh |
Token ID | 3966 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ONS | +0.447 |
EMS | +0.432 |
LIST | +0.429 |
Kind | +0.426 |
Imper | +0.414 |
Neg logit contributions | |
banter | -0.407 |
puter | -0.403 |
egu | -0.399 |
ottesville | -0.383 |
ousy | -0.382 |
Token | dear |
Token ID | 13674 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
ONS | +0.951 |
EMS | +0.923 |
LIST | +0.918 |
Kind | +0.914 |
Imper | +0.890 |
Neg logit contributions | |
banter | -0.746 |
puter | -0.742 |
egu | -0.732 |
ottesville | -0.703 |
ousy | -0.698 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ONS | +4.705 |
EMS | +4.572 |
LIST | +4.561 |
Kind | +4.551 |
Imper | +4.492 |
Neg logit contributions | |
puter | -4.508 |
egu | -4.433 |
banter | -4.433 |
ottesville | -4.335 |
ousy | -4.242 |
Token | Pressure |
Token ID | 30980 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ONS | +0.987 |
EMS | +0.955 |
LIST | +0.949 |
Kind | +0.944 |
Imper | +0.917 |
Neg logit contributions | |
banter | -0.884 |
puter | -0.879 |
egu | -0.868 |
ottesville | -0.835 |
ousy | -0.831 |
Token | ? |
Token ID | 30 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
ONS | +0.090 |
EMS | +0.087 |
LIST | +0.087 |
Kind | +0.086 |
ALS | +0.084 |
Neg logit contributions | |
banter | -0.076 |
puter | -0.075 |
egu | -0.074 |
ousy | -0.071 |
ottesville | -0.071 |
Token | Or |
Token ID | 1471 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
banter | +0.669 |
puter | +0.655 |
egu | +0.651 |
ousy | +0.625 |
dop | +0.624 |
Neg logit contributions | |
ONS | -0.755 |
EMS | -0.733 |
LIST | -0.728 |
Kind | -0.719 |
ALS | -0.702 |
Token | over |
Token ID | 625 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
banter | +1.059 |
puter | +1.030 |
egu | +1.019 |
dop | +0.987 |
ousy | +0.977 |
Neg logit contributions | |
ONS | -1.175 |
EMS | -1.144 |
LIST | -1.136 |
Kind | -1.124 |
ALS | -1.095 |
Token | ; |
Token ID | 2162 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
banter | +0.123 |
puter | +0.121 |
egu | +0.121 |
dop | +0.118 |
ousy | +0.116 |
Neg logit contributions | |
ONS | -0.074 |
EMS | -0.070 |
LIST | -0.070 |
Kind | -0.068 |
ALS | -0.067 |
Token | } |
Token ID | 1782 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
banter | +2.538 |
egu | +2.473 |
puter | +2.453 |
dop | +2.427 |
ousy | +2.373 |
Neg logit contributions | |
ONS | -2.704 |
EMS | -2.583 |
LIST | -2.549 |
Kind | -2.515 |
ALS | -2.467 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
banter | +0.026 |
puter | +0.025 |
egu | +0.025 |
dop | +0.024 |
ottesville | +0.024 |
Neg logit contributions | |
ONS | -0.023 |
EMS | -0.023 |
LIST | -0.022 |
Kind | -0.022 |
Imper | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
ONS | +0.813 |
EMS | +0.786 |
LIST | +0.780 |
Kind | +0.776 |
Imper | +0.753 |
Neg logit contributions | |
banter | -0.786 |
puter | -0.779 |
egu | -0.772 |
ottesville | -0.742 |
ousy | -0.740 |
Token | In |
Token ID | 818 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
ONS | +0.533 |
EMS | +0.511 |
LIST | +0.507 |
Kind | +0.501 |
Imper | +0.489 |
Neg logit contributions | |
banter | -0.713 |
puter | -0.712 |
egu | -0.707 |
ottesville | -0.683 |
ousy | -0.680 |
Token | order |
Token ID | 1502 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
ONS | +0.732 |
EMS | +0.711 |
LIST | +0.705 |
Kind | +0.699 |
ALS | +0.680 |
Neg logit contributions | |
banter | -0.616 |
puter | -0.612 |
egu | -0.606 |
ottesville | -0.578 |
dop | -0.577 |
Token | to |
Token ID | 284 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
ONS | +3.974 |
LIST | +3.859 |
Kind | +3.827 |
EMS | +3.812 |
Imper | +3.696 |
Neg logit contributions | |
banter | -4.813 |
puter | -4.778 |
egu | -4.750 |
ottesville | -4.673 |
ousy | -4.562 |
Token | perform |
Token ID | 1620 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ONS | +2.594 |
EMS | +2.501 |
LIST | +2.493 |
Kind | +2.479 |
Imper | +2.430 |
Neg logit contributions | |
puter | -2.323 |
banter | -2.309 |
egu | -2.278 |
ottesville | -2.234 |
ousy | -2.203 |
Token | the |
Token ID | 262 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
ONS | +1.634 |
EMS | +1.581 |
LIST | +1.570 |
Kind | +1.559 |
ALS | +1.513 |
Neg logit contributions | |
banter | -1.436 |
puter | -1.420 |
egu | -1.407 |
dop | -1.349 |
ottesville | -1.348 |
Token | load |
Token ID | 3440 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ONS | +1.910 |
EMS | +1.845 |
LIST | +1.833 |
Kind | +1.822 |
Imper | +1.766 |
Neg logit contributions | |
banter | -1.896 |
puter | -1.883 |
egu | -1.862 |
ottesville | -1.793 |
ousy | -1.785 |
Token | , |
Token ID | 11 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ONS | +1.856 |
EMS | +1.788 |
LIST | +1.775 |
Kind | +1.764 |
Imper | +1.706 |
Neg logit contributions | |
banter | -2.145 |
puter | -2.132 |
egu | -2.110 |
ottesville | -2.039 |
ousy | -2.030 |
Token | woman |
Token ID | 2415 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ONS | +0.777 |
EMS | +0.753 |
LIST | +0.749 |
Kind | +0.745 |
Imper | +0.724 |
Neg logit contributions | |
banter | -0.641 |
puter | -0.637 |
egu | -0.629 |
ottesville | -0.604 |
ousy | -0.601 |
Token | was |
Token ID | 373 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ONS | +0.805 |
EMS | +0.780 |
LIST | +0.775 |
Kind | +0.771 |
Imper | +0.749 |
Neg logit contributions | |
banter | -0.680 |
puter | -0.675 |
egu | -0.665 |
ottesville | -0.639 |
ousy | -0.636 |
Token | riding |
Token ID | 10311 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
ONS | +1.529 |
EMS | +1.485 |
LIST | +1.476 |
Kind | +1.468 |
Imper | +1.428 |
Neg logit contributions | |
banter | -1.222 |
puter | -1.215 |
egu | -1.201 |
ottesville | -1.152 |
ousy | -1.145 |
Token | her |
Token ID | 607 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ONS | +2.479 |
EMS | +2.394 |
LIST | +2.381 |
Kind | +2.369 |
Imper | +2.304 |
Neg logit contributions | |
banter | -2.485 |
puter | -2.478 |
egu | -2.453 |
ottesville | -2.367 |
ousy | -2.350 |
Token | bike |
Token ID | 7161 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ONS | +0.841 |
EMS | +0.812 |
LIST | +0.807 |
Kind | +0.801 |
ALS | +0.778 |
Neg logit contributions | |
banter | -0.762 |
puter | -0.754 |
egu | -0.743 |
ottesville | -0.715 |
dop | -0.714 |
Token | north |
Token ID | 5093 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
ONS | +1.382 |
EMS | +1.336 |
LIST | +1.325 |
Kind | +1.319 |
Imper | +1.278 |
Neg logit contributions | |
banter | -1.316 |
puter | -1.305 |
egu | -1.285 |
ottesville | -1.235 |
dop | -1.234 |
Token | bound |
Token ID | 7784 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ONS | +3.618 |
EMS | +3.471 |
LIST | +3.436 |
Kind | +3.407 |
Imper | +3.350 |
Neg logit contributions | |
puter | -5.178 |
banter | -5.163 |
egu | -5.158 |
ottesville | -4.957 |
ousy | -4.944 |
Token | on |
Token ID | 319 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ONS | +1.021 |
EMS | +0.987 |
LIST | +0.980 |
Kind | +0.974 |
Imper | +0.940 |
Neg logit contributions | |
banter | -0.995 |
puter | -0.981 |
egu | -0.970 |
ottesville | -0.933 |
dop | -0.933 |
Token | Pennsylvania |
Token ID | 9589 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
ONS | +1.104 |
EMS | +1.066 |
LIST | +1.058 |
Kind | +1.052 |
Imper | +1.019 |
Neg logit contributions | |
banter | -1.181 |
puter | -1.173 |
egu | -1.161 |
ottesville | -1.120 |
ousy | -1.115 |
Token | Street |
Token ID | 3530 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
banter | +0.833 |
puter | +0.820 |
egu | +0.816 |
ottesville | +0.794 |
ousy | +0.794 |
Neg logit contributions | |
ONS | -0.550 |
EMS | -0.523 |
LIST | -0.521 |
Kind | -0.512 |
Imper | -0.489 |
Token | , |
Token ID | 11 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
banter | +1.089 |
puter | +1.058 |
egu | +1.049 |
dop | +1.014 |
ousy | +1.009 |
Neg logit contributions | |
ONS | -1.318 |
LIST | -1.266 |
EMS | -1.262 |
Kind | -1.251 |
ALS | -1.213 |
Token | worked |
Token ID | 3111 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
ONS | +0.379 |
EMS | +0.368 |
LIST | +0.365 |
Kind | +0.363 |
Imper | +0.352 |
Neg logit contributions | |
banter | -0.334 |
puter | -0.330 |
egu | -0.327 |
ottesville | -0.314 |
ousy | -0.312 |
Token | in |
Token ID | 287 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
ONS | +0.752 |
EMS | +0.728 |
LIST | +0.722 |
Kind | +0.718 |
Imper | +0.697 |
Neg logit contributions | |
banter | -0.697 |
puter | -0.690 |
egu | -0.683 |
ottesville | -0.656 |
ousy | -0.654 |
Token | his |
Token ID | 465 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
ONS | +1.843 |
EMS | +1.777 |
LIST | +1.764 |
Kind | +1.756 |
Imper | +1.704 |
Neg logit contributions | |
banter | -1.959 |
puter | -1.956 |
egu | -1.932 |
ottesville | -1.868 |
ousy | -1.857 |
Token | individual |
Token ID | 1981 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ONS | +0.384 |
EMS | +0.375 |
LIST | +0.371 |
Kind | +0.367 |
ALS | +0.356 |
Neg logit contributions | |
banter | -0.319 |
puter | -0.313 |
egu | -0.308 |
dop | -0.297 |
ottesville | -0.296 |
Token | capacity |
Token ID | 5339 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
banter | +0.892 |
puter | +0.876 |
egu | +0.859 |
ottesville | +0.825 |
dop | +0.821 |
Neg logit contributions | |
ONS | -1.239 |
EMS | -1.207 |
LIST | -1.198 |
Kind | -1.186 |
ALS | -1.155 |
Token | whole |
Token ID | 2187 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
banter | +0.107 |
puter | +0.105 |
egu | +0.104 |
ottesville | +0.100 |
dop | +0.100 |
Neg logit contributions | |
ONS | -0.118 |
EMS | -0.115 |
LIST | -0.114 |
Kind | -0.113 |
Imper | -0.110 |
Token | living |
Token ID | 2877 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
ONS | +4.275 |
LIST | +4.127 |
EMS | +4.053 |
Kind | +4.039 |
Imper | +3.901 |
Neg logit contributions | |
puter | -4.446 |
egu | -4.415 |
banter | -4.414 |
ousy | -4.243 |
ottesville | -4.229 |
Token | in |
Token ID | 287 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ONS | +2.747 |
EMS | +2.640 |
LIST | +2.638 |
Kind | +2.620 |
Imper | +2.545 |
Neg logit contributions | |
puter | -2.714 |
banter | -2.709 |
egu | -2.693 |
ottesville | -2.589 |
ousy | -2.580 |
Token | London |
Token ID | 3576 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
ONS | +1.461 |
EMS | +1.412 |
LIST | +1.403 |
Kind | +1.396 |
Imper | +1.354 |
Neg logit contributions | |
banter | -1.423 |
puter | -1.415 |
egu | -1.399 |
ottesville | -1.348 |
ousy | -1.341 |
Token | for |
Token ID | 329 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
banter | +0.463 |
puter | +0.459 |
egu | +0.451 |
ottesville | +0.436 |
ousy | +0.433 |
Neg logit contributions | |
ONS | -0.531 |
EMS | -0.512 |
LIST | -0.510 |
Kind | -0.506 |
ALS | -0.490 |
Token | years |
Token ID | 812 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
ONS | +0.622 |
EMS | +0.603 |
LIST | +0.600 |
Kind | +0.596 |
Imper | +0.578 |
Neg logit contributions | |
banter | -0.543 |
puter | -0.538 |
egu | -0.531 |
ottesville | -0.510 |
ousy | -0.508 |
Token | Th |
Token ID | 536 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
banter | +0.889 |
puter | +0.883 |
egu | +0.872 |
ottesville | +0.852 |
ousy | +0.852 |
Neg logit contributions | |
ONS | -0.423 |
EMS | -0.406 |
LIST | -0.398 |
Kind | -0.392 |
ALS | -0.375 |
Token | ru |
Token ID | 622 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ONS | +1.204 |
EMS | +1.173 |
LIST | +1.167 |
Kind | +1.166 |
Imper | +1.138 |
Neg logit contributions | |
banter | -0.526 |
puter | -0.525 |
egu | -0.507 |
ottesville | -0.479 |
dop | -0.473 |
Token | , |
Token ID | 11 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
banter | +0.852 |
puter | +0.836 |
egu | +0.825 |
ottesville | +0.798 |
ousy | +0.795 |
Neg logit contributions | |
ONS | -1.086 |
EMS | -1.053 |
LIST | -1.043 |
Kind | -1.034 |
ALS | -1.005 |
Token | Thomas |
Token ID | 5658 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ONS | +0.504 |
EMS | +0.485 |
LIST | +0.482 |
Kind | +0.479 |
Imper | +0.462 |
Neg logit contributions | |
banter | -0.563 |
puter | -0.558 |
egu | -0.552 |
ottesville | -0.533 |
ousy | -0.532 |
Token | imb |
Token ID | 33966 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ONS | +0.849 |
EMS | +0.822 |
LIST | +0.817 |
Kind | +0.814 |
Imper | +0.794 |
Neg logit contributions | |
banter | -0.681 |
puter | -0.679 |
egu | -0.671 |
ottesville | -0.643 |
ousy | -0.640 |
Token | ib |
Token ID | 571 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
ONS | +1.268 |
EMS | +1.203 |
LIST | +1.192 |
Kind | +1.192 |
ALS | +1.146 |
Neg logit contributions | |
banter | -1.890 |
puter | -1.882 |
egu | -1.854 |
ottesville | -1.803 |
dop | -1.797 |
Token | ed |
Token ID | 276 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ONS | +4.155 |
EMS | +3.945 |
Kind | +3.915 |
LIST | +3.892 |
ALS | +3.805 |
Neg logit contributions | |
puter | -4.639 |
banter | -4.589 |
ottesville | -4.433 |
egu | -4.413 |
dop | -4.406 |
Token | at |
Token ID | 379 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ONS | +1.809 |
EMS | +1.752 |
LIST | +1.740 |
Kind | +1.735 |
Imper | +1.689 |
Neg logit contributions | |
puter | -1.593 |
banter | -1.593 |
egu | -1.570 |
ottesville | -1.513 |
ousy | -1.504 |
Token | every |
Token ID | 790 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
ONS | +0.181 |
EMS | +0.176 |
LIST | +0.176 |
Kind | +0.175 |
Imper | +0.170 |
Neg logit contributions | |
banter | -0.113 |
puter | -0.112 |
egu | -0.110 |
ottesville | -0.105 |
ousy | -0.104 |
Token | stop |
Token ID | 2245 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
banter | +0.610 |
puter | +0.598 |
egu | +0.593 |
ottesville | +0.572 |
dop | +0.571 |
Neg logit contributions | |
ONS | -0.705 |
EMS | -0.681 |
LIST | -0.677 |
Kind | -0.669 |
ALS | -0.653 |
Token | . |
Token ID | 13 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
banter | +0.060 |
puter | +0.059 |
egu | +0.058 |
ousy | +0.056 |
ottesville | +0.056 |
Neg logit contributions | |
ONS | -0.069 |
EMS | -0.067 |
Kind | -0.066 |
LIST | -0.066 |
Imper | -0.064 |
Token | that |
Token ID | 326 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
banter | +0.308 |
puter | +0.301 |
egu | +0.299 |
dop | +0.289 |
ottesville | +0.286 |
Neg logit contributions | |
ONS | -0.306 |
EMS | -0.296 |
LIST | -0.293 |
Kind | -0.290 |
ALS | -0.281 |
Token | of |
Token ID | 286 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
banter | +0.203 |
puter | +0.199 |
egu | +0.197 |
dop | +0.190 |
ousy | +0.188 |
Neg logit contributions | |
ONS | -0.244 |
EMS | -0.238 |
LIST | -0.235 |
Kind | -0.232 |
ALS | -0.227 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ONS | +0.682 |
EMS | +0.660 |
LIST | +0.654 |
Kind | +0.647 |
ALS | +0.626 |
Neg logit contributions | |
banter | -0.765 |
puter | -0.754 |
egu | -0.748 |
dop | -0.721 |
ottesville | -0.720 |
Token | law |
Token ID | 1099 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ONS | +0.968 |
EMS | +0.944 |
LIST | +0.935 |
Kind | +0.926 |
ALS | +0.902 |
Neg logit contributions | |
banter | -0.807 |
puter | -0.792 |
egu | -0.784 |
dop | -0.754 |
ottesville | -0.750 |
Token | of |
Token ID | 286 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
ONS | +1.620 |
EMS | +1.566 |
LIST | +1.556 |
Kind | +1.551 |
Imper | +1.508 |
Neg logit contributions | |
banter | -1.413 |
puter | -1.405 |
egu | -1.390 |
ottesville | -1.336 |
ousy | -1.330 |
Token | Moses |
Token ID | 19010 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
ONS | +2.896 |
EMS | +2.775 |
LIST | +2.762 |
Kind | +2.757 |
Imper | +2.668 |
Neg logit contributions | |
puter | -3.855 |
banter | -3.847 |
egu | -3.805 |
ottesville | -3.692 |
ousy | -3.678 |
Token | as |
Token ID | 355 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
ONS | +4.515 |
Kind | +4.282 |
LIST | +4.265 |
EMS | +4.255 |
Imper | +4.194 |
Neg logit contributions | |
puter | -4.191 |
banter | -4.160 |
egu | -4.111 |
ottesville | -3.988 |
ousy | -3.969 |
Token | recorded |
Token ID | 6264 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ONS | +2.627 |
EMS | +2.529 |
Kind | +2.527 |
LIST | +2.518 |
Imper | +2.466 |
Neg logit contributions | |
puter | -1.976 |
banter | -1.973 |
egu | -1.951 |
ottesville | -1.877 |
ousy | -1.862 |
Token | in |
Token ID | 287 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
ONS | +1.116 |
EMS | +1.079 |
LIST | +1.073 |
Kind | +1.067 |
Imper | +1.036 |
Neg logit contributions | |
banter | -1.039 |
puter | -1.032 |
egu | -1.020 |
ottesville | -0.982 |
ousy | -0.977 |
Token | De |
Token ID | 1024 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ONS | +0.437 |
EMS | +0.421 |
LIST | +0.418 |
Kind | +0.414 |
ALS | +0.399 |
Neg logit contributions | |
banter | -0.520 |
puter | -0.512 |
egu | -0.508 |
dop | -0.490 |
ottesville | -0.487 |
Token | ut |
Token ID | 315 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ONS | +1.449 |
EMS | +1.400 |
LIST | +1.394 |
Kind | +1.382 |
Imper | +1.341 |
Neg logit contributions | |
banter | -1.303 |
puter | -1.296 |
egu | -1.279 |
ottesville | -1.228 |
ousy | -1.223 |
Token | with |
Token ID | 351 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
ONS | +0.046 |
EMS | +0.044 |
LIST | +0.044 |
Kind | +0.044 |
Imper | +0.043 |
Neg logit contributions | |
banter | -0.040 |
puter | -0.040 |
egu | -0.039 |
ottesville | -0.038 |
ousy | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
banter | +0.495 |
puter | +0.489 |
egu | +0.484 |
ottesville | +0.466 |
dop | +0.466 |
Neg logit contributions | |
ONS | -0.451 |
EMS | -0.433 |
LIST | -0.432 |
Kind | -0.430 |
ALS | -0.415 |
Token | patrol |
Token ID | 13969 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
banter | +0.341 |
puter | +0.337 |
egu | +0.332 |
dop | +0.314 |
ottesville | +0.314 |
Neg logit contributions | |
ONS | -0.559 |
EMS | -0.541 |
LIST | -0.539 |
Kind | -0.537 |
ALS | -0.524 |
Token | car |
Token ID | 1097 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
ONS | +0.705 |
EMS | +0.686 |
LIST | +0.681 |
Kind | +0.677 |
Imper | +0.660 |
Neg logit contributions | |
banter | -0.559 |
puter | -0.556 |
egu | -0.549 |
ottesville | -0.526 |
ousy | -0.524 |
Token | traveling |
Token ID | 11300 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
ONS | +2.408 |
EMS | +2.339 |
LIST | +2.323 |
Kind | +2.309 |
Imper | +2.251 |
Neg logit contributions | |
banter | -2.058 |
puter | -2.047 |
egu | -2.034 |
ottesville | -1.961 |
ousy | -1.948 |
Token | west |
Token ID | 7421 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
ONS | +2.393 |
EMS | +2.301 |
LIST | +2.284 |
Kind | +2.272 |
Imper | +2.204 |
Neg logit contributions | |
banter | -3.023 |
puter | -3.022 |
egu | -2.991 |
ottesville | -2.904 |
ousy | -2.884 |
Token | bound |
Token ID | 7784 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ONS | +3.396 |
EMS | +3.256 |
LIST | +3.217 |
Kind | +3.169 |
Imper | +3.096 |
Neg logit contributions | |
puter | -5.173 |
banter | -5.170 |
egu | -5.167 |
ottesville | -4.980 |
ousy | -4.966 |
Token | on |
Token ID | 319 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ONS | +1.065 |
EMS | +1.030 |
LIST | +1.024 |
Kind | +1.018 |
Imper | +0.986 |
Neg logit contributions | |
banter | -1.032 |
puter | -1.024 |
egu | -1.011 |
ottesville | -0.974 |
ousy | -0.970 |
Token | East |
Token ID | 3687 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
ONS | +1.012 |
EMS | +0.978 |
LIST | +0.969 |
Kind | +0.964 |
Imper | +0.939 |
Neg logit contributions | |
banter | -1.135 |
puter | -1.129 |
egu | -1.120 |
ottesville | -1.082 |
ousy | -1.074 |
Token | 16 |
Token ID | 1467 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ONS | +2.345 |
EMS | +2.274 |
Kind | +2.253 |
LIST | +2.251 |
Imper | +2.208 |
Neg logit contributions | |
banter | -2.363 |
puter | -2.356 |
egu | -2.330 |
dop | -2.236 |
ottesville | -2.236 |
Token | th |
Token ID | 400 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ONS | +1.252 |
EMS | +1.213 |
LIST | +1.206 |
Kind | +1.200 |
Imper | +1.167 |
Neg logit contributions | |
banter | -1.021 |
puter | -1.014 |
egu | -1.001 |
ottesville | -0.961 |
ousy | -0.956 |
Token | or |
Token ID | 393 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ONS | +1.280 |
LIST | +1.245 |
EMS | +1.244 |
Kind | +1.237 |
Imper | +1.210 |
Neg logit contributions | |
banter | -0.775 |
puter | -0.771 |
egu | -0.762 |
ottesville | -0.726 |
ousy | -0.720 |
Token | empty |
Token ID | 6565 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
ONS | +0.347 |
EMS | +0.335 |
LIST | +0.332 |
Kind | +0.330 |
Imper | +0.320 |
Neg logit contributions | |
banter | -0.349 |
puter | -0.346 |
egu | -0.342 |
ottesville | -0.330 |
ousy | -0.328 |
Token | Example |
Token ID | 17934 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ONS | +0.514 |
EMS | +0.492 |
LIST | +0.486 |
Kind | +0.483 |
Imper | +0.465 |
Neg logit contributions | |
banter | -0.766 |
puter | -0.761 |
egu | -0.754 |
ottesville | -0.731 |
ousy | -0.728 |
Token | : |
Token ID | 25 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
ONS | +0.925 |
EMS | +0.894 |
LIST | +0.893 |
Kind | +0.889 |
Imper | +0.860 |
Neg logit contributions | |
banter | -0.911 |
puter | -0.910 |
egu | -0.899 |
ottesville | -0.869 |
ousy | -0.862 |
Token | /* |
Token ID | 11900 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
banter | +0.039 |
puter | +0.038 |
egu | +0.038 |
ottesville | +0.036 |
dop | +0.036 |
Neg logit contributions | |
ONS | -0.040 |
EMS | -0.038 |
LIST | -0.038 |
Kind | -0.038 |
ALS | -0.036 |
Token | vim |
Token ID | 43907 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
banter | +0.694 |
puter | +0.691 |
egu | +0.681 |
ottesville | +0.656 |
dop | +0.654 |
Neg logit contributions | |
ONS | -0.638 |
EMS | -0.613 |
LIST | -0.602 |
Kind | -0.600 |
Imper | -0.583 |
Token | : |
Token ID | 25 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ONS | +4.124 |
LIST | +4.062 |
Kind | +4.028 |
EMS | +4.019 |
Imper | +3.848 |
Neg logit contributions | |
puter | -4.382 |
banter | -4.375 |
egu | -4.330 |
ottesville | -4.211 |
ousy | -4.156 |
Token | set |
Token ID | 900 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
banter | +0.300 |
puter | +0.297 |
egu | +0.295 |
ottesville | +0.282 |
ousy | +0.282 |
Neg logit contributions | |
ONS | -0.322 |
EMS | -0.311 |
LIST | -0.307 |
Kind | -0.306 |
Imper | -0.298 |
Token | a |
Token ID | 257 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ONS | +2.426 |
LIST | +2.358 |
EMS | +2.356 |
Kind | +2.339 |
Imper | +2.264 |
Neg logit contributions | |
banter | -2.249 |
puter | -2.243 |
egu | -2.213 |
ottesville | -2.135 |
ousy | -2.131 |
Token | i |
Token ID | 72 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
ONS | +0.403 |
EMS | +0.389 |
LIST | +0.384 |
Kind | +0.383 |
Imper | +0.372 |
Neg logit contributions | |
banter | -0.383 |
puter | -0.380 |
egu | -0.376 |
ottesville | -0.361 |
dop | -0.360 |
Token | tw |
Token ID | 665 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
ONS | +0.712 |
EMS | +0.689 |
LIST | +0.683 |
Kind | +0.679 |
Imper | +0.662 |
Neg logit contributions | |
banter | -0.616 |
puter | -0.612 |
egu | -0.604 |
ottesville | -0.580 |
ousy | -0.577 |
Token | had |
Token ID | 550 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ONS | +1.594 |
EMS | +1.535 |
LIST | +1.525 |
Kind | +1.519 |
Imper | +1.484 |
Neg logit contributions | |
banter | -1.478 |
puter | -1.473 |
egu | -1.455 |
ottesville | -1.407 |
ousy | -1.397 |
Token | fallen |
Token ID | 9292 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ONS | +0.489 |
EMS | +0.475 |
LIST | +0.472 |
Kind | +0.469 |
Imper | +0.456 |
Neg logit contributions | |
banter | -0.386 |
puter | -0.383 |
egu | -0.378 |
ottesville | -0.362 |
ousy | -0.360 |
Token | to |
Token ID | 284 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
ONS | +1.053 |
EMS | +1.019 |
LIST | +1.013 |
Kind | +1.007 |
Imper | +0.979 |
Neg logit contributions | |
banter | -0.937 |
puter | -0.932 |
egu | -0.921 |
ottesville | -0.886 |
ousy | -0.882 |
Token | him |
Token ID | 683 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ONS | +0.595 |
EMS | +0.576 |
LIST | +0.571 |
Kind | +0.569 |
Imper | +0.550 |
Neg logit contributions | |
banter | -0.571 |
puter | -0.566 |
egu | -0.561 |
ottesville | -0.538 |
ousy | -0.537 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
banter | +0.734 |
puter | +0.725 |
egu | +0.712 |
dop | +0.684 |
ottesville | +0.680 |
Neg logit contributions | |
ONS | -0.934 |
EMS | -0.907 |
LIST | -0.899 |
Kind | -0.896 |
ALS | -0.872 |
Token | Whole |
Token ID | 23431 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
ONS | +0.017 |
EMS | +0.017 |
LIST | +0.017 |
Kind | +0.017 |
ALS | +0.016 |
Neg logit contributions | |
banter | -0.016 |
puter | -0.016 |
egu | -0.016 |
ousy | -0.015 |
ottesville | -0.015 |
Token | cultures |
Token ID | 13817 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ONS | +4.647 |
EMS | +4.460 |
LIST | +4.446 |
Kind | +4.414 |
Imper | +4.387 |
Neg logit contributions | |
puter | -3.879 |
banter | -3.845 |
egu | -3.808 |
ousy | -3.686 |
ottesville | -3.652 |
Token | had |
Token ID | 550 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ONS | +1.202 |
EMS | +1.161 |
LIST | +1.154 |
Kind | +1.148 |
Imper | +1.117 |
Neg logit contributions | |
banter | -1.136 |
puter | -1.132 |
egu | -1.118 |
ottesville | -1.078 |
ousy | -1.072 |
Token | been |
Token ID | 587 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ONS | +1.179 |
EMS | +1.142 |
LIST | +1.137 |
Kind | +1.128 |
Imper | +1.101 |
Neg logit contributions | |
banter | -1.044 |
puter | -1.043 |
egu | -1.029 |
ottesville | -0.991 |
ousy | -0.987 |
Token | erased |
Token ID | 33588 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
ONS | +1.023 |
EMS | +0.994 |
LIST | +0.988 |
Kind | +0.983 |
Imper | +0.957 |
Neg logit contributions | |
banter | -0.737 |
puter | -0.731 |
egu | -0.722 |
ottesville | -0.690 |
ousy | -0.686 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
banter | +2.453 |
puter | +2.424 |
egu | +2.377 |
dop | +2.303 |
ousy | +2.291 |
Neg logit contributions | |
ONS | -3.251 |
EMS | -3.152 |
Kind | -3.123 |
LIST | -3.103 |
ALS | -3.034 |
Token | machine |
Token ID | 4572 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
banter | +0.419 |
puter | +0.412 |
egu | +0.403 |
dop | +0.392 |
ottesville | +0.385 |
Neg logit contributions | |
ONS | -0.508 |
EMS | -0.493 |
LIST | -0.492 |
Kind | -0.490 |
ALS | -0.473 |
Token | has |
Token ID | 468 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
banter | +0.425 |
puter | +0.422 |
egu | +0.415 |
ottesville | +0.398 |
dop | +0.397 |
Neg logit contributions | |
ONS | -0.505 |
EMS | -0.488 |
LIST | -0.486 |
Kind | -0.483 |
Imper | -0.470 |
Token | to |
Token ID | 284 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
banter | +0.204 |
puter | +0.203 |
egu | +0.198 |
dop | +0.192 |
ousy | +0.190 |
Neg logit contributions | |
ONS | -0.235 |
EMS | -0.228 |
LIST | -0.227 |
Kind | -0.225 |
ALS | -0.219 |
Token | move |
Token ID | 1445 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
banter | +0.993 |
puter | +0.979 |
egu | +0.964 |
dop | +0.925 |
ousy | +0.916 |
Neg logit contributions | |
ONS | -1.251 |
EMS | -1.216 |
LIST | -1.212 |
Kind | -1.206 |
ALS | -1.169 |
Token | the |
Token ID | 262 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
banter | +1.119 |
puter | +1.101 |
egu | +1.081 |
dop | +1.061 |
ousy | +1.022 |
Neg logit contributions | |
ONS | -1.426 |
LIST | -1.389 |
EMS | -1.387 |
Kind | -1.384 |
ALS | -1.335 |
Token | whole |
Token ID | 2187 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
ONS | +0.345 |
EMS | +0.335 |
LIST | +0.333 |
Kind | +0.332 |
ALS | +0.321 |
Neg logit contributions | |
banter | -0.291 |
puter | -0.288 |
egu | -0.284 |
dop | -0.273 |
ottesville | -0.272 |
Token | stack |
Token ID | 8931 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ONS | +4.282 |
EMS | +4.091 |
LIST | +4.087 |
Kind | +4.048 |
Imper | +3.964 |
Neg logit contributions | |
banter | -4.298 |
egu | -4.273 |
puter | -4.258 |
ottesville | -4.127 |
ousy | -4.101 |
Token | , |
Token ID | 11 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
ONS | +1.490 |
EMS | +1.443 |
LIST | +1.434 |
Kind | +1.426 |
Imper | +1.386 |
Neg logit contributions | |
banter | -1.272 |
puter | -1.263 |
egu | -1.249 |
ottesville | -1.200 |
ousy | -1.193 |
Token | by |
Token ID | 416 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ONS | +0.039 |
EMS | +0.038 |
LIST | +0.038 |
Kind | +0.038 |
ALS | +0.037 |
Neg logit contributions | |
banter | -0.029 |
puter | -0.029 |
egu | -0.028 |
dop | -0.027 |
ousy | -0.027 |
Token | only |
Token ID | 691 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ONS | +0.474 |
EMS | +0.460 |
LIST | +0.457 |
Kind | +0.455 |
Imper | +0.442 |
Neg logit contributions | |
banter | -0.389 |
puter | -0.386 |
egu | -0.381 |
ottesville | -0.364 |
ousy | -0.363 |
Token | an |
Token ID | 281 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ONS | +0.839 |
EMS | +0.812 |
LIST | +0.809 |
Kind | +0.803 |
ALS | +0.778 |
Neg logit contributions | |
banter | -0.759 |
puter | -0.753 |
egu | -0.742 |
dop | -0.713 |
ottesville | -0.711 |
Token | new |
Token ID | 649 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ONS | +1.457 |
EMS | +1.414 |
LIST | +1.405 |
Kind | +1.397 |
Imper | +1.365 |
Neg logit contributions | |
puter | -1.180 |
banter | -1.179 |
egu | -1.166 |
ottesville | -1.117 |
ousy | -1.106 |
Token | team |
Token ID | 1074 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
ONS | +1.044 |
EMS | +1.013 |
LIST | +1.007 |
Kind | +1.002 |
Imper | +0.976 |
Neg logit contributions | |
banter | -0.819 |
puter | -0.815 |
egu | -0.805 |
ottesville | -0.771 |
ousy | -0.766 |
Token | , |
Token ID | 11 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
banter | +0.382 |
puter | +0.379 |
egu | +0.373 |
ottesville | +0.358 |
ousy | +0.357 |
Neg logit contributions | |
ONS | -0.475 |
EMS | -0.460 |
LIST | -0.457 |
Kind | -0.455 |
Imper | -0.442 |
Token | and |
Token ID | 290 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
ONS | +0.282 |
EMS | +0.274 |
LIST | +0.272 |
Kind | +0.271 |
ALS | +0.262 |
Neg logit contributions | |
banter | -0.233 |
puter | -0.230 |
egu | -0.226 |
dop | -0.218 |
ousy | -0.217 |
Token | the |
Token ID | 262 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
banter | +0.017 |
puter | +0.016 |
egu | +0.016 |
dop | +0.015 |
ousy | +0.015 |
Neg logit contributions | |
ONS | -0.019 |
EMS | -0.018 |
LIST | -0.018 |
Kind | -0.018 |
ALS | -0.018 |
Token | seeds |
Token ID | 11904 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
ONS | +0.055 |
EMS | +0.053 |
LIST | +0.053 |
Kind | +0.053 |
ALS | +0.051 |
Neg logit contributions | |
banter | -0.047 |
puter | -0.046 |
egu | -0.045 |
dop | -0.044 |
ousy | -0.044 |
Token | were |
Token ID | 547 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ONS | +4.122 |
Kind | +3.918 |
EMS | +3.915 |
LIST | +3.898 |
Imper | +3.858 |
Neg logit contributions | |
egu | -4.351 |
banter | -4.326 |
puter | -4.312 |
ottesville | -4.241 |
ousy | -4.134 |
Token | thus |
Token ID | 4145 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ONS | +0.342 |
EMS | +0.331 |
LIST | +0.328 |
Kind | +0.326 |
Imper | +0.316 |
Neg logit contributions | |
banter | -0.346 |
puter | -0.343 |
egu | -0.339 |
dop | -0.327 |
ottesville | -0.326 |
Token | planted |
Token ID | 18969 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ONS | +2.398 |
EMS | +2.308 |
LIST | +2.294 |
Kind | +2.278 |
Imper | +2.214 |
Neg logit contributions | |
banter | -2.538 |
puter | -2.526 |
egu | -2.492 |
ottesville | -2.416 |
ousy | -2.398 |
Token | for |
Token ID | 329 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ONS | +2.175 |
EMS | +2.100 |
LIST | +2.090 |
Kind | +2.076 |
Imper | +2.017 |
Neg logit contributions | |
banter | -2.254 |
puter | -2.244 |
egu | -2.222 |
ottesville | -2.152 |
ousy | -2.130 |
Token | an |
Token ID | 281 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ONS | +0.339 |
EMS | +0.326 |
LIST | +0.324 |
Kind | +0.323 |
Imper | +0.312 |
Neg logit contributions | |
banter | -0.355 |
puter | -0.351 |
egu | -0.347 |
ousy | -0.334 |
ottesville | -0.334 |
Token | on |
Token ID | 319 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
banter | +0.251 |
puter | +0.249 |
egu | +0.244 |
dop | +0.235 |
ousy | +0.234 |
Neg logit contributions | |
ONS | -0.311 |
EMS | -0.301 |
LIST | -0.300 |
Kind | -0.299 |
ALS | -0.290 |
Token | the |
Token ID | 262 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
banter | +0.147 |
puter | +0.146 |
egu | +0.143 |
dop | +0.138 |
ousy | +0.138 |
Neg logit contributions | |
ONS | -0.141 |
EMS | -0.136 |
Kind | -0.135 |
LIST | -0.135 |
ALS | -0.130 |
Token | planet |
Token ID | 5440 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
banter | +0.633 |
puter | +0.613 |
egu | +0.608 |
dop | +0.602 |
ottesville | +0.584 |
Neg logit contributions | |
ONS | -0.549 |
EMS | -0.528 |
Kind | -0.522 |
LIST | -0.520 |
ALS | -0.506 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ONS | +0.304 |
EMS | +0.295 |
LIST | +0.293 |
Kind | +0.292 |
Imper | +0.283 |
Neg logit contributions | |
banter | -0.243 |
puter | -0.241 |
egu | -0.238 |
ottesville | -0.228 |
ousy | -0.227 |
Token | spending |
Token ID | 4581 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
banter | +0.659 |
puter | +0.648 |
egu | +0.645 |
dop | +0.615 |
ousy | +0.609 |
Neg logit contributions | |
ONS | -0.830 |
EMS | -0.808 |
LIST | -0.802 |
Kind | -0.801 |
ALS | -0.775 |
Token | twice |
Token ID | 5403 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
ONS | +1.494 |
EMS | +1.444 |
LIST | +1.435 |
Kind | +1.426 |
Imper | +1.383 |
Neg logit contributions | |
banter | -1.479 |
puter | -1.467 |
egu | -1.452 |
ottesville | -1.395 |
ousy | -1.390 |
Token | as |
Token ID | 355 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ONS | +4.036 |
LIST | +3.912 |
EMS | +3.893 |
Kind | +3.887 |
Imper | +3.742 |
Neg logit contributions | |
puter | -4.402 |
banter | -4.342 |
ottesville | -4.302 |
egu | -4.294 |
ousy | -4.168 |
Token | much |
Token ID | 881 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
ONS | +2.470 |
EMS | +2.400 |
LIST | +2.387 |
Kind | +2.376 |
Imper | +2.315 |
Neg logit contributions | |
banter | -1.553 |
puter | -1.543 |
egu | -1.520 |
ottesville | -1.450 |
ousy | -1.439 |
Token | as |
Token ID | 355 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ONS | +0.269 |
EMS | +0.261 |
LIST | +0.259 |
Kind | +0.259 |
Imper | +0.250 |
Neg logit contributions | |
banter | -0.251 |
puter | -0.248 |
egu | -0.245 |
dop | -0.235 |
ousy | -0.235 |
Token | the |
Token ID | 262 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ONS | +1.064 |
EMS | +1.029 |
LIST | +1.023 |
Kind | +1.017 |
ALS | +0.984 |
Neg logit contributions | |
banter | -1.013 |
puter | -1.003 |
egu | -0.991 |
ottesville | -0.953 |
dop | -0.952 |
Token | U |
Token ID | 471 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ONS | +0.379 |
EMS | +0.367 |
LIST | +0.365 |
Kind | +0.363 |
ALS | +0.351 |
Neg logit contributions | |
banter | -0.364 |
puter | -0.358 |
egu | -0.354 |
dop | -0.343 |
ottesville | -0.339 |
Token | of |
Token ID | 286 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ONS | +0.026 |
EMS | +0.026 |
LIST | +0.025 |
Kind | +0.025 |
Imper | +0.025 |
Neg logit contributions | |
banter | -0.023 |
puter | -0.023 |
egu | -0.023 |
ottesville | -0.022 |
ousy | -0.022 |
Token | skin |
Token ID | 4168 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ONS | +0.273 |
EMS | +0.264 |
LIST | +0.263 |
Kind | +0.261 |
Imper | +0.255 |
Neg logit contributions | |
banter | -0.219 |
puter | -0.218 |
egu | -0.215 |
ottesville | -0.206 |
ousy | -0.205 |
Token | that |
Token ID | 326 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
banter | +0.422 |
puter | +0.419 |
egu | +0.414 |
ousy | +0.397 |
ottesville | +0.396 |
Neg logit contributions | |
ONS | -0.497 |
EMS | -0.482 |
LIST | -0.478 |
Kind | -0.475 |
Imper | -0.462 |
Token | run |
Token ID | 1057 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ONS | +0.694 |
EMS | +0.672 |
LIST | +0.668 |
Kind | +0.664 |
Imper | +0.646 |
Neg logit contributions | |
banter | -0.585 |
puter | -0.582 |
egu | -0.574 |
ottesville | -0.552 |
ousy | -0.548 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ONS | +0.379 |
EMS | +0.366 |
LIST | +0.364 |
Kind | +0.362 |
Imper | +0.352 |
Neg logit contributions | |
banter | -0.334 |
puter | -0.333 |
egu | -0.329 |
ottesville | -0.316 |
ousy | -0.314 |
Token | whole |
Token ID | 2187 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
ONS | +0.847 |
EMS | +0.820 |
LIST | +0.813 |
Kind | +0.808 |
Imper | +0.780 |
Neg logit contributions | |
banter | -0.934 |
puter | -0.922 |
egu | -0.914 |
ottesville | -0.882 |
dop | -0.881 |
Token | length |
Token ID | 4129 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ONS | +3.889 |
LIST | +3.689 |
Kind | +3.658 |
EMS | +3.654 |
Imper | +3.598 |
Neg logit contributions | |
puter | -4.592 |
banter | -4.551 |
egu | -4.537 |
ottesville | -4.402 |
ousy | -4.379 |
Token | of |
Token ID | 286 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ONS | +1.577 |
LIST | +1.515 |
EMS | +1.507 |
Kind | +1.498 |
Imper | +1.461 |
Neg logit contributions | |
banter | -1.559 |
puter | -1.554 |
egu | -1.538 |
ottesville | -1.480 |
ousy | -1.465 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ONS | +0.900 |
EMS | +0.867 |
LIST | +0.863 |
Kind | +0.858 |
Imper | +0.838 |
Neg logit contributions | |
puter | -0.822 |
banter | -0.822 |
egu | -0.811 |
ottesville | -0.781 |
ousy | -0.776 |
Token | trunk |
Token ID | 21427 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
ONS | +1.247 |
EMS | +1.208 |
LIST | +1.201 |
Kind | +1.195 |
Imper | +1.161 |
Neg logit contributions | |
banter | -1.058 |
puter | -1.051 |
egu | -1.038 |
ottesville | -0.997 |
ousy | -0.992 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
ONS | +0.548 |
EMS | +0.532 |
LIST | +0.528 |
Kind | +0.525 |
Imper | +0.510 |
Neg logit contributions | |
banter | -0.462 |
puter | -0.458 |
egu | -0.452 |
ottesville | -0.435 |
ousy | -0.433 |
Token | similar |
Token ID | 2092 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ONS | +2.069 |
LIST | +1.999 |
EMS | +1.996 |
Kind | +1.983 |
Imper | +1.936 |
Neg logit contributions | |
banter | -1.889 |
puter | -1.883 |
egu | -1.871 |
ottesville | -1.800 |
ousy | -1.789 |
Token | to |
Token ID | 284 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
ONS | +1.776 |
EMS | +1.705 |
LIST | +1.703 |
Kind | +1.702 |
Imper | +1.648 |
Neg logit contributions | |
puter | -1.866 |
banter | -1.865 |
egu | -1.839 |
ottesville | -1.790 |
ousy | -1.775 |
Token | Allah |
Token ID | 11475 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ONS | +0.705 |
EMS | +0.688 |
LIST | +0.681 |
Kind | +0.676 |
ALS | +0.658 |
Neg logit contributions | |
banter | -0.516 |
puter | -0.507 |
egu | -0.501 |
dop | -0.480 |
ottesville | -0.476 |
Token | 's |
Token ID | 338 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ONS | +1.007 |
EMS | +0.977 |
LIST | +0.969 |
Kind | +0.961 |
ALS | +0.933 |
Neg logit contributions | |
banter | -0.852 |
puter | -0.846 |
egu | -0.835 |
ottesville | -0.801 |
dop | -0.796 |
Token | Judgment |
Token ID | 36969 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
ONS | +1.780 |
EMS | +1.721 |
LIST | +1.712 |
Kind | +1.704 |
Imper | +1.655 |
Neg logit contributions | |
banter | -1.619 |
puter | -1.610 |
egu | -1.591 |
ottesville | -1.531 |
ousy | -1.524 |
Token | ( |
Token ID | 357 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
ONS | +2.328 |
LIST | +2.248 |
EMS | +2.248 |
Kind | +2.234 |
Imper | +2.182 |
Neg logit contributions | |
banter | -2.030 |
puter | -2.021 |
egu | -2.007 |
ottesville | -1.927 |
ousy | -1.914 |
Token | or |
Token ID | 273 |
Feature activation | -9.91e-03 |
Pos logit contributions | |
ONS | +3.826 |
LIST | +3.688 |
Kind | +3.674 |
EMS | +3.639 |
Imper | +3.524 |
Neg logit contributions | |
banter | -4.596 |
puter | -4.574 |
egu | -4.514 |
ottesville | -4.402 |
ousy | -4.395 |
Token | the |
Token ID | 262 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ONS | +0.008 |
EMS | +0.007 |
LIST | +0.007 |
Kind | +0.007 |
ALS | +0.007 |
Neg logit contributions | |
banter | -0.007 |
puter | -0.007 |
egu | -0.007 |
dop | -0.006 |
ousy | -0.006 |
Token | King |
Token ID | 2677 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ONS | +0.981 |
EMS | +0.953 |
LIST | +0.944 |
Kind | +0.934 |
ALS | +0.909 |
Neg logit contributions | |
banter | -0.953 |
puter | -0.940 |
egu | -0.931 |
ottesville | -0.894 |
dop | -0.893 |
Token | 's |
Token ID | 338 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ONS | +1.102 |
EMS | +1.068 |
LIST | +1.061 |
Kind | +1.052 |
Imper | +1.021 |
Neg logit contributions | |
banter | -0.999 |
puter | -0.990 |
egu | -0.979 |
ottesville | -0.942 |
ousy | -0.936 |
Token | judgment |
Token ID | 8492 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
ONS | +0.247 |
EMS | +0.240 |
LIST | +0.237 |
Kind | +0.235 |
ALS | +0.229 |
Neg logit contributions | |
banter | -0.240 |
puter | -0.238 |
egu | -0.235 |
dop | -0.226 |
ottesville | -0.226 |
Token | German |
Token ID | 2679 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
banter | +0.054 |
puter | +0.054 |
egu | +0.053 |
ottesville | +0.051 |
ousy | +0.051 |
Neg logit contributions | |
ONS | -0.047 |
EMS | -0.046 |
LIST | -0.045 |
Kind | -0.045 |
Imper | -0.043 |
Token | division |
Token ID | 7297 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
banter | +0.520 |
puter | +0.516 |
egu | +0.510 |
ottesville | +0.489 |
ousy | +0.486 |
Neg logit contributions | |
ONS | -0.623 |
EMS | -0.604 |
LIST | -0.601 |
Kind | -0.597 |
Imper | -0.580 |
Token | Hel |
Token ID | 5053 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
banter | +0.377 |
puter | +0.374 |
egu | +0.369 |
ottesville | +0.354 |
ousy | +0.353 |
Neg logit contributions | |
ONS | -0.436 |
EMS | -0.423 |
LIST | -0.420 |
Kind | -0.418 |
Imper | -0.406 |
Token | fen |
Token ID | 41037 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ONS | +0.733 |
EMS | +0.707 |
LIST | +0.701 |
Kind | +0.698 |
Imper | +0.674 |
Neg logit contributions | |
banter | -0.850 |
puter | -0.844 |
egu | -0.835 |
ottesville | -0.808 |
ousy | -0.804 |
Token | oh |
Token ID | 11752 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
ONS | +0.431 |
EMS | +0.418 |
LIST | +0.414 |
Kind | +0.412 |
Imper | +0.400 |
Neg logit contributions | |
banter | -0.391 |
puter | -0.389 |
egu | -0.384 |
ottesville | -0.369 |
ousy | -0.368 |
Token | ne |
Token ID | 710 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
ONS | +0.057 |
EMS | +0.055 |
LIST | +0.055 |
Kind | +0.055 |
Imper | +0.053 |
Neg logit contributions | |
banter | -0.046 |
puter | -0.046 |
egu | -0.045 |
ottesville | -0.043 |
ousy | -0.043 |
Token | Gren |
Token ID | 19674 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ONS | +4.256 |
Kind | +4.136 |
EMS | +4.128 |
LIST | +4.095 |
Imper | +4.076 |
Neg logit contributions | |
banter | -4.051 |
puter | -4.035 |
egu | -3.945 |
ottesville | -3.865 |
ousy | -3.777 |
Token | zen |
Token ID | 4801 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ONS | +1.590 |
EMS | +1.538 |
LIST | +1.528 |
Kind | +1.524 |
Imper | +1.481 |
Neg logit contributions | |
banter | -1.449 |
puter | -1.435 |
egu | -1.417 |
ottesville | -1.366 |
ousy | -1.357 |
Token | e |
Token ID | 304 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
banter | +0.302 |
puter | +0.301 |
egu | +0.298 |
ottesville | +0.285 |
ousy | +0.284 |
Neg logit contributions | |
ONS | -0.341 |
EMS | -0.330 |
LIST | -0.328 |
Kind | -0.326 |
Imper | -0.316 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
banter | +0.365 |
puter | +0.364 |
egu | +0.360 |
ousy | +0.346 |
dop | +0.346 |
Neg logit contributions | |
ONS | -0.339 |
LIST | -0.326 |
EMS | -0.326 |
Kind | -0.320 |
ALS | -0.311 |
Token | V |
Token ID | 53 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
puter | +1.619 |
banter | +1.618 |
egu | +1.608 |
dop | +1.553 |
ousy | +1.545 |
Neg logit contributions | |
ONS | -0.972 |
EMS | -0.928 |
LIST | -0.920 |
Kind | -0.896 |
ALS | -0.871 |
Token | Muslims |
Token ID | 7045 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
ONS | +1.117 |
EMS | +1.089 |
LIST | +1.079 |
Kind | +1.067 |
ALS | +1.043 |
Neg logit contributions | |
banter | -1.038 |
puter | -1.022 |
egu | -1.013 |
dop | -0.974 |
ousy | -0.964 |
Token | present |
Token ID | 1944 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
ONS | +3.609 |
LIST | +3.486 |
EMS | +3.470 |
Kind | +3.469 |
Imper | +3.387 |
Neg logit contributions | |
puter | -3.199 |
banter | -3.178 |
egu | -3.160 |
ottesville | -3.047 |
ousy | -3.024 |
Token | that |
Token ID | 326 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ONS | +2.705 |
EMS | +2.612 |
LIST | +2.610 |
Kind | +2.590 |
Imper | +2.527 |
Neg logit contributions | |
banter | -2.421 |
puter | -2.420 |
egu | -2.397 |
ottesville | -2.295 |
ousy | -2.285 |
Token | they |
Token ID | 484 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ONS | +0.422 |
EMS | +0.410 |
LIST | +0.407 |
Kind | +0.401 |
ALS | +0.391 |
Neg logit contributions | |
banter | -0.403 |
puter | -0.392 |
egu | -0.390 |
dop | -0.377 |
ousy | -0.374 |
Token | would |
Token ID | 561 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ONS | +1.029 |
EMS | +0.998 |
LIST | +0.992 |
Kind | +0.986 |
Imper | +0.958 |
Neg logit contributions | |
banter | -0.862 |
puter | -0.854 |
egu | -0.844 |
ottesville | -0.810 |
ousy | -0.806 |
Token | indeed |
Token ID | 5600 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
ONS | +1.735 |
EMS | +1.674 |
LIST | +1.668 |
Kind | +1.661 |
Imper | +1.621 |
Neg logit contributions | |
puter | -1.405 |
banter | -1.402 |
egu | -1.381 |
ottesville | -1.330 |
ousy | -1.324 |
Token | abide |
Token ID | 27851 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
ONS | +4.426 |
Kind | +4.210 |
LIST | +4.196 |
EMS | +4.179 |
Imper | +4.162 |
Neg logit contributions | |
puter | -3.977 |
egu | -3.813 |
banter | -3.812 |
ottesville | -3.744 |
ousy | -3.735 |
Token | by |
Token ID | 416 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
ONS | +3.035 |
LIST | +2.927 |
EMS | +2.918 |
Kind | +2.917 |
Imper | +2.848 |
Neg logit contributions | |
puter | -2.604 |
banter | -2.598 |
egu | -2.550 |
ottesville | -2.468 |
ousy | -2.463 |
Token | his |
Token ID | 465 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
ONS | +2.213 |
EMS | +2.136 |
LIST | +2.127 |
Kind | +2.116 |
Imper | +2.061 |
Neg logit contributions | |
puter | -2.153 |
banter | -2.153 |
egu | -2.123 |
ottesville | -2.053 |
ousy | -2.039 |
Token | judgment |
Token ID | 8492 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ONS | +0.071 |
EMS | +0.070 |
LIST | +0.068 |
Kind | +0.068 |
ALS | +0.066 |
Neg logit contributions | |
banter | -0.068 |
puter | -0.066 |
egu | -0.066 |
dop | -0.063 |
ottesville | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ONS | +2.845 |
LIST | +2.747 |
EMS | +2.741 |
Kind | +2.727 |
Imper | +2.665 |
Neg logit contributions | |
puter | -2.411 |
banter | -2.408 |
egu | -2.392 |
ottesville | -2.291 |
ousy | -2.282 |
Token | curly |
Token ID | 45731 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
ONS | +0.818 |
EMS | +0.790 |
LIST | +0.785 |
Kind | +0.781 |
Imper | +0.757 |
Neg logit contributions | |
banter | -0.810 |
puter | -0.805 |
egu | -0.796 |
ottesville | -0.767 |
ousy | -0.764 |
Token | braces |
Token ID | 47241 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ONS | +0.230 |
EMS | +0.223 |
LIST | +0.221 |
Kind | +0.220 |
Imper | +0.213 |
Neg logit contributions | |
banter | -0.210 |
puter | -0.208 |
egu | -0.205 |
ottesville | -0.197 |
dop | -0.197 |
Token | though |
Token ID | 996 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ONS | +1.088 |
EMS | +1.053 |
LIST | +1.046 |
Kind | +1.041 |
Imper | +1.010 |
Neg logit contributions | |
banter | -0.969 |
puter | -0.962 |
egu | -0.950 |
ottesville | -0.913 |
ousy | -0.909 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ONS | +1.612 |
EMS | +1.563 |
LIST | +1.553 |
Kind | +1.547 |
Imper | +1.506 |
Neg logit contributions | |
banter | -1.422 |
puter | -1.418 |
egu | -1.398 |
ottesville | -1.349 |
ousy | -1.335 |
Token | in |
Token ID | 287 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ONS | +0.093 |
EMS | +0.090 |
LIST | +0.090 |
Kind | +0.089 |
ALS | +0.087 |
Neg logit contributions | |
banter | -0.064 |
puter | -0.062 |
egu | -0.062 |
dop | -0.059 |
ousy | -0.059 |
Token | order |
Token ID | 1502 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
ONS | +0.250 |
EMS | +0.242 |
LIST | +0.240 |
Kind | +0.239 |
Imper | +0.231 |
Neg logit contributions | |
banter | -0.231 |
puter | -0.229 |
egu | -0.226 |
ottesville | -0.217 |
ousy | -0.217 |
Token | to |
Token ID | 284 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ONS | +3.760 |
LIST | +3.640 |
Kind | +3.614 |
EMS | +3.591 |
Imper | +3.510 |
Neg logit contributions | |
puter | -4.460 |
banter | -4.458 |
egu | -4.404 |
ottesville | -4.356 |
ousy | -4.267 |
Token | differentiate |
Token ID | 28754 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ONS | +2.504 |
EMS | +2.418 |
LIST | +2.412 |
Kind | +2.397 |
Imper | +2.356 |
Neg logit contributions | |
puter | -2.130 |
banter | -2.107 |
egu | -2.085 |
ottesville | -2.041 |
ousy | -2.013 |
Token | between |
Token ID | 1022 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ONS | +0.949 |
EMS | +0.919 |
LIST | +0.913 |
Kind | +0.909 |
Imper | +0.885 |
Neg logit contributions | |
banter | -0.816 |
puter | -0.812 |
egu | -0.802 |
ottesville | -0.772 |
ousy | -0.767 |
Token | string |
Token ID | 4731 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ONS | +0.480 |
EMS | +0.465 |
LIST | +0.461 |
Kind | +0.459 |
ALS | +0.444 |
Neg logit contributions | |
banter | -0.457 |
puter | -0.452 |
egu | -0.448 |
ottesville | -0.430 |
dop | -0.429 |
Token | liter |
Token ID | 4187 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
banter | +0.101 |
puter | +0.099 |
egu | +0.098 |
ottesville | +0.094 |
dop | +0.094 |
Neg logit contributions | |
ONS | -0.126 |
EMS | -0.122 |
LIST | -0.121 |
Kind | -0.120 |
Imper | -0.117 |
Token | single |
Token ID | 2060 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ONS | +0.106 |
EMS | +0.103 |
LIST | +0.102 |
Kind | +0.102 |
Imper | +0.099 |
Neg logit contributions | |
banter | -0.093 |
puter | -0.093 |
egu | -0.091 |
ottesville | -0.088 |
dop | -0.087 |
Token | binary |
Token ID | 13934 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
banter | +1.187 |
puter | +1.185 |
egu | +1.155 |
dop | +1.122 |
ottesville | +1.112 |
Neg logit contributions | |
ONS | -1.434 |
EMS | -1.392 |
LIST | -1.382 |
Kind | -1.365 |
ALS | -1.333 |
Token | package |
Token ID | 5301 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
banter | +0.296 |
puter | +0.295 |
egu | +0.289 |
dop | +0.277 |
ottesville | +0.277 |
Neg logit contributions | |
ONS | -0.343 |
EMS | -0.332 |
LIST | -0.328 |
Kind | -0.327 |
ALS | -0.318 |
Token | to |
Token ID | 284 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
banter | +0.734 |
puter | +0.730 |
egu | +0.715 |
dop | +0.688 |
ottesville | +0.679 |
Neg logit contributions | |
ONS | -0.827 |
EMS | -0.802 |
LIST | -0.792 |
Kind | -0.789 |
ALS | -0.767 |
Token | work |
Token ID | 670 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ONS | +0.635 |
EMS | +0.615 |
LIST | +0.612 |
Kind | +0.608 |
Imper | +0.592 |
Neg logit contributions | |
banter | -0.512 |
puter | -0.509 |
egu | -0.502 |
ottesville | -0.483 |
ousy | -0.480 |
Token | perfectly |
Token ID | 7138 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
ONS | +0.506 |
EMS | +0.491 |
LIST | +0.487 |
Kind | +0.484 |
ALS | +0.470 |
Neg logit contributions | |
banter | -0.446 |
puter | -0.442 |
egu | -0.437 |
ottesville | -0.419 |
dop | -0.418 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ONS | +4.047 |
LIST | +3.877 |
Kind | +3.839 |
EMS | +3.819 |
Imper | +3.745 |
Neg logit contributions | |
puter | -4.276 |
banter | -4.238 |
egu | -4.234 |
ottesville | -4.121 |
ousy | -4.088 |
Token | securely |
Token ID | 30835 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
ONS | +1.051 |
EMS | +1.019 |
LIST | +1.014 |
Kind | +1.010 |
Imper | +0.984 |
Neg logit contributions | |
banter | -0.797 |
puter | -0.793 |
egu | -0.784 |
ottesville | -0.753 |
ousy | -0.747 |
Token | on |
Token ID | 319 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
banter | +0.582 |
puter | +0.574 |
egu | +0.567 |
dop | +0.546 |
ousy | +0.539 |
Neg logit contributions | |
ONS | -0.668 |
EMS | -0.649 |
LIST | -0.645 |
Kind | -0.642 |
ALS | -0.623 |
Token | any |
Token ID | 597 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ONS | +1.570 |
EMS | +1.530 |
Kind | +1.514 |
LIST | +1.513 |
Imper | +1.488 |
Neg logit contributions | |
banter | -1.059 |
puter | -1.054 |
egu | -1.046 |
ottesville | -1.008 |
ousy | -0.994 |
Token | Linux |
Token ID | 7020 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
banter | +0.526 |
puter | +0.522 |
egu | +0.514 |
ottesville | +0.491 |
dop | +0.491 |
Neg logit contributions | |
ONS | -0.685 |
EMS | -0.664 |
LIST | -0.660 |
Kind | -0.655 |
ALS | -0.637 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ONS | +0.683 |
EMS | +0.662 |
LIST | +0.658 |
Kind | +0.652 |
ALS | +0.631 |
Neg logit contributions | |
banter | -0.699 |
puter | -0.690 |
egu | -0.681 |
ottesville | -0.655 |
dop | -0.654 |
Token | option |
Token ID | 3038 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
ONS | +0.094 |
EMS | +0.092 |
LIST | +0.091 |
Kind | +0.090 |
ALS | +0.088 |
Neg logit contributions | |
banter | -0.084 |
puter | -0.082 |
egu | -0.081 |
dop | -0.078 |
ottesville | -0.078 |
Token | of |
Token ID | 286 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
ONS | +0.501 |
LIST | +0.482 |
EMS | +0.481 |
Kind | +0.477 |
Imper | +0.463 |
Neg logit contributions | |
puter | -0.511 |
banter | -0.510 |
egu | -0.509 |
ottesville | -0.492 |
ousy | -0.483 |
Token | using |
Token ID | 1262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
banter | +0.494 |
puter | +0.487 |
egu | +0.479 |
dop | +0.461 |
ousy | +0.457 |
Neg logit contributions | |
ONS | -0.589 |
EMS | -0.572 |
LIST | -0.568 |
Kind | -0.565 |
ALS | -0.548 |
Token | steering |
Token ID | 19702 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ONS | +0.867 |
EMS | +0.839 |
LIST | +0.833 |
Kind | +0.829 |
Imper | +0.807 |
Neg logit contributions | |
banter | -0.779 |
puter | -0.775 |
egu | -0.766 |
ottesville | -0.738 |
ousy | -0.733 |
Token | wheel |
Token ID | 7825 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
ONS | +1.641 |
EMS | +1.573 |
LIST | +1.568 |
Kind | +1.554 |
Imper | +1.506 |
Neg logit contributions | |
banter | -1.888 |
puter | -1.883 |
egu | -1.872 |
ottesville | -1.809 |
ousy | -1.799 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ONS | +4.446 |
Kind | +4.252 |
EMS | +4.244 |
LIST | +4.226 |
ALS | +4.133 |
Neg logit contributions | |
egu | -3.848 |
puter | -3.813 |
banter | -3.781 |
ottesville | -3.700 |
ousy | -3.666 |
Token | pedal |
Token ID | 26667 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ONS | +0.930 |
EMS | +0.900 |
LIST | +0.894 |
Kind | +0.890 |
Imper | +0.865 |
Neg logit contributions | |
banter | -0.803 |
puter | -0.798 |
egu | -0.790 |
ottesville | -0.760 |
ousy | -0.756 |
Token | sets |
Token ID | 5621 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ONS | +1.732 |
EMS | +1.668 |
LIST | +1.659 |
Kind | +1.655 |
Imper | +1.604 |
Neg logit contributions | |
banter | -1.470 |
puter | -1.459 |
egu | -1.455 |
ottesville | -1.395 |
ousy | -1.385 |
Token | and |
Token ID | 290 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ONS | +0.087 |
EMS | +0.085 |
LIST | +0.084 |
Kind | +0.084 |
Imper | +0.081 |
Neg logit contributions | |
banter | -0.076 |
puter | -0.075 |
egu | -0.074 |
dop | -0.071 |
ottesville | -0.071 |
Token | support |
Token ID | 1104 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ONS | +0.187 |
EMS | +0.181 |
LIST | +0.180 |
Kind | +0.179 |
Imper | +0.174 |
Neg logit contributions | |
banter | -0.158 |
puter | -0.157 |
egu | -0.154 |
dop | -0.148 |
ottesville | -0.148 |
Token | ( |
Token ID | 357 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
ONS | +0.556 |
EMS | +0.538 |
LIST | +0.535 |
Kind | +0.533 |
Imper | +0.517 |
Neg logit contributions | |
banter | -0.465 |
puter | -0.462 |
egu | -0.456 |
ottesville | -0.438 |
ousy | -0.436 |
Token | your |
Token ID | 14108 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ONS | +0.512 |
EMS | +0.492 |
LIST | +0.489 |
Kind | +0.486 |
Imper | +0.472 |
Neg logit contributions | |
banter | -0.584 |
puter | -0.581 |
egu | -0.576 |
ottesville | -0.555 |
ousy | -0.553 |
Token | W |
Token ID | 370 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ONS | +1.005 |
EMS | +0.973 |
LIST | +0.967 |
Kind | +0.962 |
Imper | +0.935 |
Neg logit contributions | |
banter | -0.893 |
puter | -0.888 |
egu | -0.877 |
ottesville | -0.844 |
ousy | -0.840 |
Token | AB |
Token ID | 6242 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
banter | +1.379 |
egu | +1.371 |
puter | +1.370 |
ousy | +1.339 |
ottesville | +1.336 |
Neg logit contributions | |
ONS | -0.237 |
EMS | -0.214 |
LIST | -0.204 |
Kind | -0.204 |
Imper | -0.187 |
Token | L |
Token ID | 43 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
banter | +0.534 |
puter | +0.524 |
egu | +0.522 |
ousy | +0.505 |
dop | +0.504 |
Neg logit contributions | |
ONS | -0.461 |
EMS | -0.447 |
Kind | -0.439 |
LIST | -0.435 |
Imper | -0.432 |
Token | number |
Token ID | 1271 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
banter | +0.649 |
puter | +0.644 |
egu | +0.636 |
ottesville | +0.607 |
dop | +0.606 |
Neg logit contributions | |
ONS | -0.786 |
EMS | -0.761 |
LIST | -0.755 |
Kind | -0.753 |
Imper | -0.730 |
Token | ) |
Token ID | 8 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
banter | +2.570 |
puter | +2.552 |
egu | +2.497 |
dop | +2.386 |
ousy | +2.368 |
Neg logit contributions | |
ONS | -3.534 |
EMS | -3.419 |
Kind | -3.402 |
LIST | -3.389 |
Imper | -3.298 |
Token | and |
Token ID | 290 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ONS | +0.463 |
EMS | +0.449 |
LIST | +0.446 |
Kind | +0.444 |
Imper | +0.431 |
Neg logit contributions | |
banter | -0.391 |
puter | -0.389 |
egu | -0.384 |
ottesville | -0.368 |
ousy | -0.367 |
Token | your |
Token ID | 534 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
banter | +0.804 |
puter | +0.793 |
egu | +0.784 |
dop | +0.753 |
ottesville | +0.752 |
Neg logit contributions | |
ONS | -0.888 |
EMS | -0.859 |
LIST | -0.854 |
Kind | -0.848 |
Imper | -0.821 |
Token | registered |
Token ID | 6823 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
ONS | +0.768 |
EMS | +0.743 |
LIST | +0.739 |
Kind | +0.735 |
Imper | +0.714 |
Neg logit contributions | |
banter | -0.696 |
puter | -0.693 |
egu | -0.684 |
ottesville | -0.658 |
ousy | -0.655 |
Token | email |
Token ID | 3053 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ONS | +0.327 |
EMS | +0.316 |
LIST | +0.315 |
Kind | +0.313 |
Imper | +0.303 |
Neg logit contributions | |
banter | -0.299 |
puter | -0.297 |
egu | -0.293 |
ottesville | -0.282 |
ousy | -0.281 |
Token | Havana |
Token ID | 40274 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
ONS | +0.238 |
EMS | +0.231 |
LIST | +0.230 |
Kind | +0.229 |
Imper | +0.222 |
Neg logit contributions | |
banter | -0.194 |
puter | -0.193 |
egu | -0.190 |
ottesville | -0.183 |
ousy | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ONS | +0.269 |
EMS | +0.261 |
LIST | +0.259 |
Kind | +0.258 |
Imper | +0.251 |
Neg logit contributions | |
banter | -0.231 |
puter | -0.229 |
egu | -0.226 |
ottesville | -0.218 |
ousy | -0.216 |
Token | Because |
Token ID | 4362 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ONS | +0.327 |
EMS | +0.316 |
LIST | +0.314 |
Kind | +0.311 |
ALS | +0.302 |
Neg logit contributions | |
banter | -0.312 |
puter | -0.309 |
egu | -0.306 |
ottesville | -0.294 |
ousy | -0.293 |
Token | despite |
Token ID | 3805 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
banter | +0.791 |
puter | +0.776 |
egu | +0.767 |
dop | +0.739 |
ousy | +0.735 |
Neg logit contributions | |
ONS | -0.930 |
EMS | -0.900 |
LIST | -0.890 |
Kind | -0.887 |
ALS | -0.860 |
Token | his |
Token ID | 465 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ONS | +0.049 |
EMS | +0.047 |
LIST | +0.047 |
Kind | +0.047 |
Imper | +0.045 |
Neg logit contributions | |
banter | -0.045 |
puter | -0.045 |
egu | -0.044 |
ottesville | -0.042 |
ousy | -0.042 |
Token | best |
Token ID | 1266 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
banter | +0.724 |
puter | +0.706 |
egu | +0.698 |
dop | +0.680 |
ottesville | +0.672 |
Neg logit contributions | |
ONS | -0.833 |
EMS | -0.808 |
LIST | -0.802 |
Kind | -0.794 |
ALS | -0.770 |
Token | efforts |
Token ID | 4040 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
banter | +1.824 |
egu | +1.727 |
puter | +1.716 |
dop | +1.593 |
ottesville | +1.568 |
Neg logit contributions | |
ONS | -5.767 |
EMS | -5.634 |
LIST | -5.616 |
Kind | -5.520 |
ALS | -5.436 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
banter | +1.399 |
puter | +1.387 |
egu | +1.360 |
ousy | +1.314 |
dop | +1.312 |
Neg logit contributions | |
ONS | -1.766 |
EMS | -1.708 |
LIST | -1.696 |
Kind | -1.683 |
ALS | -1.634 |
Token | the |
Token ID | 262 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ONS | +0.250 |
EMS | +0.241 |
LIST | +0.240 |
Kind | +0.238 |
Imper | +0.230 |
Neg logit contributions | |
banter | -0.265 |
puter | -0.263 |
egu | -0.260 |
ottesville | -0.251 |
ousy | -0.250 |
Token | life |
Token ID | 1204 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ONS | +0.432 |
EMS | +0.419 |
LIST | +0.416 |
Kind | +0.413 |
Imper | +0.401 |
Neg logit contributions | |
banter | -0.347 |
puter | -0.343 |
egu | -0.339 |
ottesville | -0.325 |
dop | -0.323 |
Token | could |
Token ID | 714 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
ONS | +1.184 |
EMS | +1.148 |
LIST | +1.142 |
Kind | +1.136 |
Imper | +1.106 |
Neg logit contributions | |
banter | -1.043 |
puter | -1.038 |
egu | -1.026 |
ottesville | -0.988 |
ousy | -0.981 |
Token | based |
Token ID | 3106 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
banter | +0.123 |
puter | +0.123 |
egu | +0.121 |
ottesville | +0.115 |
ousy | +0.115 |
Neg logit contributions | |
ONS | -0.171 |
EMS | -0.166 |
LIST | -0.165 |
Kind | -0.164 |
Imper | -0.160 |
Token | Anat |
Token ID | 28880 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ONS | +0.588 |
EMS | +0.566 |
LIST | +0.562 |
Kind | +0.557 |
ALS | +0.536 |
Neg logit contributions | |
banter | -0.797 |
puter | -0.793 |
egu | -0.784 |
dop | -0.758 |
ottesville | -0.758 |
Token | ol |
Token ID | 349 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
banter | +0.615 |
puter | +0.610 |
egu | +0.604 |
ottesville | +0.583 |
ousy | +0.580 |
Neg logit contributions | |
ONS | -0.561 |
EMS | -0.540 |
LIST | -0.536 |
Kind | -0.534 |
Imper | -0.517 |
Token | iy |
Token ID | 7745 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
banter | +0.031 |
puter | +0.031 |
egu | +0.031 |
ottesville | +0.030 |
ousy | +0.030 |
Neg logit contributions | |
ONS | -0.014 |
EMS | -0.013 |
LIST | -0.013 |
Kind | -0.013 |
Imper | -0.012 |
Token | D |
Token ID | 360 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
ONS | +1.492 |
EMS | +1.416 |
Kind | +1.409 |
LIST | +1.408 |
Imper | +1.375 |
Neg logit contributions | |
banter | -1.874 |
puter | -1.861 |
egu | -1.836 |
ottesville | -1.793 |
ousy | -1.772 |
Token | erk |
Token ID | 9587 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
ONS | +0.385 |
EMS | +0.370 |
LIST | +0.367 |
Kind | +0.366 |
Imper | +0.357 |
Neg logit contributions | |
banter | -0.466 |
puter | -0.463 |
egu | -0.463 |
ousy | -0.445 |
ottesville | -0.445 |
Token | ach |
Token ID | 620 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
egu | +3.948 |
banter | +3.889 |
puter | +3.819 |
ousy | +3.795 |
ottesville | +3.716 |
Neg logit contributions | |
ONS | -2.599 |
LIST | -2.578 |
EMS | -2.574 |
Kind | -2.459 |
Imper | -2.455 |
Token | , |
Token ID | 11 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
banter | +0.614 |
puter | +0.612 |
egu | +0.603 |
ottesville | +0.579 |
dop | +0.577 |
Neg logit contributions | |
ONS | -0.740 |
EMS | -0.721 |
LIST | -0.715 |
Kind | -0.712 |
Imper | -0.690 |
Token | the |
Token ID | 262 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
ONS | +0.598 |
EMS | +0.583 |
LIST | +0.578 |
Kind | +0.576 |
ALS | +0.558 |
Neg logit contributions | |
banter | -0.512 |
puter | -0.508 |
egu | -0.501 |
dop | -0.480 |
ottesville | -0.479 |
Token | owner |
Token ID | 4870 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ONS | +0.571 |
EMS | +0.558 |
LIST | +0.554 |
Kind | +0.551 |
ALS | +0.536 |
Neg logit contributions | |
banter | -0.455 |
puter | -0.449 |
egu | -0.444 |
dop | -0.426 |
ottesville | -0.422 |
Token | of |
Token ID | 286 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
ONS | +0.289 |
EMS | +0.279 |
LIST | +0.278 |
Kind | +0.277 |
Imper | +0.269 |
Neg logit contributions | |
banter | -0.264 |
puter | -0.262 |
egu | -0.259 |
ottesville | -0.250 |
ousy | -0.248 |
Token | her |
Token ID | 607 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
banter | +0.639 |
puter | +0.632 |
egu | +0.624 |
ottesville | +0.597 |
ousy | +0.597 |
Neg logit contributions | |
ONS | -0.791 |
EMS | -0.767 |
LIST | -0.762 |
Kind | -0.757 |
ALS | -0.735 |
Token | , |
Token ID | 11 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
banter | +0.990 |
puter | +0.975 |
egu | +0.952 |
dop | +0.928 |
ousy | +0.911 |
Neg logit contributions | |
ONS | -1.245 |
EMS | -1.211 |
LIST | -1.202 |
Kind | -1.186 |
ALS | -1.159 |
Token | giving |
Token ID | 3501 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
banter | +0.446 |
puter | +0.442 |
egu | +0.435 |
dop | +0.417 |
ousy | +0.416 |
Neg logit contributions | |
ONS | -0.559 |
EMS | -0.543 |
LIST | -0.538 |
Kind | -0.534 |
ALS | -0.520 |
Token | her |
Token ID | 607 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
ONS | +0.369 |
EMS | +0.357 |
LIST | +0.355 |
Kind | +0.354 |
Imper | +0.344 |
Neg logit contributions | |
banter | -0.309 |
puter | -0.308 |
egu | -0.304 |
ottesville | -0.293 |
ousy | -0.290 |
Token | my |
Token ID | 616 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
banter | +0.593 |
puter | +0.583 |
egu | +0.573 |
dop | +0.557 |
ousy | +0.552 |
Neg logit contributions | |
ONS | -0.538 |
EMS | -0.521 |
LIST | -0.515 |
Kind | -0.509 |
ALS | -0.495 |
Token | best |
Token ID | 1266 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
ONS | +0.292 |
EMS | +0.284 |
LIST | +0.282 |
Kind | +0.280 |
ALS | +0.272 |
Neg logit contributions | |
banter | -0.225 |
puter | -0.222 |
egu | -0.219 |
dop | -0.210 |
ottesville | -0.210 |
Token | sed |
Token ID | 10081 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
banter | +3.056 |
puter | +2.884 |
egu | +2.866 |
dop | +2.842 |
ousy | +2.686 |
Neg logit contributions | |
ONS | -4.552 |
EMS | -4.426 |
LIST | -4.366 |
Kind | -4.236 |
ALS | -4.215 |
Token | uctive |
Token ID | 45857 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
banter | +0.335 |
puter | +0.332 |
egu | +0.326 |
ottesville | +0.307 |
ousy | +0.305 |
Neg logit contributions | |
ONS | -0.740 |
EMS | -0.722 |
LIST | -0.718 |
Kind | -0.715 |
Imper | -0.700 |
Token | eyes |
Token ID | 2951 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
banter | +1.080 |
egu | +1.010 |
puter | +1.007 |
dop | +0.975 |
ousy | +0.934 |
Neg logit contributions | |
ONS | -2.153 |
EMS | -2.107 |
LIST | -2.082 |
Kind | -2.052 |
ALS | -2.026 |
Token | as |
Token ID | 355 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
banter | +0.464 |
puter | +0.459 |
egu | +0.452 |
ousy | +0.435 |
ottesville | +0.434 |
Neg logit contributions | |
ONS | -0.554 |
EMS | -0.537 |
LIST | -0.531 |
Kind | -0.529 |
ALS | -0.513 |
Token | I |
Token ID | 314 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
banter | +0.191 |
puter | +0.189 |
egu | +0.186 |
dop | +0.178 |
ottesville | +0.178 |
Neg logit contributions | |
ONS | -0.225 |
EMS | -0.218 |
LIST | -0.217 |
Kind | -0.215 |
ALS | -0.209 |
Token | data |
Token ID | 7890 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
ONS | +0.756 |
EMS | +0.732 |
LIST | +0.725 |
Kind | +0.721 |
ALS | +0.696 |
Neg logit contributions | |
banter | -0.837 |
puter | -0.828 |
egu | -0.822 |
ottesville | -0.795 |
ousy | -0.790 |
Token | _ |
Token ID | 62 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ONS | +0.472 |
EMS | +0.452 |
LIST | +0.449 |
Kind | +0.445 |
Imper | +0.429 |
Neg logit contributions | |
banter | -0.678 |
puter | -0.674 |
egu | -0.668 |
ottesville | -0.647 |
ousy | -0.645 |
Token | full |
Token ID | 12853 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
puter | +1.409 |
banter | +1.404 |
egu | +1.394 |
ottesville | +1.349 |
ousy | +1.340 |
Neg logit contributions | |
ONS | -1.035 |
EMS | -0.991 |
LIST | -0.975 |
Kind | -0.971 |
Imper | -0.944 |
Token | v |
Token ID | 410 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ONS | +1.240 |
EMS | +1.201 |
LIST | +1.192 |
Kind | +1.186 |
Imper | +1.152 |
Neg logit contributions | |
banter | -1.088 |
puter | -1.080 |
egu | -1.067 |
ottesville | -1.026 |
ousy | -1.020 |
Token | ) |
Token ID | 8 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
banter | +0.706 |
puter | +0.698 |
egu | +0.689 |
ottesville | +0.668 |
dop | +0.663 |
Neg logit contributions | |
ONS | -0.767 |
EMS | -0.741 |
LIST | -0.733 |
Kind | -0.724 |
Imper | -0.711 |
Token | { |
Token ID | 1391 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
banter | +0.516 |
puter | +0.512 |
egu | +0.508 |
ottesville | +0.493 |
dop | +0.493 |
Neg logit contributions | |
ONS | -0.288 |
EMS | -0.275 |
LIST | -0.270 |
Kind | -0.268 |
Imper | -0.255 |
Token | v |
Token ID | 410 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
banter | +3.681 |
puter | +3.582 |
egu | +3.532 |
dop | +3.506 |
ousy | +3.369 |
Neg logit contributions | |
ONS | -3.796 |
EMS | -3.664 |
Kind | -3.588 |
LIST | -3.573 |
ALS | -3.437 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ONS | +0.008 |
EMS | +0.008 |
LIST | +0.008 |
Kind | +0.008 |
Imper | +0.008 |
Neg logit contributions | |
banter | -0.007 |
puter | -0.007 |
egu | -0.007 |
ottesville | -0.007 |
ousy | -0.007 |
Token | ver |
Token ID | 332 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
banter | +0.903 |
puter | +0.895 |
egu | +0.885 |
ottesville | +0.850 |
dop | +0.844 |
Neg logit contributions | |
ONS | -1.187 |
EMS | -1.152 |
LIST | -1.143 |
Kind | -1.136 |
Imper | -1.104 |
Token | tex |
Token ID | 16886 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ONS | +2.078 |
EMS | +2.012 |
LIST | +2.008 |
Kind | +2.000 |
Imper | +1.943 |
Neg logit contributions | |
banter | -1.527 |
puter | -1.524 |
egu | -1.492 |
ousy | -1.429 |
ottesville | -1.429 |
Token | . |
Token ID | 13 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
ONS | +2.502 |
EMS | +2.418 |
LIST | +2.416 |
Kind | +2.413 |
Imper | +2.318 |
Neg logit contributions | |
banter | -2.774 |
puter | -2.754 |
egu | -2.717 |
ousy | -2.632 |
ottesville | -2.630 |
Token | to |
Token ID | 284 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
banter | +1.386 |
puter | +1.366 |
egu | +1.348 |
ousy | +1.296 |
dop | +1.295 |
Neg logit contributions | |
ONS | -1.590 |
LIST | -1.542 |
EMS | -1.533 |
Kind | -1.524 |
Imper | -1.474 |
Token | asted |
Token ID | 8992 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
ONS | +0.818 |
EMS | +0.790 |
LIST | +0.783 |
Kind | +0.779 |
Imper | +0.755 |
Neg logit contributions | |
banter | -0.866 |
puter | -0.861 |
egu | -0.851 |
ottesville | -0.822 |
ousy | -0.817 |
Token | its |
Token ID | 663 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
banter | +0.283 |
puter | +0.278 |
egu | +0.276 |
ousy | +0.266 |
ottesville | +0.265 |
Neg logit contributions | |
ONS | -0.280 |
EMS | -0.271 |
LIST | -0.270 |
Kind | -0.267 |
ALS | -0.259 |
Token | world |
Token ID | 995 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
ONS | +0.531 |
EMS | +0.514 |
LIST | +0.513 |
Kind | +0.508 |
ALS | +0.493 |
Neg logit contributions | |
banter | -0.494 |
puter | -0.487 |
egu | -0.481 |
dop | -0.464 |
ottesville | -0.464 |
Token | champion |
Token ID | 8783 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ONS | +0.288 |
EMS | +0.279 |
LIST | +0.278 |
Kind | +0.276 |
Imper | +0.268 |
Neg logit contributions | |
banter | -0.252 |
puter | -0.250 |
egu | -0.247 |
ottesville | -0.237 |
ousy | -0.236 |
Token | Cleveland |
Token ID | 10306 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ONS | +0.706 |
EMS | +0.684 |
LIST | +0.681 |
Kind | +0.677 |
Imper | +0.656 |
Neg logit contributions | |
banter | -0.615 |
puter | -0.608 |
egu | -0.601 |
ottesville | -0.577 |
ousy | -0.576 |
Token | Rams |
Token ID | 16077 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
banter | +1.064 |
puter | +1.050 |
egu | +1.034 |
ousy | +0.998 |
dop | +0.994 |
Neg logit contributions | |
ONS | -1.252 |
LIST | -1.214 |
EMS | -1.212 |
Kind | -1.205 |
Imper | -1.166 |
Token | in |
Token ID | 287 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
ONS | +1.097 |
EMS | +1.062 |
LIST | +1.056 |
Kind | +1.050 |
Imper | +1.020 |
Neg logit contributions | |
banter | -0.980 |
puter | -0.974 |
egu | -0.962 |
ottesville | -0.925 |
ousy | -0.921 |
Token | a |
Token ID | 257 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
ONS | +0.624 |
EMS | +0.601 |
LIST | +0.601 |
Kind | +0.595 |
Imper | +0.575 |
Neg logit contributions | |
banter | -0.660 |
puter | -0.653 |
egu | -0.647 |
ottesville | -0.623 |
ousy | -0.622 |
Token | celebration |
Token ID | 14395 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ONS | +0.671 |
EMS | +0.649 |
LIST | +0.647 |
Kind | +0.642 |
Imper | +0.624 |
Neg logit contributions | |
banter | -0.586 |
puter | -0.578 |
egu | -0.571 |
dop | -0.549 |
ottesville | -0.548 |
Token | that |
Token ID | 326 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
banter | +0.735 |
puter | +0.723 |
egu | +0.712 |
dop | +0.686 |
ousy | +0.685 |
Neg logit contributions | |
ONS | -0.890 |
EMS | -0.864 |
LIST | -0.858 |
Kind | -0.854 |
Imper | -0.826 |
Token | Lake |
Token ID | 6233 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
banter | +1.570 |
puter | +1.542 |
egu | +1.536 |
ousy | +1.481 |
dop | +1.475 |
Neg logit contributions | |
ONS | -1.382 |
EMS | -1.339 |
LIST | -1.320 |
Kind | -1.309 |
ALS | -1.266 |
Token | Ur |
Token ID | 8799 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
ONS | +1.101 |
EMS | +1.054 |
LIST | +1.046 |
Kind | +1.040 |
Imper | +1.001 |
Neg logit contributions | |
banter | -1.674 |
puter | -1.668 |
egu | -1.652 |
ottesville | -1.603 |
ousy | -1.596 |
Token | mia |
Token ID | 20730 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
banter | +0.733 |
puter | +0.730 |
egu | +0.727 |
ousy | +0.702 |
ottesville | +0.699 |
Neg logit contributions | |
ONS | -0.579 |
EMS | -0.554 |
LIST | -0.553 |
Kind | -0.543 |
Imper | -0.526 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ONS | +0.134 |
EMS | +0.131 |
LIST | +0.129 |
Kind | +0.129 |
Imper | +0.124 |
Neg logit contributions | |
banter | -0.116 |
puter | -0.114 |
egu | -0.114 |
ottesville | -0.109 |
dop | -0.108 |
Token | Iran |
Token ID | 4068 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
banter | +0.225 |
puter | +0.221 |
egu | +0.220 |
dop | +0.212 |
ousy | +0.210 |
Neg logit contributions | |
ONS | -0.218 |
EMS | -0.214 |
LIST | -0.211 |
Kind | -0.209 |
ALS | -0.202 |
Token | 1972 |
Token ID | 16101 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ONS | +1.003 |
EMS | +0.969 |
LIST | +0.965 |
Kind | +0.960 |
Imper | +0.935 |
Neg logit contributions | |
banter | -0.873 |
puter | -0.866 |
egu | -0.854 |
ottesville | -0.825 |
ousy | -0.819 |
Token | - |
Token ID | 12 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
banter | +0.695 |
puter | +0.690 |
egu | +0.680 |
ottesville | +0.649 |
ousy | +0.648 |
Neg logit contributions | |
ONS | -0.903 |
EMS | -0.878 |
LIST | -0.872 |
Kind | -0.868 |
ALS | -0.841 |
Token | 2014 |
Token ID | 4967 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
banter | +1.349 |
puter | +1.346 |
egu | +1.329 |
ousy | +1.273 |
dop | +1.268 |
Neg logit contributions | |
ONS | -1.522 |
EMS | -1.480 |
LIST | -1.462 |
Kind | -1.456 |
Imper | -1.432 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
banter | +0.793 |
puter | +0.784 |
egu | +0.777 |
ottesville | +0.743 |
ousy | +0.742 |
Neg logit contributions | |
ONS | -0.938 |
EMS | -0.912 |
LIST | -0.904 |
Kind | -0.902 |
Imper | -0.872 |
Token |
|
Token ID | 198 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
banter | +0.144 |
egu | +0.141 |
puter | +0.141 |
ousy | +0.135 |
dop | +0.134 |
Neg logit contributions | |
ONS | -0.160 |
EMS | -0.155 |
LIST | -0.153 |
Kind | -0.152 |
Imper | -0.149 |
Token | The |
Token ID | 464 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
banter | +0.383 |
puter | +0.383 |
egu | +0.382 |
ousy | +0.367 |
ottesville | +0.366 |
Neg logit contributions | |
ONS | -0.276 |
EMS | -0.265 |
LIST | -0.261 |
Kind | -0.260 |
Imper | -0.257 |
Token | APD |
Token ID | 35349 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
banter | +0.460 |
egu | +0.460 |
puter | +0.459 |
ousy | +0.442 |
ottesville | +0.438 |
Neg logit contributions | |
ONS | -0.449 |
EMS | -0.436 |
Kind | -0.436 |
LIST | -0.433 |
Imper | -0.420 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
banter | +1.881 |
puter | +1.861 |
egu | +1.849 |
ottesville | +1.780 |
ousy | +1.778 |
Neg logit contributions | |
ONS | -2.084 |
EMS | -2.037 |
Kind | -2.018 |
LIST | -2.013 |
Imper | -1.948 |
Token |
|
Token ID | 198 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
banter | +0.236 |
puter | +0.232 |
egu | +0.230 |
ottesville | +0.221 |
ousy | +0.221 |
Neg logit contributions | |
ONS | -0.254 |
EMS | -0.247 |
LIST | -0.244 |
Kind | -0.243 |
ALS | -0.235 |
Token |
|
Token ID | 198 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
banter | +0.304 |
egu | +0.297 |
puter | +0.297 |
ousy | +0.284 |
ottesville | +0.283 |
Neg logit contributions | |
ONS | -0.342 |
EMS | -0.331 |
LIST | -0.327 |
Kind | -0.325 |
Imper | -0.319 |
Token | The |
Token ID | 464 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
banter | +0.616 |
puter | +0.615 |
egu | +0.609 |
ottesville | +0.589 |
ousy | +0.587 |
Neg logit contributions | |
ONS | -0.455 |
EMS | -0.437 |
LIST | -0.430 |
Kind | -0.428 |
Imper | -0.424 |
Token | defeat |
Token ID | 7433 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
banter | +0.286 |
puter | +0.283 |
egu | +0.279 |
dop | +0.269 |
ottesville | +0.269 |
Neg logit contributions | |
ONS | -0.318 |
EMS | -0.308 |
LIST | -0.306 |
Kind | -0.304 |
ALS | -0.294 |
Token | of |
Token ID | 286 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
banter | +0.368 |
puter | +0.366 |
egu | +0.361 |
ottesville | +0.347 |
ousy | +0.345 |
Neg logit contributions | |
ONS | -0.429 |
EMS | -0.416 |
LIST | -0.414 |
Kind | -0.411 |
Imper | -0.400 |
Token | the |
Token ID | 262 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
banter | +0.538 |
puter | +0.531 |
egu | +0.526 |
dop | +0.507 |
ottesville | +0.506 |
Neg logit contributions | |
ONS | -0.553 |
EMS | -0.535 |
LIST | -0.530 |
Kind | -0.529 |
ALS | -0.510 |
Token | Russian |
Token ID | 3394 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
banter | +0.465 |
puter | +0.459 |
egu | +0.455 |
dop | +0.439 |
ottesville | +0.437 |
Neg logit contributions | |
ONS | -0.494 |
EMS | -0.479 |
LIST | -0.476 |
Kind | -0.474 |
ALS | -0.457 |
Token | Revolution |
Token ID | 9303 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
banter | +0.346 |
puter | +0.342 |
egu | +0.338 |
ottesville | +0.326 |
dop | +0.325 |
Neg logit contributions | |
ONS | -0.361 |
EMS | -0.350 |
LIST | -0.347 |
Kind | -0.346 |
ALS | -0.334 |
Token | , |
Token ID | 11 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
banter | +0.819 |
puter | +0.814 |
egu | +0.805 |
ottesville | +0.773 |
ousy | +0.769 |
Neg logit contributions | |
ONS | -0.961 |
EMS | -0.931 |
LIST | -0.925 |
Kind | -0.921 |
Imper | -0.892 |
Token | year |
Token ID | 614 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ONS | +0.540 |
EMS | +0.521 |
LIST | +0.518 |
Kind | +0.515 |
Imper | +0.499 |
Neg logit contributions | |
banter | -0.552 |
puter | -0.549 |
egu | -0.543 |
ottesville | -0.523 |
ousy | -0.521 |
Token | China |
Token ID | 2807 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
banter | +0.401 |
puter | +0.396 |
egu | +0.391 |
dop | +0.374 |
ottesville | +0.372 |
Neg logit contributions | |
ONS | -0.513 |
EMS | -0.497 |
LIST | -0.496 |
Kind | -0.493 |
ALS | -0.478 |
Token | became |
Token ID | 2627 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ONS | +0.758 |
EMS | +0.733 |
LIST | +0.730 |
Kind | +0.726 |
Imper | +0.703 |
Neg logit contributions | |
banter | -0.650 |
puter | -0.645 |
egu | -0.638 |
ottesville | -0.611 |
dop | -0.609 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
banter | +0.212 |
puter | +0.211 |
egu | +0.209 |
dop | +0.201 |
ousy | +0.200 |
Neg logit contributions | |
ONS | -0.199 |
LIST | -0.191 |
EMS | -0.191 |
Kind | -0.190 |
ALS | -0.184 |
Token | largest |
Token ID | 4387 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ONS | +0.171 |
EMS | +0.165 |
LIST | +0.165 |
Kind | +0.164 |
ALS | +0.159 |
Neg logit contributions | |
banter | -0.189 |
puter | -0.186 |
egu | -0.185 |
dop | -0.179 |
ottesville | -0.177 |
Token | purchaser |
Token ID | 39122 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
banter | +1.652 |
puter | +1.616 |
egu | +1.593 |
dop | +1.558 |
ousy | +1.512 |
Neg logit contributions | |
ONS | -2.144 |
EMS | -2.074 |
Kind | -2.073 |
LIST | -2.048 |
ALS | -2.023 |
Token | of |
Token ID | 286 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
banter | +0.486 |
puter | +0.483 |
egu | +0.477 |
ottesville | +0.459 |
ousy | +0.457 |
Neg logit contributions | |
ONS | -0.546 |
EMS | -0.528 |
LIST | -0.525 |
Kind | -0.522 |
Imper | -0.507 |
Token | jet |
Token ID | 12644 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
banter | +0.198 |
puter | +0.194 |
egu | +0.191 |
dop | +0.186 |
ousy | +0.182 |
Neg logit contributions | |
ONS | -0.247 |
EMS | -0.239 |
LIST | -0.238 |
Kind | -0.238 |
ALS | -0.231 |
Token | liners |
Token ID | 34380 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
banter | +0.401 |
puter | +0.395 |
egu | +0.387 |
ottesville | +0.366 |
ousy | +0.365 |
Neg logit contributions | |
ONS | -0.730 |
EMS | -0.710 |
LIST | -0.708 |
Kind | -0.708 |
Imper | -0.689 |
Token | on |
Token ID | 319 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
banter | +0.251 |
puter | +0.249 |
egu | +0.244 |
dop | +0.235 |
ousy | +0.234 |
Neg logit contributions | |
ONS | -0.311 |
EMS | -0.301 |
LIST | -0.300 |
Kind | -0.299 |
ALS | -0.290 |
Token | the |
Token ID | 262 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
banter | +0.147 |
puter | +0.146 |
egu | +0.143 |
dop | +0.138 |
ousy | +0.138 |
Neg logit contributions | |
ONS | -0.141 |
EMS | -0.136 |
Kind | -0.135 |
LIST | -0.135 |
ALS | -0.130 |
Token | I |
Token ID | 314 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
banter | +0.474 |
puter | +0.468 |
egu | +0.460 |
dop | +0.442 |
ottesville | +0.441 |
Neg logit contributions | |
ONS | -0.583 |
EMS | -0.565 |
LIST | -0.563 |
Kind | -0.559 |
ALS | -0.543 |
Token | don |
Token ID | 836 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
banter | +0.207 |
puter | +0.206 |
egu | +0.203 |
ottesville | +0.195 |
ousy | +0.194 |
Neg logit contributions | |
ONS | -0.268 |
EMS | -0.260 |
LIST | -0.259 |
Kind | -0.257 |
Imper | -0.251 |
Token | 't |
Token ID | 470 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
banter | +1.290 |
egu | +1.268 |
puter | +1.250 |
ousy | +1.207 |
dop | +1.198 |
Neg logit contributions | |
ONS | -1.416 |
EMS | -1.370 |
LIST | -1.354 |
Kind | -1.338 |
Imper | -1.320 |
Token | even |
Token ID | 772 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ONS | +0.190 |
EMS | +0.184 |
LIST | +0.183 |
Kind | +0.182 |
Imper | +0.178 |
Neg logit contributions | |
banter | -0.142 |
puter | -0.142 |
egu | -0.140 |
ottesville | -0.134 |
ousy | -0.133 |
Token | play |
Token ID | 711 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ONS | +1.492 |
EMS | +1.436 |
LIST | +1.436 |
Kind | +1.423 |
Imper | +1.401 |
Neg logit contributions | |
puter | -1.252 |
banter | -1.242 |
egu | -1.237 |
ottesville | -1.209 |
ousy | -1.185 |
Token | games |
Token ID | 1830 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
banter | +0.297 |
puter | +0.294 |
egu | +0.290 |
ottesville | +0.277 |
dop | +0.277 |
Neg logit contributions | |
ONS | -0.387 |
EMS | -0.376 |
LIST | -0.374 |
Kind | -0.372 |
ALS | -0.361 |
Token | with |
Token ID | 351 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
banter | +0.603 |
puter | +0.598 |
egu | +0.588 |
ottesville | +0.565 |
ousy | +0.564 |
Neg logit contributions | |
ONS | -0.701 |
EMS | -0.680 |
LIST | -0.675 |
Kind | -0.672 |
Imper | -0.651 |
Token | AA |
Token ID | 15923 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
banter | +0.688 |
puter | +0.680 |
egu | +0.672 |
ottesville | +0.642 |
dop | +0.641 |
Neg logit contributions | |
ONS | -0.892 |
EMS | -0.866 |
LIST | -0.862 |
Kind | -0.857 |
Imper | -0.830 |
Token | on |
Token ID | 319 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
banter | +0.010 |
puter | +0.010 |
egu | +0.010 |
ottesville | +0.010 |
ousy | +0.010 |
Neg logit contributions | |
ONS | -0.013 |
EMS | -0.013 |
LIST | -0.013 |
Kind | -0.013 |
Imper | -0.012 |
Token | ( |
Token ID | 357 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ONS | +0.230 |
EMS | +0.222 |
LIST | +0.221 |
Kind | +0.220 |
Imper | +0.215 |
Neg logit contributions | |
banter | -0.187 |
puter | -0.185 |
egu | -0.184 |
ottesville | -0.178 |
ousy | -0.175 |
Token | Anti |
Token ID | 28795 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
ONS | +0.919 |
EMS | +0.888 |
LIST | +0.882 |
Kind | +0.879 |
ALS | +0.848 |
Neg logit contributions | |
banter | -0.946 |
puter | -0.938 |
egu | -0.929 |
ottesville | -0.898 |
ousy | -0.892 |
Token | had |
Token ID | 550 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
banter | +0.482 |
puter | +0.474 |
egu | +0.474 |
dop | +0.454 |
ottesville | +0.452 |
Neg logit contributions | |
ONS | -0.532 |
EMS | -0.519 |
LIST | -0.515 |
Kind | -0.512 |
ALS | -0.496 |
Token | evidence |
Token ID | 2370 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ONS | +0.388 |
EMS | +0.378 |
LIST | +0.374 |
Kind | +0.373 |
ALS | +0.362 |
Neg logit contributions | |
banter | -0.307 |
puter | -0.303 |
egu | -0.300 |
ottesville | -0.287 |
dop | -0.287 |
Token | of |
Token ID | 286 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ONS | +0.091 |
EMS | +0.088 |
LIST | +0.088 |
Kind | +0.087 |
Imper | +0.085 |
Neg logit contributions | |
banter | -0.081 |
puter | -0.079 |
egu | -0.078 |
dop | -0.075 |
ousy | -0.075 |
Token | institutional |
Token ID | 15855 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
banter | +1.117 |
egu | +1.066 |
puter | +1.060 |
dop | +1.032 |
ottesville | +1.013 |
Neg logit contributions | |
ONS | -1.194 |
EMS | -1.167 |
LIST | -1.158 |
Kind | -1.156 |
ALS | -1.115 |
Token | ised |
Token ID | 1417 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
ONS | +0.578 |
EMS | +0.560 |
LIST | +0.556 |
Kind | +0.553 |
Imper | +0.537 |
Neg logit contributions | |
banter | -0.535 |
puter | -0.531 |
egu | -0.525 |
ottesville | -0.505 |
ousy | -0.503 |
Token | local |
Token ID | 1957 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ONS | +0.569 |
EMS | +0.553 |
LIST | +0.549 |
Kind | +0.546 |
Imper | +0.530 |
Neg logit contributions | |
banter | -0.464 |
puter | -0.457 |
egu | -0.452 |
ottesville | -0.434 |
ousy | -0.432 |
Token | government |
Token ID | 1230 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
ONS | +0.179 |
EMS | +0.173 |
LIST | +0.173 |
Kind | +0.171 |
Imper | +0.166 |
Neg logit contributions | |
banter | -0.155 |
puter | -0.152 |
egu | -0.151 |
ottesville | -0.145 |
dop | -0.144 |
Token | discrimination |
Token ID | 8839 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
banter | +0.510 |
puter | +0.502 |
egu | +0.498 |
ottesville | +0.478 |
dop | +0.477 |
Neg logit contributions | |
ONS | -0.570 |
EMS | -0.553 |
LIST | -0.549 |
Kind | -0.546 |
Imper | -0.530 |
Token | against |
Token ID | 1028 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
banter | +0.828 |
puter | +0.813 |
egu | +0.807 |
ottesville | +0.771 |
dop | +0.771 |
Neg logit contributions | |
ONS | -1.014 |
EMS | -0.989 |
LIST | -0.980 |
Kind | -0.974 |
ALS | -0.944 |
Token | Rohingya |
Token ID | 34016 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ONS | +0.335 |
EMS | +0.324 |
LIST | +0.322 |
Kind | +0.320 |
Imper | +0.309 |
Neg logit contributions | |
banter | -0.362 |
puter | -0.358 |
egu | -0.355 |
ottesville | -0.342 |
dop | -0.342 |
Token | . |
Token ID | 13 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
ONS | +0.792 |
EMS | +0.769 |
LIST | +0.763 |
Kind | +0.758 |
Imper | +0.736 |
Neg logit contributions | |
banter | -0.684 |
puter | -0.674 |
egu | -0.669 |
ottesville | -0.641 |
ousy | -0.639 |
Token | reverse |
Token ID | 9575 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
banter | +0.301 |
puter | +0.296 |
egu | +0.293 |
dop | +0.282 |
ottesville | +0.282 |
Neg logit contributions | |
ONS | -0.298 |
EMS | -0.289 |
LIST | -0.286 |
Kind | -0.283 |
ALS | -0.275 |
Token | the |
Token ID | 262 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ONS | +1.326 |
EMS | +1.282 |
LIST | +1.277 |
Kind | +1.270 |
Imper | +1.236 |
Neg logit contributions | |
banter | -1.171 |
puter | -1.167 |
egu | -1.156 |
ottesville | -1.110 |
ousy | -1.105 |
Token | crossing |
Token ID | 12538 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
banter | +0.119 |
puter | +0.117 |
egu | +0.115 |
dop | +0.112 |
ottesville | +0.111 |
Neg logit contributions | |
ONS | -0.133 |
EMS | -0.130 |
LIST | -0.128 |
Kind | -0.127 |
ALS | -0.123 |
Token | route |
Token ID | 6339 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
banter | +0.710 |
puter | +0.698 |
egu | +0.689 |
ottesville | +0.661 |
dop | +0.660 |
Neg logit contributions | |
ONS | -0.849 |
EMS | -0.823 |
LIST | -0.816 |
Kind | -0.812 |
ALS | -0.788 |
Token | of |
Token ID | 286 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
banter | +0.205 |
puter | +0.202 |
egu | +0.199 |
dop | +0.191 |
ottesville | +0.190 |
Neg logit contributions | |
ONS | -0.245 |
EMS | -0.238 |
LIST | -0.236 |
Kind | -0.235 |
ALS | -0.227 |
Token | another |
Token ID | 1194 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ONS | +0.087 |
EMS | +0.084 |
LIST | +0.083 |
Kind | +0.083 |
ALS | +0.080 |
Neg logit contributions | |
banter | -0.091 |
puter | -0.090 |
egu | -0.089 |
dop | -0.086 |
ottesville | -0.086 |
Token | celebrated |
Token ID | 13943 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ONS | +0.841 |
EMS | +0.812 |
LIST | +0.808 |
Kind | +0.804 |
Imper | +0.783 |
Neg logit contributions | |
banter | -0.780 |
puter | -0.777 |
egu | -0.768 |
ottesville | -0.739 |
ousy | -0.736 |
Token | inv |
Token ID | 800 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ONS | +0.335 |
EMS | +0.325 |
LIST | +0.323 |
Kind | +0.322 |
Imper | +0.312 |
Neg logit contributions | |
banter | -0.270 |
puter | -0.268 |
egu | -0.265 |
ottesville | -0.254 |
ousy | -0.253 |
Token | ader |
Token ID | 5067 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
banter | +0.314 |
puter | +0.314 |
egu | +0.312 |
ottesville | +0.303 |
ousy | +0.300 |
Neg logit contributions | |
ONS | -0.239 |
EMS | -0.229 |
LIST | -0.226 |
Kind | -0.224 |
ALS | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
banter | +0.592 |
puter | +0.584 |
egu | +0.577 |
ottesville | +0.554 |
dop | +0.552 |
Neg logit contributions | |
ONS | -0.762 |
EMS | -0.743 |
LIST | -0.735 |
Kind | -0.730 |
ALS | -0.710 |
Token | In |
Token ID | 554 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
ONS | +0.255 |
EMS | +0.248 |
LIST | +0.245 |
Kind | +0.243 |
ALS | +0.236 |
Neg logit contributions | |
banter | -0.245 |
puter | -0.242 |
egu | -0.240 |
ottesville | -0.231 |
ousy | -0.230 |
Token | " |
Token ID | 366 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ONS | +0.067 |
EMS | +0.065 |
LIST | +0.064 |
Kind | +0.064 |
ALS | +0.062 |
Neg logit contributions | |
banter | -0.061 |
puter | -0.060 |
egu | -0.059 |
dop | -0.057 |
ottesville | -0.057 |
Token | to |
Token ID | 1462 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
ONS | +0.127 |
EMS | +0.122 |
LIST | +0.121 |
Kind | +0.120 |
Imper | +0.118 |
Neg logit contributions | |
banter | -0.132 |
puter | -0.132 |
egu | -0.130 |
ottesville | -0.126 |
ousy | -0.125 |
Token | err |
Token ID | 11454 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
ONS | +0.225 |
EMS | +0.218 |
LIST | +0.217 |
Kind | +0.215 |
Imper | +0.210 |
Neg logit contributions | |
banter | -0.195 |
puter | -0.193 |
egu | -0.191 |
ottesville | -0.183 |
ousy | -0.182 |
Token | is |
Token ID | 318 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
banter | +0.633 |
puter | +0.629 |
egu | +0.616 |
ottesville | +0.596 |
ousy | +0.596 |
Neg logit contributions | |
ONS | -0.718 |
EMS | -0.700 |
LIST | -0.697 |
Kind | -0.692 |
ALS | -0.671 |
Token | human |
Token ID | 1692 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
ONS | +0.333 |
EMS | +0.323 |
LIST | +0.321 |
Kind | +0.319 |
Imper | +0.310 |
Neg logit contributions | |
banter | -0.290 |
puter | -0.288 |
egu | -0.285 |
ottesville | -0.274 |
ousy | -0.272 |
Token | " |
Token ID | 1 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
banter | +0.422 |
puter | +0.415 |
egu | +0.410 |
ottesville | +0.393 |
ousy | +0.393 |
Neg logit contributions | |
ONS | -0.517 |
EMS | -0.501 |
LIST | -0.498 |
Kind | -0.494 |
Imper | -0.481 |
Token | to |
Token ID | 284 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ONS | +1.547 |
EMS | +1.492 |
LIST | +1.491 |
Kind | +1.480 |
Imper | +1.435 |
Neg logit contributions | |
puter | -1.537 |
banter | -1.528 |
egu | -1.523 |
ottesville | -1.477 |
ousy | -1.456 |
Token | accusations |
Token ID | 14227 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
banter | +0.089 |
puter | +0.089 |
egu | +0.088 |
ottesville | +0.085 |
ousy | +0.084 |
Neg logit contributions | |
ONS | -0.088 |
EMS | -0.085 |
LIST | -0.084 |
Kind | -0.084 |
Imper | -0.081 |
Token | of |
Token ID | 286 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ONS | +0.602 |
EMS | +0.581 |
LIST | +0.579 |
Kind | +0.575 |
Imper | +0.560 |
Neg logit contributions | |
banter | -0.541 |
puter | -0.539 |
egu | -0.533 |
ottesville | -0.513 |
ousy | -0.509 |
Token | " |
Token ID | 366 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
banter | +0.247 |
puter | +0.242 |
egu | +0.238 |
dop | +0.231 |
ottesville | +0.228 |
Neg logit contributions | |
ONS | -0.279 |
EMS | -0.272 |
LIST | -0.269 |
Kind | -0.267 |
ALS | -0.259 |
Token | a |
Token ID | 64 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ONS | +0.485 |
EMS | +0.470 |
LIST | +0.466 |
Kind | +0.464 |
Imper | +0.451 |
Neg logit contributions | |
banter | -0.429 |
puter | -0.427 |
egu | -0.422 |
ottesville | -0.405 |
ousy | -0.403 |
Token | has |
Token ID | 468 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
banter | +0.345 |
puter | +0.342 |
egu | +0.337 |
ottesville | +0.324 |
dop | +0.322 |
Neg logit contributions | |
ONS | -0.419 |
EMS | -0.405 |
LIST | -0.403 |
Kind | -0.401 |
Imper | -0.389 |
Token | had |
Token ID | 550 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
banter | +0.391 |
puter | +0.387 |
egu | +0.381 |
dop | +0.365 |
ottesville | +0.364 |
Neg logit contributions | |
ONS | -0.536 |
EMS | -0.519 |
LIST | -0.516 |
Kind | -0.514 |
ALS | -0.499 |
Token | an |
Token ID | 281 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
banter | +0.163 |
puter | +0.161 |
egu | +0.159 |
dop | +0.153 |
ousy | +0.152 |
Neg logit contributions | |
ONS | -0.191 |
EMS | -0.186 |
LIST | -0.184 |
Kind | -0.183 |
ALS | -0.178 |
Token | uncertain |
Token ID | 8627 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ONS | +0.018 |
LIST | +0.018 |
EMS | +0.018 |
Kind | +0.018 |
ALS | +0.017 |
Neg logit contributions | |
banter | -0.015 |
puter | -0.015 |
egu | -0.014 |
ousy | -0.014 |
dop | -0.014 |
Token | era |
Token ID | 6980 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
banter | +1.274 |
puter | +1.229 |
egu | +1.223 |
dop | +1.189 |
ousy | +1.167 |
Neg logit contributions | |
ONS | -1.573 |
EMS | -1.520 |
LIST | -1.514 |
Kind | -1.506 |
ALS | -1.468 |
Token | following |
Token ID | 1708 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
banter | +0.105 |
puter | +0.104 |
egu | +0.103 |
ottesville | +0.099 |
ousy | +0.099 |
Neg logit contributions | |
ONS | -0.119 |
EMS | -0.115 |
LIST | -0.114 |
Kind | -0.114 |
Imper | -0.111 |
Token | a |
Token ID | 257 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
banter | +0.242 |
puter | +0.240 |
egu | +0.237 |
ottesville | +0.228 |
ousy | +0.228 |
Neg logit contributions | |
ONS | -0.247 |
EMS | -0.239 |
LIST | -0.237 |
Kind | -0.235 |
Imper | -0.228 |
Token | strong |
Token ID | 1913 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
banter | +0.334 |
puter | +0.331 |
egu | +0.326 |
dop | +0.315 |
ousy | +0.312 |
Neg logit contributions | |
ONS | -0.382 |
EMS | -0.369 |
LIST | -0.367 |
Kind | -0.363 |
ALS | -0.354 |
Token | class |
Token ID | 1398 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
banter | +0.382 |
puter | +0.378 |
egu | +0.373 |
ottesville | +0.358 |
ousy | +0.357 |
Neg logit contributions | |
ONS | -0.474 |
EMS | -0.460 |
LIST | -0.457 |
Kind | -0.454 |
ALS | -0.442 |
Token | of |
Token ID | 286 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
banter | +0.041 |
puter | +0.041 |
egu | +0.040 |
ottesville | +0.039 |
ousy | +0.039 |
Neg logit contributions | |
ONS | -0.047 |
EMS | -0.045 |
LIST | -0.045 |
Kind | -0.045 |
ALS | -0.043 |
Token | kick |
Token ID | 4829 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
banter | +0.142 |
puter | +0.141 |
egu | +0.139 |
ottesville | +0.133 |
ousy | +0.132 |
Neg logit contributions | |
ONS | -0.193 |
EMS | -0.187 |
LIST | -0.186 |
Kind | -0.185 |
Imper | -0.180 |
Token | Championship |
Token ID | 10749 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ONS | +0.140 |
EMS | +0.135 |
LIST | +0.135 |
Kind | +0.134 |
Imper | +0.130 |
Neg logit contributions | |
banter | -0.121 |
puter | -0.120 |
egu | -0.118 |
ousy | -0.113 |
ottesville | -0.113 |
Token | in |
Token ID | 287 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ONS | +0.232 |
EMS | +0.225 |
LIST | +0.224 |
Kind | +0.222 |
Imper | +0.215 |
Neg logit contributions | |
banter | -0.187 |
puter | -0.185 |
egu | -0.182 |
ottesville | -0.175 |
ousy | -0.175 |
Token | 1949 |
Token ID | 24977 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
banter | +0.146 |
puter | +0.144 |
egu | +0.142 |
ousy | +0.135 |
dop | +0.135 |
Neg logit contributions | |
ONS | -0.248 |
EMS | -0.241 |
LIST | -0.239 |
Kind | -0.237 |
ALS | -0.232 |
Token | — |
Token ID | 960 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ONS | +0.030 |
EMS | +0.029 |
LIST | +0.029 |
Kind | +0.028 |
Imper | +0.028 |
Neg logit contributions | |
banter | -0.025 |
puter | -0.025 |
egu | -0.025 |
ottesville | -0.024 |
ousy | -0.024 |
Token | a |
Token ID | 64 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
ONS | +0.231 |
EMS | +0.223 |
LIST | +0.221 |
Kind | +0.220 |
Imper | +0.214 |
Neg logit contributions | |
banter | -0.245 |
puter | -0.244 |
egu | -0.241 |
ottesville | -0.232 |
ousy | -0.232 |
Token | game |
Token ID | 983 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
banter | +0.024 |
puter | +0.024 |
egu | +0.024 |
dop | +0.023 |
ottesville | +0.023 |
Neg logit contributions | |
ONS | -0.027 |
EMS | -0.027 |
LIST | -0.026 |
Kind | -0.026 |
Imper | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
ONS | +0.028 |
EMS | +0.027 |
LIST | +0.027 |
Kind | +0.027 |
Imper | +0.026 |
Neg logit contributions | |
banter | -0.024 |
puter | -0.024 |
egu | -0.023 |
ottesville | -0.022 |
ousy | -0.022 |
Token | which |
Token ID | 543 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
banter | +0.149 |
puter | +0.147 |
egu | +0.145 |
ousy | +0.138 |
ottesville | +0.138 |
Neg logit contributions | |
ONS | -0.213 |
EMS | -0.206 |
LIST | -0.205 |
Kind | -0.204 |
Imper | -0.199 |
Token | the |
Token ID | 262 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
ONS | +0.441 |
EMS | +0.426 |
LIST | +0.424 |
Kind | +0.422 |
Imper | +0.408 |
Neg logit contributions | |
banter | -0.411 |
puter | -0.406 |
egu | -0.400 |
ousy | -0.386 |
ottesville | -0.385 |
Token | Philadelphia |
Token ID | 8857 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ONS | +0.369 |
EMS | +0.358 |
LIST | +0.356 |
Kind | +0.354 |
Imper | +0.343 |
Neg logit contributions | |
banter | -0.301 |
puter | -0.296 |
egu | -0.292 |
ottesville | -0.281 |
dop | -0.280 |
Token | Eagles |
Token ID | 13785 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
banter | +1.110 |
puter | +1.100 |
egu | +1.089 |
ottesville | +1.055 |
ousy | +1.053 |
Neg logit contributions | |
ONS | -0.861 |
EMS | -0.827 |
LIST | -0.825 |
Kind | -0.815 |
ALS | -0.785 |
Token | disappointed |
Token ID | 11679 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
banter | +0.379 |
puter | +0.372 |
egu | +0.368 |
dop | +0.356 |
ottesville | +0.352 |
Neg logit contributions | |
ONS | -0.481 |
EMS | -0.466 |
LIST | -0.464 |
Kind | -0.462 |
ALS | -0.448 |
Token | but |
Token ID | 475 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
ONS | +0.055 |
EMS | +0.054 |
LIST | +0.053 |
Kind | +0.053 |
Imper | +0.052 |
Neg logit contributions | |
banter | -0.046 |
puter | -0.046 |
egu | -0.045 |
ottesville | -0.043 |
ousy | -0.043 |
Token | Canadians |
Token ID | 14008 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ONS | +0.308 |
EMS | +0.299 |
LIST | +0.297 |
Kind | +0.295 |
Imper | +0.287 |
Neg logit contributions | |
banter | -0.260 |
puter | -0.257 |
egu | -0.253 |
ousy | -0.243 |
dop | -0.242 |
Token | as |
Token ID | 355 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ONS | +1.573 |
EMS | +1.523 |
LIST | +1.514 |
Kind | +1.508 |
Imper | +1.465 |
Neg logit contributions | |
banter | -1.333 |
puter | -1.325 |
egu | -1.309 |
ottesville | -1.258 |
ousy | -1.250 |
Token | a |
Token ID | 257 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
banter | +0.198 |
puter | +0.195 |
egu | +0.191 |
dop | +0.184 |
ottesville | +0.183 |
Neg logit contributions | |
ONS | -0.274 |
EMS | -0.269 |
LIST | -0.267 |
Kind | -0.263 |
ALS | -0.259 |
Token | whole |
Token ID | 2187 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
ONS | +0.196 |
EMS | +0.191 |
LIST | +0.188 |
Kind | +0.187 |
Imper | +0.182 |
Neg logit contributions | |
banter | -0.207 |
puter | -0.205 |
egu | -0.202 |
dop | -0.195 |
ottesville | -0.194 |
Token | are |
Token ID | 389 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ONS | +3.314 |
EMS | +3.199 |
LIST | +3.177 |
Kind | +3.170 |
Imper | +3.061 |
Neg logit contributions | |
puter | -3.092 |
banter | -3.081 |
egu | -3.056 |
ottesville | -2.924 |
ousy | -2.908 |
Token | , |
Token ID | 11 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ONS | +0.364 |
EMS | +0.352 |
LIST | +0.350 |
Kind | +0.349 |
Imper | +0.339 |
Neg logit contributions | |
banter | -0.298 |
puter | -0.295 |
egu | -0.291 |
ottesville | -0.280 |
dop | -0.279 |
Token | � |
Token ID | 447 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ONS | +0.198 |
EMS | +0.192 |
LIST | +0.191 |
Kind | +0.190 |
Imper | +0.184 |
Neg logit contributions | |
banter | -0.171 |
puter | -0.170 |
egu | -0.168 |
ottesville | -0.161 |
ousy | -0.160 |
Token | � |
Token ID | 251 |
Feature activation | +8.39e-03 |
Pos logit contributions | |
banter | +0.096 |
puter | +0.095 |
egu | +0.094 |
ottesville | +0.090 |
ousy | +0.089 |
Neg logit contributions | |
ONS | -0.131 |
EMS | -0.127 |
LIST | -0.126 |
Kind | -0.126 |
Imper | -0.122 |
Token | said |
Token ID | 531 |
Feature activation | +5.68e-03 |
Pos logit contributions | |
banter | +0.005 |
puter | +0.005 |
egu | +0.005 |
ottesville | +0.005 |
ousy | +0.005 |
Neg logit contributions | |
ONS | -0.007 |
EMS | -0.007 |
LIST | -0.006 |
Kind | -0.006 |
Imper | -0.006 |
Token | British |
Token ID | 3517 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ONS | +0.337 |
EMS | +0.327 |
LIST | +0.325 |
Kind | +0.323 |
Imper | +0.313 |
Neg logit contributions | |
banter | -0.294 |
puter | -0.291 |
egu | -0.287 |
ottesville | -0.275 |
dop | -0.275 |
Token | citizen |
Token ID | 9511 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ONS | +0.269 |
EMS | +0.259 |
LIST | +0.258 |
Kind | +0.256 |
Imper | +0.249 |
Neg logit contributions | |
banter | -0.256 |
puter | -0.255 |
egu | -0.253 |
ottesville | -0.244 |
ousy | -0.242 |
Token | who |
Token ID | 508 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
banter | +0.399 |
puter | +0.396 |
egu | +0.390 |
ousy | +0.373 |
ottesville | +0.373 |
Neg logit contributions | |
ONS | -0.488 |
EMS | -0.475 |
LIST | -0.470 |
Kind | -0.469 |
ALS | -0.454 |
Token | had |
Token ID | 550 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
banter | +0.025 |
puter | +0.025 |
egu | +0.024 |
ottesville | +0.023 |
dop | +0.023 |
Neg logit contributions | |
ONS | -0.034 |
EMS | -0.033 |
LIST | -0.033 |
Kind | -0.033 |
ALS | -0.032 |
Token | been |
Token ID | 587 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
banter | +0.038 |
puter | +0.037 |
egu | +0.037 |
dop | +0.035 |
ottesville | +0.035 |
Neg logit contributions | |
ONS | -0.055 |
EMS | -0.054 |
LIST | -0.053 |
Kind | -0.053 |
ALS | -0.052 |
Token | born |
Token ID | 4642 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ONS | +1.082 |
EMS | +1.049 |
LIST | +1.043 |
Kind | +1.038 |
Imper | +1.010 |
Neg logit contributions | |
banter | -0.843 |
puter | -0.838 |
egu | -0.827 |
ottesville | -0.793 |
ousy | -0.788 |
Token | in |
Token ID | 287 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ONS | +2.362 |
LIST | +2.268 |
EMS | +2.251 |
Kind | +2.240 |
Imper | +2.200 |
Neg logit contributions | |
puter | -2.544 |
banter | -2.544 |
egu | -2.510 |
ottesville | -2.428 |
ousy | -2.409 |
Token | Pakistan |
Token ID | 7648 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
ONS | +0.157 |
EMS | +0.153 |
LIST | +0.151 |
Kind | +0.150 |
ALS | +0.145 |
Neg logit contributions | |
banter | -0.176 |
puter | -0.174 |
egu | -0.173 |
ottesville | -0.166 |
ousy | -0.166 |
Token | , |
Token ID | 11 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
banter | +0.379 |
puter | +0.377 |
egu | +0.373 |
ousy | +0.355 |
ottesville | +0.355 |
Neg logit contributions | |
ONS | -0.495 |
EMS | -0.481 |
LIST | -0.475 |
Kind | -0.474 |
Imper | -0.459 |
Token | the |
Token ID | 262 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
banter | +0.299 |
puter | +0.293 |
egu | +0.291 |
ousy | +0.277 |
dop | +0.277 |
Neg logit contributions | |
ONS | -0.370 |
EMS | -0.361 |
LIST | -0.357 |
Kind | -0.357 |
ALS | -0.345 |
Token | police |
Token ID | 1644 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
banter | +0.254 |
puter | +0.251 |
egu | +0.248 |
ottesville | +0.237 |
dop | +0.237 |
Neg logit contributions | |
ONS | -0.311 |
EMS | -0.302 |
LIST | -0.300 |
Kind | -0.299 |
ALS | -0.290 |
Token | political |
Token ID | 1964 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
banter | +0.997 |
puter | +0.962 |
egu | +0.939 |
dop | +0.930 |
ottesville | +0.901 |
Neg logit contributions | |
ONS | -1.299 |
EMS | -1.263 |
LIST | -1.247 |
Kind | -1.244 |
ALS | -1.216 |
Token | move |
Token ID | 1445 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ONS | +0.886 |
EMS | +0.860 |
LIST | +0.855 |
Kind | +0.851 |
Imper | +0.826 |
Neg logit contributions | |
banter | -0.692 |
puter | -0.684 |
egu | -0.675 |
ottesville | -0.648 |
ousy | -0.644 |
Token | they |
Token ID | 484 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ONS | +0.351 |
EMS | +0.341 |
LIST | +0.339 |
Kind | +0.337 |
Imper | +0.328 |
Neg logit contributions | |
banter | -0.277 |
puter | -0.275 |
egu | -0.271 |
ottesville | -0.260 |
ousy | -0.259 |
Token | are |
Token ID | 389 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ONS | +0.172 |
EMS | +0.167 |
LIST | +0.166 |
Kind | +0.165 |
Imper | +0.160 |
Neg logit contributions | |
banter | -0.145 |
puter | -0.144 |
egu | -0.142 |
ottesville | -0.137 |
ousy | -0.136 |
Token | now |
Token ID | 783 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
banter | +0.730 |
puter | +0.717 |
egu | +0.704 |
dop | +0.689 |
ottesville | +0.676 |
Neg logit contributions | |
ONS | -0.861 |
EMS | -0.837 |
LIST | -0.831 |
Kind | -0.829 |
Imper | -0.804 |
Token | stunned |
Token ID | 19987 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
banter | +0.972 |
puter | +0.950 |
egu | +0.933 |
dop | +0.917 |
ottesville | +0.892 |
Neg logit contributions | |
ONS | -1.203 |
EMS | -1.171 |
LIST | -1.161 |
Kind | -1.159 |
Imper | -1.124 |
Token | at |
Token ID | 379 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ONS | +2.805 |
EMS | +2.730 |
LIST | +2.725 |
Kind | +2.686 |
Imper | +2.628 |
Neg logit contributions | |
puter | -2.400 |
banter | -2.378 |
egu | -2.360 |
ottesville | -2.277 |
ousy | -2.236 |
Token | the |
Token ID | 262 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
banter | +1.323 |
puter | +1.284 |
egu | +1.281 |
dop | +1.245 |
ousy | +1.240 |
Neg logit contributions | |
ONS | -1.432 |
EMS | -1.368 |
Kind | -1.359 |
LIST | -1.356 |
ALS | -1.318 |
Token | criticism |
Token ID | 7734 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
banter | +0.240 |
puter | +0.231 |
egu | +0.230 |
dop | +0.226 |
ousy | +0.219 |
Neg logit contributions | |
ONS | -0.273 |
EMS | -0.264 |
LIST | -0.263 |
Kind | -0.261 |
ALS | -0.255 |
Token | . |
Token ID | 13 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
ONS | +0.439 |
EMS | +0.425 |
LIST | +0.422 |
Kind | +0.420 |
Imper | +0.407 |
Neg logit contributions | |
banter | -0.385 |
puter | -0.380 |
egu | -0.376 |
dop | -0.361 |
ottesville | -0.361 |
Token | Via |
Token ID | 33356 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ONS | +0.554 |
EMS | +0.536 |
LIST | +0.530 |
Kind | +0.527 |
ALS | +0.511 |
Neg logit contributions | |
banter | -0.517 |
puter | -0.507 |
egu | -0.505 |
ousy | -0.485 |
dop | -0.483 |
Token | List |
Token ID | 8053 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
ONS | +0.646 |
EMS | +0.585 |
LIST | +0.566 |
Kind | +0.556 |
Imper | +0.506 |
Neg logit contributions | |
banter | -3.131 |
puter | -3.117 |
egu | -3.094 |
ottesville | -3.026 |
ousy | -3.020 |
Token | $ |
Token ID | 720 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ONS | +2.111 |
EMS | +2.023 |
LIST | +2.009 |
Kind | +1.999 |
Imper | +1.920 |
Neg logit contributions | |
banter | -3.192 |
puter | -3.177 |
egu | -3.149 |
ottesville | -3.054 |
ousy | -3.043 |
Token | w |
Token ID | 86 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
ONS | +1.319 |
EMS | +1.272 |
LIST | +1.263 |
Kind | +1.257 |
Imper | +1.214 |
Neg logit contributions | |
banter | -1.486 |
puter | -1.475 |
egu | -1.460 |
ottesville | -1.411 |
ousy | -1.404 |
Token | path |
Token ID | 6978 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
puter | +0.814 |
banter | +0.810 |
egu | +0.803 |
ottesville | +0.780 |
ousy | +0.778 |
Neg logit contributions | |
ONS | -0.449 |
EMS | -0.425 |
LIST | -0.417 |
Kind | -0.409 |
Imper | -0.401 |
Token | $ |
Token ID | 720 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ONS | +0.531 |
EMS | +0.513 |
LIST | +0.506 |
Kind | +0.502 |
ALS | +0.491 |
Neg logit contributions | |
banter | -0.439 |
puter | -0.437 |
egu | -0.426 |
ottesville | -0.411 |
ousy | -0.410 |
Token | image |
Token ID | 9060 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ONS | +1.225 |
EMS | +1.183 |
LIST | +1.176 |
Kind | +1.171 |
Imper | +1.130 |
Neg logit contributions | |
banter | -1.317 |
puter | -1.307 |
egu | -1.293 |
ottesville | -1.249 |
ousy | -1.243 |
Token | = |
Token ID | 796 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ONS | +2.366 |
EMS | +2.285 |
Kind | +2.281 |
LIST | +2.277 |
Imper | +2.175 |
Neg logit contributions | |
banter | -2.973 |
puter | -2.935 |
egu | -2.918 |
ottesville | -2.820 |
ousy | -2.803 |
Token | [ |
Token ID | 685 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ONS | +0.081 |
EMS | +0.078 |
LIST | +0.077 |
Kind | +0.076 |
ALS | +0.074 |
Neg logit contributions | |
banter | -0.092 |
puter | -0.091 |
egu | -0.090 |
dop | -0.087 |
ottesville | -0.087 |
Token | System |
Token ID | 11964 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ONS | +1.171 |
EMS | +1.124 |
LIST | +1.116 |
Kind | +1.109 |
Imper | +1.068 |
Neg logit contributions | |
banter | -1.610 |
puter | -1.600 |
egu | -1.585 |
ottesville | -1.536 |
ousy | -1.530 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ONS | +1.850 |
EMS | +1.786 |
LIST | +1.776 |
Kind | +1.758 |
Imper | +1.714 |
Neg logit contributions | |
banter | -1.628 |
puter | -1.620 |
egu | -1.597 |
ottesville | -1.534 |
ousy | -1.528 |
Token | Draw |
Token ID | 25302 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
ONS | +0.798 |
EMS | +0.762 |
LIST | +0.754 |
Kind | +0.747 |
Imper | +0.721 |
Neg logit contributions | |
banter | -1.258 |
puter | -1.254 |
egu | -1.243 |
ottesville | -1.204 |
ousy | -1.201 |
Token | the |
Token ID | 262 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
banter | +0.133 |
puter | +0.131 |
egu | +0.130 |
dop | +0.125 |
ottesville | +0.123 |
Neg logit contributions | |
ONS | -0.147 |
EMS | -0.143 |
LIST | -0.142 |
Kind | -0.140 |
ALS | -0.137 |
Token | closest |
Token ID | 11706 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
banter | +0.056 |
puter | +0.055 |
egu | +0.054 |
dop | +0.052 |
ottesville | +0.051 |
Neg logit contributions | |
ONS | -0.074 |
EMS | -0.072 |
LIST | -0.072 |
Kind | -0.071 |
ALS | -0.069 |
Token | thing |
Token ID | 1517 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
banter | +0.129 |
puter | +0.128 |
egu | +0.127 |
dop | +0.123 |
ottesville | +0.122 |
Neg logit contributions | |
ONS | -0.096 |
EMS | -0.092 |
LIST | -0.091 |
Kind | -0.091 |
ALS | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
banter | +1.711 |
puter | +1.701 |
egu | +1.647 |
dop | +1.598 |
ousy | +1.576 |
Neg logit contributions | |
ONS | -2.244 |
EMS | -2.162 |
LIST | -2.152 |
Kind | -2.148 |
Imper | -2.095 |
Token | Not |
Token ID | 1892 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ONS | +0.078 |
EMS | +0.075 |
LIST | +0.075 |
Kind | +0.074 |
ALS | +0.072 |
Neg logit contributions | |
banter | -0.070 |
puter | -0.069 |
egu | -0.069 |
ousy | -0.066 |
ottesville | -0.066 |
Token | only |
Token ID | 691 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
banter | +0.662 |
puter | +0.656 |
egu | +0.646 |
dop | +0.618 |
ousy | +0.614 |
Neg logit contributions | |
ONS | -0.881 |
EMS | -0.854 |
LIST | -0.848 |
Kind | -0.843 |
Imper | -0.821 |
Token | is |
Token ID | 318 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ONS | +2.598 |
EMS | +2.506 |
LIST | +2.504 |
Kind | +2.470 |
Imper | +2.427 |
Neg logit contributions | |
puter | -2.572 |
banter | -2.542 |
egu | -2.522 |
ottesville | -2.456 |
ousy | -2.432 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ONS | +0.889 |
EMS | +0.867 |
LIST | +0.862 |
Kind | +0.856 |
Imper | +0.837 |
Neg logit contributions | |
puter | -0.667 |
banter | -0.666 |
egu | -0.654 |
ottesville | -0.633 |
ousy | -0.624 |
Token | dummy |
Token ID | 31548 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
ONS | +0.140 |
EMS | +0.136 |
LIST | +0.136 |
Kind | +0.135 |
Imper | +0.132 |
Neg logit contributions | |
banter | -0.081 |
puter | -0.081 |
egu | -0.080 |
ottesville | -0.076 |
ousy | -0.075 |
Token | programmed |
Token ID | 27402 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
banter | +0.535 |
puter | +0.528 |
egu | +0.520 |
dop | +0.498 |
ottesville | +0.496 |
Neg logit contributions | |
ONS | -0.719 |
EMS | -0.697 |
LIST | -0.692 |
Kind | -0.688 |
ALS | -0.669 |
Token | to |
Token ID | 284 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
banter | +1.347 |
puter | +1.336 |
egu | +1.320 |
ottesville | +1.264 |
dop | +1.262 |
Neg logit contributions | |
ONS | -1.441 |
EMS | -1.395 |
LIST | -1.382 |
Kind | -1.375 |
Imper | -1.333 |