Token |
|
Token ID | 198 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
advoc | +0.586 |
mathemat | +0.568 |
horizont | +0.531 |
rul | +0.512 |
tyr | +0.505 |
Neg logit contributions | |
| -0.133 |
- | -0.118 |
on | -0.115 |
in | -0.104 |
, | -0.098 |
Token | https |
Token ID | 5450 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
advoc | +1.460 |
mathemat | +1.418 |
horizont | +1.270 |
tyr | +1.240 |
rul | +1.234 |
Neg logit contributions | |
| -0.522 |
on | -0.519 |
in | -0.492 |
- | -0.487 |
, | -0.469 |
Token | :// |
Token ID | 1378 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
advoc | +1.747 |
mathemat | +1.672 |
horizont | +1.524 |
rul | +1.479 |
tyr | +1.432 |
Neg logit contributions | |
| -0.761 |
on | -0.707 |
- | -0.697 |
in | -0.667 |
, | -0.641 |
Token | www |
Token ID | 2503 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
| +0.060 |
- | +0.056 |
on | +0.056 |
in | +0.053 |
, | +0.052 |
Neg logit contributions | |
advoc | -0.158 |
mathemat | -0.153 |
horizont | -0.137 |
tyr | -0.136 |
nodd | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
advoc | +3.730 |
mathemat | +3.642 |
horizont | +3.435 |
rul | +3.319 |
tyr | +3.261 |
Neg logit contributions | |
| -0.344 |
on | -0.234 |
- | -0.224 |
in | -0.163 |
Mar | -0.122 |
Token | eff |
Token ID | 14822 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
advoc | +0.204 |
mathemat | +0.197 |
horizont | +0.177 |
tyr | +0.176 |
nodd | +0.174 |
Neg logit contributions | |
| -0.087 |
- | -0.083 |
on | -0.082 |
in | -0.078 |
, | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
advoc | +7.376 |
mathemat | +7.192 |
horizont | +6.757 |
rul | +6.566 |
tyr | +6.473 |
Neg logit contributions | |
| -0.625 |
- | -0.426 |
on | -0.402 |
in | -0.282 |
, | -0.228 |
Token | org |
Token ID | 2398 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
advoc | +2.426 |
mathemat | +2.309 |
horizont | +2.121 |
rul | +2.086 |
nodd | +2.012 |
Neg logit contributions | |
| -0.980 |
- | -0.932 |
on | -0.912 |
in | -0.863 |
, | -0.848 |
Token | / |
Token ID | 14 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
advoc | +0.471 |
mathemat | +0.457 |
horizont | +0.426 |
rul | +0.412 |
tyr | +0.408 |
Neg logit contributions | |
| -0.085 |
- | -0.071 |
on | -0.068 |
in | -0.062 |
, | -0.058 |
Token | d |
Token ID | 67 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
advoc | +0.969 |
mathemat | +0.926 |
horizont | +0.844 |
rul | +0.832 |
tyr | +0.827 |
Neg logit contributions | |
| -0.315 |
- | -0.296 |
on | -0.288 |
in | -0.272 |
, | -0.271 |
Token | ee |
Token ID | 1453 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
advoc | +1.190 |
mathemat | +1.164 |
horizont | +1.061 |
tyr | +1.045 |
nodd | +1.043 |
Neg logit contributions | |
| -0.272 |
on | -0.241 |
- | -0.236 |
in | -0.219 |
, | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
| +0.038 |
- | +0.030 |
on | +0.021 |
Mar | +0.013 |
in | +0.011 |
Neg logit contributions | |
advoc | -0.517 |
mathemat | -0.508 |
horizont | -0.465 |
tyr | -0.462 |
destro | -0.458 |
Token | � |
Token ID | 447 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
| +0.035 |
- | +0.034 |
on | +0.031 |
, | +0.029 |
in | +0.028 |
Neg logit contributions | |
advoc | -0.161 |
mathemat | -0.157 |
horizont | -0.143 |
tyr | -0.141 |
destro | -0.141 |
Token | � |
Token ID | 251 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
| +0.363 |
- | +0.352 |
on | +0.344 |
, | +0.332 |
in | +0.332 |
Neg logit contributions | |
advoc | -0.541 |
mathemat | -0.538 |
tyr | -0.463 |
horizont | -0.462 |
nodd | -0.461 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
| +0.139 |
- | +0.128 |
on | +0.122 |
in | +0.111 |
, | +0.108 |
Neg logit contributions | |
advoc | -0.651 |
mathemat | -0.636 |
horizont | -0.581 |
tyr | -0.575 |
destro | -0.570 |
Token | WH |
Token ID | 12418 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
| +0.173 |
on | +0.166 |
- | +0.162 |
in | +0.156 |
, | +0.152 |
Neg logit contributions | |
advoc | -0.474 |
mathemat | -0.466 |
horizont | -0.415 |
tyr | -0.407 |
nodd | -0.404 |
Token | EN |
Token ID | 1677 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
advoc | +2.235 |
mathemat | +2.222 |
tyr | +1.944 |
nodd | +1.943 |
horizont | +1.940 |
Neg logit contributions | |
| -0.705 |
- | -0.641 |
on | -0.634 |
in | -0.592 |
, | -0.575 |
Token | Catherine |
Token ID | 22578 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
advoc | +6.612 |
mathemat | +6.581 |
tyr | +5.906 |
nodd | +5.886 |
horizont | +5.871 |
Neg logit contributions | |
| -1.360 |
- | -1.202 |
on | -1.106 |
— | -0.993 |
in | -0.979 |
Token | Mull |
Token ID | 19574 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
advoc | +0.583 |
mathemat | +0.570 |
horizont | +0.510 |
tyr | +0.509 |
nodd | +0.509 |
Neg logit contributions | |
| -0.176 |
- | -0.159 |
on | -0.154 |
in | -0.142 |
— | -0.140 |
Token | igan |
Token ID | 5516 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
| +0.127 |
- | +0.114 |
on | +0.108 |
— | +0.097 |
in | +0.097 |
Neg logit contributions | |
advoc | -0.583 |
mathemat | -0.570 |
tyr | -0.517 |
horizont | -0.517 |
destro | -0.515 |
Token | , |
Token ID | 11 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
| +0.290 |
- | +0.255 |
on | +0.244 |
in | +0.220 |
. | +0.219 |
Neg logit contributions | |
advoc | -1.215 |
mathemat | -1.202 |
tyr | -1.076 |
horizont | -1.070 |
destro | -1.069 |
Token | a |
Token ID | 257 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
| +0.116 |
- | +0.103 |
on | +0.086 |
, | +0.083 |
. | +0.082 |
Neg logit contributions | |
advoc | -0.654 |
mathemat | -0.643 |
tyr | -0.586 |
horizont | -0.579 |
nodd | -0.577 |
Token |
|
Token ID | 198 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
| +0.301 |
- | +0.268 |
on | +0.263 |
in | +0.236 |
, | +0.225 |
Neg logit contributions | |
advoc | -1.391 |
mathemat | -1.350 |
horizont | -1.260 |
rul | -1.220 |
tyr | -1.197 |
Token | https |
Token ID | 5450 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
| +0.406 |
on | +0.385 |
- | +0.377 |
in | +0.363 |
, | +0.356 |
Neg logit contributions | |
advoc | -1.134 |
mathemat | -1.105 |
horizont | -0.993 |
rul | -0.975 |
tyr | -0.972 |
Token | :// |
Token ID | 1378 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
advoc | +0.699 |
mathemat | +0.676 |
horizont | +0.611 |
rul | +0.600 |
tyr | +0.585 |
Neg logit contributions | |
| -0.282 |
- | -0.264 |
on | -0.261 |
in | -0.246 |
, | -0.242 |
Token | www |
Token ID | 2503 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
| +0.201 |
- | +0.188 |
on | +0.185 |
in | +0.176 |
, | +0.174 |
Neg logit contributions | |
advoc | -0.552 |
mathemat | -0.537 |
horizont | -0.486 |
rul | -0.479 |
tyr | -0.478 |
Token | . |
Token ID | 13 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
advoc | +3.063 |
mathemat | +2.991 |
horizont | +2.826 |
rul | +2.741 |
tyr | +2.673 |
Neg logit contributions | |
| -0.285 |
on | -0.213 |
- | -0.205 |
in | -0.154 |
Mar | -0.131 |
Token | eff |
Token ID | 14822 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
advoc | +0.982 |
mathemat | +0.940 |
horizont | +0.858 |
tyr | +0.845 |
rul | +0.836 |
Neg logit contributions | |
| -0.447 |
on | -0.426 |
- | -0.425 |
in | -0.401 |
, | -0.396 |
Token | . |
Token ID | 13 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
advoc | +7.012 |
mathemat | +6.829 |
horizont | +6.440 |
rul | +6.255 |
tyr | +6.201 |
Neg logit contributions | |
| -0.580 |
- | -0.398 |
on | -0.393 |
in | -0.289 |
Mar | -0.280 |
Token | org |
Token ID | 2398 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
advoc | +1.528 |
mathemat | +1.454 |
horizont | +1.353 |
rul | +1.312 |
tyr | +1.295 |
Neg logit contributions | |
| -0.608 |
- | -0.601 |
on | -0.577 |
in | -0.555 |
, | -0.541 |
Token | / |
Token ID | 14 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
| +0.089 |
- | +0.078 |
on | +0.073 |
in | +0.066 |
, | +0.062 |
Neg logit contributions | |
advoc | -0.550 |
mathemat | -0.537 |
horizont | -0.497 |
rul | -0.484 |
tyr | -0.482 |
Token | document |
Token ID | 22897 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
| +0.408 |
- | +0.386 |
on | +0.372 |
in | +0.355 |
, | +0.350 |
Neg logit contributions | |
advoc | -1.213 |
mathemat | -1.152 |
horizont | -1.054 |
rul | -1.043 |
tyr | -1.038 |
Token | / |
Token ID | 14 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
| +0.075 |
on | +0.066 |
in | +0.062 |
- | +0.061 |
Mar | +0.058 |
Neg logit contributions | |
advoc | -0.427 |
mathemat | -0.415 |
horizont | -0.381 |
tyr | -0.376 |
rul | -0.375 |
Token |
|
Token ID | 198 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
| +0.029 |
- | +0.026 |
on | +0.026 |
in | +0.023 |
, | +0.022 |
Neg logit contributions | |
advoc | -0.128 |
mathemat | -0.124 |
horizont | -0.116 |
rul | -0.112 |
tyr | -0.110 |
Token | https |
Token ID | 5450 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
| +0.170 |
on | +0.166 |
- | +0.158 |
in | +0.158 |
, | +0.152 |
Neg logit contributions | |
advoc | -0.425 |
mathemat | -0.416 |
horizont | -0.367 |
tyr | -0.362 |
destro | -0.359 |
Token | :// |
Token ID | 1378 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
advoc | +0.586 |
mathemat | +0.565 |
horizont | +0.512 |
rul | +0.499 |
tyr | +0.484 |
Neg logit contributions | |
| -0.247 |
on | -0.229 |
- | -0.227 |
in | -0.216 |
, | -0.209 |
Token | www |
Token ID | 2503 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
| +0.331 |
- | +0.309 |
on | +0.307 |
in | +0.291 |
, | +0.287 |
Neg logit contributions | |
advoc | -0.901 |
mathemat | -0.878 |
horizont | -0.786 |
tyr | -0.778 |
nodd | -0.775 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
advoc | +3.119 |
mathemat | +3.055 |
horizont | +2.872 |
rul | +2.777 |
tyr | +2.727 |
Neg logit contributions | |
| -0.282 |
on | -0.197 |
- | -0.192 |
in | -0.140 |
Mar | -0.109 |
Token | eff |
Token ID | 14822 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
advoc | +0.474 |
mathemat | +0.457 |
horizont | +0.411 |
tyr | +0.405 |
nodd | +0.403 |
Neg logit contributions | |
| -0.204 |
on | -0.193 |
- | -0.193 |
in | -0.182 |
, | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
advoc | +7.027 |
mathemat | +6.876 |
horizont | +6.411 |
rul | +6.257 |
tyr | +6.204 |
Neg logit contributions | |
| -0.553 |
- | -0.376 |
on | -0.357 |
in | -0.246 |
, | -0.208 |
Token | org |
Token ID | 2398 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
advoc | +2.426 |
mathemat | +2.321 |
horizont | +2.118 |
rul | +2.091 |
nodd | +2.020 |
Neg logit contributions | |
| -0.973 |
- | -0.925 |
on | -0.903 |
in | -0.855 |
, | -0.843 |
Token | / |
Token ID | 14 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
| +0.025 |
- | +0.021 |
on | +0.020 |
in | +0.018 |
, | +0.017 |
Neg logit contributions | |
advoc | -0.145 |
mathemat | -0.142 |
horizont | -0.131 |
rul | -0.128 |
tyr | -0.127 |
Token | d |
Token ID | 67 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
| +0.206 |
- | +0.193 |
on | +0.187 |
in | +0.178 |
, | +0.177 |
Neg logit contributions | |
advoc | -0.555 |
mathemat | -0.531 |
horizont | -0.480 |
tyr | -0.471 |
rul | -0.471 |
Token | ee |
Token ID | 1453 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
advoc | +1.191 |
mathemat | +1.162 |
horizont | +1.051 |
tyr | +1.030 |
rul | +1.025 |
Neg logit contributions | |
| -0.383 |
on | -0.341 |
- | -0.334 |
in | -0.323 |
, | -0.312 |
Token | wounded |
Token ID | 10657 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
advoc | +0.563 |
mathemat | +0.551 |
tyr | +0.493 |
horizont | +0.492 |
destro | +0.488 |
Neg logit contributions | |
| -0.253 |
- | -0.231 |
on | -0.209 |
: | -0.208 |
— | -0.208 |
Token | .] |
Token ID | 8183 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
mathemat | +1.201 |
advoc | +1.200 |
horizont | +1.094 |
tyr | +1.080 |
nodd | +1.080 |
Neg logit contributions | |
| -0.191 |
- | -0.157 |
on | -0.121 |
Mar | -0.110 |
Ad | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
advoc | +2.123 |
mathemat | +2.099 |
horizont | +1.908 |
tyr | +1.897 |
destro | +1.863 |
Neg logit contributions | |
| -0.481 |
- | -0.429 |
on | -0.408 |
in | -0.371 |
, | -0.366 |
Token |
|
Token ID | 198 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
advoc | +0.039 |
mathemat | +0.038 |
horizont | +0.036 |
rul | +0.034 |
tyr | +0.034 |
Neg logit contributions | |
| -0.009 |
- | -0.008 |
on | -0.008 |
in | -0.007 |
, | -0.007 |
Token | [ |
Token ID | 58 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
advoc | +0.186 |
mathemat | +0.183 |
horizont | +0.165 |
tyr | +0.159 |
nodd | +0.157 |
Neg logit contributions | |
| -0.072 |
on | -0.070 |
in | -0.067 |
- | -0.067 |
, | -0.064 |
Token | UPDATE |
Token ID | 16977 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
advoc | +0.048 |
mathemat | +0.048 |
horizont | +0.042 |
tyr | +0.042 |
destro | +0.041 |
Neg logit contributions | |
| -0.024 |
- | -0.023 |
on | -0.023 |
in | -0.022 |
, | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
advoc | +6.975 |
mathemat | +6.958 |
horizont | +6.388 |
tyr | +6.282 |
nodd | +6.275 |
Neg logit contributions | |
| -0.644 |
- | -0.391 |
on | -0.301 |
in | -0.238 |
. | -0.192 |
Token | 8 |
Token ID | 807 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
advoc | +2.270 |
mathemat | +2.229 |
horizont | +2.046 |
tyr | +2.011 |
rul | +1.993 |
Neg logit contributions | |
| -0.435 |
- | -0.362 |
on | -0.316 |
, | -0.292 |
— | -0.284 |
Token | : |
Token ID | 25 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
advoc | +0.598 |
mathemat | +0.595 |
horizont | +0.543 |
tyr | +0.542 |
nodd | +0.541 |
Neg logit contributions | |
| -0.048 |
- | -0.031 |
on | -0.030 |
in | -0.020 |
, | -0.018 |
Token | 03 |
Token ID | 3070 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
advoc | +1.255 |
mathemat | +1.217 |
horizont | +1.122 |
rul | +1.086 |
tyr | +1.077 |
Neg logit contributions | |
| -0.375 |
on | -0.334 |
- | -0.333 |
in | -0.305 |
, | -0.294 |
Token | p |
Token ID | 279 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
advoc | +1.750 |
mathemat | +1.735 |
horizont | +1.583 |
tyr | +1.570 |
nodd | +1.568 |
Neg logit contributions | |
| -0.285 |
- | -0.232 |
on | -0.219 |
in | -0.192 |
, | -0.183 |
Token | html |
Token ID | 6494 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
mathemat | +0.796 |
advoc | +0.791 |
horizont | +0.695 |
nodd | +0.689 |
rul | +0.676 |
Neg logit contributions | |
| -0.471 |
- | -0.437 |
on | -0.435 |
, | -0.413 |
in | -0.412 |
Token | https |
Token ID | 3740 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
advoc | +1.948 |
mathemat | +1.925 |
nodd | +1.731 |
horizont | +1.731 |
tyr | +1.719 |
Neg logit contributions | |
| -0.597 |
- | -0.511 |
on | -0.495 |
in | -0.463 |
: | -0.463 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
| +0.268 |
on | +0.242 |
- | +0.239 |
in | +0.227 |
, | +0.221 |
Neg logit contributions | |
advoc | -0.620 |
mathemat | -0.602 |
horizont | -0.551 |
rul | -0.529 |
tyr | -0.519 |
Token | www |
Token ID | 2503 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
advoc | +0.185 |
mathemat | +0.181 |
horizont | +0.165 |
destro | +0.158 |
tyr | +0.157 |
Neg logit contributions | |
| -0.086 |
on | -0.079 |
- | -0.079 |
in | -0.075 |
Mar | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
advoc | +4.666 |
mathemat | +4.528 |
horizont | +4.316 |
rul | +4.153 |
tyr | +4.057 |
Neg logit contributions | |
| -0.488 |
on | -0.342 |
- | -0.317 |
in | -0.247 |
Mar | -0.210 |
Token | bel |
Token ID | 6667 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
advoc | +1.532 |
mathemat | +1.509 |
tyr | +1.344 |
horizont | +1.340 |
nodd | +1.308 |
Neg logit contributions | |
| -0.889 |
on | -0.859 |
- | -0.838 |
in | -0.818 |
: | -0.800 |
Token | fast |
Token ID | 7217 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
advoc | +4.853 |
mathemat | +4.763 |
horizont | +4.336 |
rul | +4.193 |
tyr | +4.145 |
Neg logit contributions | |
| -2.165 |
on | -1.993 |
- | -1.978 |
in | -1.887 |
, | -1.857 |
Token | te |
Token ID | 660 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
advoc | +2.541 |
mathemat | +2.504 |
horizont | +2.317 |
tyr | +2.222 |
rul | +2.216 |
Neg logit contributions | |
| -0.712 |
on | -0.629 |
- | -0.624 |
in | -0.587 |
Mar | -0.572 |
Token | legraph |
Token ID | 16606 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
advoc | +0.544 |
mathemat | +0.537 |
horizont | +0.482 |
rul | +0.467 |
tyr | +0.464 |
Neg logit contributions | |
| -0.283 |
- | -0.269 |
on | -0.264 |
in | -0.250 |
, | -0.249 |
Token | . |
Token ID | 13 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
| +0.067 |
on | +0.046 |
- | +0.043 |
in | +0.033 |
, | +0.025 |
Neg logit contributions | |
advoc | -0.699 |
mathemat | -0.685 |
horizont | -0.647 |
rul | -0.621 |
tyr | -0.617 |
Token | co |
Token ID | 1073 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
| +0.339 |
- | +0.310 |
on | +0.305 |
in | +0.279 |
, | +0.273 |
Neg logit contributions | |
advoc | -1.246 |
mathemat | -1.210 |
horizont | -1.109 |
rul | -1.084 |
tyr | -1.073 |
Token | us |
Token ID | 514 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
| +0.193 |
- | +0.173 |
on | +0.162 |
— | +0.152 |
, | +0.151 |
Neg logit contributions | |
advoc | -0.650 |
mathemat | -0.650 |
tyr | -0.580 |
nodd | -0.579 |
horizont | -0.576 |
Token | at |
Token ID | 379 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
| +0.121 |
- | +0.097 |
on | +0.069 |
— | +0.062 |
m | +0.061 |
Neg logit contributions | |
advoc | -0.902 |
mathemat | -0.888 |
horizont | -0.812 |
nodd | -0.805 |
tyr | -0.805 |
Token | yog |
Token ID | 27423 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
advoc | +1.408 |
mathemat | +1.394 |
horizont | +1.258 |
nodd | +1.254 |
tyr | +1.254 |
Neg logit contributions | |
| -0.322 |
- | -0.276 |
on | -0.259 |
in | -0.235 |
, | -0.234 |
Token | ventures |
Token ID | 10065 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
| +0.352 |
- | +0.335 |
on | +0.334 |
in | +0.325 |
, | +0.324 |
Neg logit contributions | |
advoc | -0.323 |
mathemat | -0.315 |
horizont | -0.267 |
tyr | -0.258 |
destro | -0.258 |
Token | @ |
Token ID | 31 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
| +0.287 |
- | +0.246 |
on | +0.242 |
in | +0.227 |
, | +0.225 |
Neg logit contributions | |
advoc | -0.967 |
mathemat | -0.944 |
horizont | -0.852 |
tyr | -0.849 |
nodd | -0.839 |
Token | y |
Token ID | 88 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
| +0.044 |
- | +0.040 |
on | +0.040 |
in | +0.038 |
, | +0.037 |
Neg logit contributions | |
advoc | -0.130 |
mathemat | -0.129 |
horizont | -0.115 |
tyr | -0.115 |
nodd | -0.114 |
Token | og |
Token ID | 519 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
advoc | +5.392 |
mathemat | +5.359 |
horizont | +4.842 |
rul | +4.801 |
nodd | +4.780 |
Neg logit contributions | |
| -1.637 |
on | -1.476 |
- | -1.434 |
in | -1.382 |
Mar | -1.335 |
Token | sc |
Token ID | 1416 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
advoc | +2.044 |
mathemat | +1.997 |
horizont | +1.744 |
tyr | +1.709 |
rul | +1.673 |
Neg logit contributions | |
| -1.692 |
on | -1.592 |
- | -1.582 |
in | -1.529 |
— | -1.518 |
Token | ast |
Token ID | 459 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
advoc | +1.188 |
mathemat | +1.177 |
horizont | +1.061 |
tyr | +1.056 |
rul | +1.052 |
Neg logit contributions | |
| -0.416 |
- | -0.371 |
on | -0.365 |
in | -0.346 |
— | -0.341 |
Token | . |
Token ID | 13 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
advoc | +1.943 |
mathemat | +1.923 |
horizont | +1.765 |
tyr | +1.762 |
nodd | +1.755 |
Neg logit contributions | |
| -0.228 |
- | -0.173 |
on | -0.167 |
in | -0.134 |
— | -0.132 |
Token | com |
Token ID | 785 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
advoc | +1.835 |
mathemat | +1.813 |
horizont | +1.619 |
tyr | +1.613 |
destro | +1.598 |
Neg logit contributions | |
| -0.641 |
- | -0.597 |
on | -0.579 |
, | -0.545 |
in | -0.540 |
Token | 132 |
Token ID | 21761 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
advoc | +1.230 |
mathemat | +1.220 |
horizont | +1.105 |
tyr | +1.098 |
nodd | +1.095 |
Neg logit contributions | |
| -0.227 |
- | -0.184 |
on | -0.161 |
— | -0.144 |
. | -0.142 |
Token | .] |
Token ID | 8183 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
| +0.103 |
- | +0.076 |
on | +0.065 |
in | +0.050 |
ad | +0.049 |
Neg logit contributions | |
advoc | -0.833 |
mathemat | -0.823 |
horizont | -0.756 |
tyr | -0.746 |
nodd | -0.744 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
advoc | +0.476 |
mathemat | +0.473 |
horizont | +0.427 |
tyr | +0.427 |
nodd | +0.423 |
Neg logit contributions | |
| -0.096 |
- | -0.086 |
on | -0.081 |
, | -0.074 |
in | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
| +0.074 |
- | +0.064 |
on | +0.063 |
in | +0.057 |
, | +0.054 |
Neg logit contributions | |
advoc | -0.316 |
mathemat | -0.306 |
horizont | -0.288 |
rul | -0.275 |
tyr | -0.272 |
Token | [ |
Token ID | 58 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
| +0.048 |
on | +0.047 |
in | +0.044 |
- | +0.044 |
, | +0.042 |
Neg logit contributions | |
advoc | -0.128 |
mathemat | -0.126 |
horizont | -0.113 |
tyr | -0.110 |
nodd | -0.108 |
Token | UPDATE |
Token ID | 16977 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
| +0.316 |
- | +0.300 |
on | +0.298 |
in | +0.287 |
, | +0.286 |
Neg logit contributions | |
advoc | -0.487 |
mathemat | -0.484 |
horizont | -0.418 |
tyr | -0.414 |
nodd | -0.411 |
Token | , |
Token ID | 11 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
advoc | +6.782 |
mathemat | +6.772 |
horizont | +6.194 |
tyr | +6.143 |
nodd | +6.125 |
Neg logit contributions | |
| -0.415 |
- | -0.257 |
on | -0.182 |
in | -0.100 |
. | -0.056 |
Token | 8 |
Token ID | 807 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
advoc | +2.201 |
mathemat | +2.172 |
horizont | +1.980 |
tyr | +1.948 |
rul | +1.933 |
Neg logit contributions | |
| -0.406 |
- | -0.339 |
on | -0.299 |
, | -0.275 |
— | -0.268 |
Token | : |
Token ID | 25 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
advoc | +1.115 |
mathemat | +1.108 |
horizont | +1.013 |
tyr | +1.008 |
nodd | +1.005 |
Neg logit contributions | |
| -0.116 |
on | -0.077 |
- | -0.075 |
in | -0.059 |
— | -0.054 |
Token | 59 |
Token ID | 3270 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
advoc | +0.459 |
mathemat | +0.446 |
horizont | +0.410 |
rul | +0.399 |
tyr | +0.394 |
Neg logit contributions | |
| -0.142 |
- | -0.127 |
on | -0.126 |
in | -0.116 |
, | -0.113 |
Token | p |
Token ID | 279 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
advoc | +0.932 |
mathemat | +0.929 |
horizont | +0.843 |
tyr | +0.840 |
nodd | +0.837 |
Neg logit contributions | |
| -0.140 |
- | -0.118 |
on | -0.109 |
in | -0.094 |
, | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
| +0.068 |
- | +0.062 |
on | +0.059 |
in | +0.053 |
, | +0.052 |
Neg logit contributions | |
advoc | -0.322 |
mathemat | -0.315 |
tyr | -0.286 |
horizont | -0.284 |
nodd | -0.282 |
Token |
|
Token ID | 198 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
advoc | +1.040 |
mathemat | +1.011 |
horizont | +0.944 |
rul | +0.910 |
tyr | +0.898 |
Neg logit contributions | |
| -0.234 |
- | -0.209 |
on | -0.204 |
in | -0.183 |
, | -0.175 |
Token | [ |
Token ID | 58 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
advoc | +0.856 |
mathemat | +0.831 |
horizont | +0.744 |
tyr | +0.730 |
nodd | +0.725 |
Neg logit contributions | |
on | -0.307 |
| -0.307 |
- | -0.295 |
in | -0.288 |
, | -0.276 |
Token | H |
Token ID | 39 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
advoc | +1.055 |
mathemat | +1.044 |
horizont | +0.927 |
tyr | +0.926 |
destro | +0.922 |
Neg logit contributions | |
| -0.369 |
- | -0.348 |
on | -0.340 |
, | -0.321 |
in | -0.319 |
Token | / |
Token ID | 14 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
advoc | +1.264 |
mathemat | +1.248 |
horizont | +1.119 |
tyr | +1.109 |
nodd | +1.109 |
Neg logit contributions | |
| -0.287 |
on | -0.253 |
- | -0.246 |
in | -0.233 |
, | -0.225 |
Token | t |
Token ID | 83 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
advoc | +3.390 |
mathemat | +3.330 |
horizont | +3.006 |
tyr | +2.956 |
rul | +2.940 |
Neg logit contributions | |
| -0.811 |
- | -0.768 |
on | -0.738 |
in | -0.679 |
, | -0.663 |
Token | The |
Token ID | 383 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
advoc | +5.819 |
mathemat | +5.711 |
tyr | +5.191 |
horizont | +5.170 |
nodd | +5.096 |
Neg logit contributions | |
| -1.232 |
- | -1.068 |
on | -1.000 |
in | -0.912 |
. | -0.860 |
Token | Hill |
Token ID | 3327 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
advoc | +0.918 |
mathemat | +0.901 |
horizont | +0.812 |
tyr | +0.811 |
nodd | +0.795 |
Neg logit contributions | |
| -0.300 |
- | -0.278 |
on | -0.270 |
in | -0.254 |
, | -0.252 |
Token | ] |
Token ID | 60 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
advoc | +0.391 |
mathemat | +0.386 |
horizont | +0.350 |
tyr | +0.345 |
destro | +0.342 |
Neg logit contributions | |
| -0.101 |
- | -0.090 |
on | -0.084 |
in | -0.078 |
— | -0.076 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
| +0.070 |
- | +0.067 |
on | +0.061 |
, | +0.058 |
in | +0.057 |
Neg logit contributions | |
advoc | -0.320 |
mathemat | -0.317 |
tyr | -0.285 |
horizont | -0.285 |
nodd | -0.283 |
Token | L |
Token ID | 43 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
| +0.618 |
on | +0.590 |
- | +0.579 |
in | +0.557 |
, | +0.544 |
Neg logit contributions | |
advoc | -1.667 |
mathemat | -1.641 |
horizont | -1.460 |
tyr | -1.433 |
nodd | -1.424 |
Token | Box |
Token ID | 8315 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
advoc | +0.444 |
mathemat | +0.438 |
tyr | +0.400 |
nodd | +0.399 |
destro | +0.399 |
Neg logit contributions | |
| -0.087 |
- | -0.078 |
on | -0.070 |
— | -0.063 |
, | -0.062 |
Token | : |
Token ID | 1058 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
| +0.009 |
- | +0.009 |
on | +0.008 |
— | +0.007 |
in | +0.007 |
Neg logit contributions | |
advoc | -0.035 |
mathemat | -0.034 |
nodd | -0.031 |
destro | -0.031 |
horizont | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
advoc | +2.424 |
mathemat | +2.417 |
tyr | +2.178 |
horizont | +2.169 |
nodd | +2.162 |
Neg logit contributions | |
| -0.453 |
- | -0.406 |
on | -0.348 |
, | -0.329 |
— | -0.324 |
Token |
|
Token ID | 198 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
advoc | +0.977 |
mathemat | +0.948 |
horizont | +0.886 |
rul | +0.853 |
tyr | +0.842 |
Neg logit contributions | |
| -0.223 |
- | -0.195 |
on | -0.193 |
in | -0.173 |
, | -0.164 |
Token | pub |
Token ID | 12984 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
advoc | +1.157 |
mathemat | +1.134 |
horizont | +0.998 |
nodd | +0.984 |
tyr | +0.980 |
Neg logit contributions | |
| -0.468 |
on | -0.451 |
- | -0.435 |
in | -0.425 |
Mar | -0.412 |
Token | struct |
Token ID | 2878 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
advoc | +0.491 |
mathemat | +0.489 |
tyr | +0.432 |
destro | +0.431 |
nodd | +0.428 |
Neg logit contributions | |
| -0.207 |
- | -0.195 |
on | -0.186 |
— | -0.181 |
, | -0.177 |
Token | Own |
Token ID | 11744 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
advoc | +5.088 |
mathemat | +5.012 |
horizont | +4.510 |
nodd | +4.493 |
destro | +4.491 |
Neg logit contributions | |
| -1.641 |
- | -1.452 |
on | -1.353 |
— | -1.304 |
, | -1.273 |
Token | ed |
Token ID | 276 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
| +0.254 |
- | +0.224 |
on | +0.219 |
in | +0.196 |
, | +0.189 |
Neg logit contributions | |
advoc | -1.414 |
mathemat | -1.379 |
nodd | -1.259 |
horizont | -1.251 |
destro | -1.249 |
Token | < |
Token ID | 1279 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
| +0.704 |
- | +0.644 |
on | +0.632 |
in | +0.596 |
— | +0.591 |
Neg logit contributions | |
advoc | -1.967 |
mathemat | -1.919 |
nodd | -1.734 |
destro | -1.730 |
horizont | -1.722 |
Token | T |
Token ID | 309 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
advoc | +2.870 |
mathemat | +2.839 |
horizont | +2.569 |
tyr | +2.547 |
destro | +2.543 |
Neg logit contributions | |
| -0.587 |
- | -0.489 |
on | -0.473 |
in | -0.426 |
— | -0.419 |
Token | > |
Token ID | 1875 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
advoc | +0.416 |
mathemat | +0.407 |
tyr | +0.367 |
horizont | +0.367 |
destro | +0.365 |
Neg logit contributions | |
| -0.123 |
- | -0.108 |
on | -0.103 |
— | -0.099 |
in | -0.096 |
Token | boot |
Token ID | 18769 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
| +0.049 |
- | +0.046 |
on | +0.046 |
in | +0.044 |
, | +0.044 |
Neg logit contributions | |
advoc | -0.094 |
mathemat | -0.094 |
nodd | -0.082 |
horizont | -0.081 |
tyr | -0.081 |
Token | ' |
Token ID | 6 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
| +0.135 |
- | +0.104 |
on | +0.100 |
in | +0.083 |
, | +0.082 |
Neg logit contributions | |
advoc | -1.062 |
mathemat | -1.058 |
horizont | -0.960 |
tyr | -0.955 |
nodd | -0.954 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
| +0.573 |
- | +0.513 |
on | +0.478 |
— | +0.465 |
, | +0.454 |
Neg logit contributions | |
advoc | -1.555 |
mathemat | -1.520 |
horizont | -1.375 |
tyr | -1.372 |
rul | -1.363 |
Token | H |
Token ID | 367 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
| +0.025 |
- | +0.022 |
on | +0.021 |
— | +0.020 |
in | +0.019 |
Neg logit contributions | |
advoc | -0.069 |
mathemat | -0.068 |
horizont | -0.062 |
tyr | -0.061 |
rul | -0.061 |
Token | AV |
Token ID | 10116 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
advoc | +0.727 |
mathemat | +0.702 |
nodd | +0.632 |
tyr | +0.620 |
horizont | +0.619 |
Neg logit contributions | |
| -0.268 |
- | -0.240 |
on | -0.231 |
— | -0.217 |
in | -0.214 |
Token | ING |
Token ID | 2751 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
advoc | +1.449 |
mathemat | +1.410 |
destro | +1.263 |
horizont | +1.251 |
rul | +1.249 |
Neg logit contributions | |
| -0.430 |
- | -0.390 |
on | -0.388 |
in | -0.357 |
— | -0.352 |
Token | line |
Token ID | 1627 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
advoc | +5.563 |
mathemat | +5.447 |
tyr | +4.949 |
horizont | +4.943 |
nodd | +4.928 |
Neg logit contributions | |
| -1.243 |
- | -0.963 |
on | -0.933 |
— | -0.906 |
, | -0.829 |
Token | contains |
Token ID | 4909 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
| +0.523 |
- | +0.457 |
on | +0.433 |
— | +0.426 |
, | +0.403 |
Neg logit contributions | |
advoc | -1.528 |
mathemat | -1.511 |
horizont | -1.359 |
tyr | -1.350 |
destro | -1.349 |
Token | ' |
Token ID | 705 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
| +0.323 |
- | +0.277 |
on | +0.256 |
— | +0.232 |
, | +0.230 |
Neg logit contributions | |
advoc | -1.481 |
mathemat | -1.474 |
tyr | -1.332 |
nodd | -1.329 |
horizont | -1.326 |
Token | [' |
Token ID | 17816 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
advoc | +0.143 |
mathemat | +0.141 |
horizont | +0.125 |
tyr | +0.125 |
destro | +0.125 |
Neg logit contributions | |
| -0.044 |
on | -0.040 |
- | -0.039 |
in | -0.036 |
, | -0.036 |
Token | ) |
Token ID | 1267 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
| +0.233 |
- | +0.197 |
on | +0.185 |
— | +0.175 |
, | +0.169 |
Neg logit contributions | |
advoc | -0.832 |
mathemat | -0.826 |
horizont | -0.750 |
tyr | -0.741 |
destro | -0.739 |
Token | across |
Token ID | 1973 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
advoc | +1.149 |
mathemat | +1.140 |
horizont | +1.031 |
destro | +1.031 |
tyr | +1.030 |
Neg logit contributions | |
| -0.211 |
- | -0.178 |
on | -0.147 |
. | -0.132 |
: | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
advoc | +0.170 |
mathemat | +0.168 |
tyr | +0.153 |
horizont | +0.152 |
destro | +0.150 |
Neg logit contributions | |
| -0.030 |
- | -0.025 |
on | -0.023 |
— | -0.021 |
, | -0.021 |
Token | southwest |
Token ID | 26283 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
| +0.273 |
- | +0.249 |
on | +0.234 |
. | +0.224 |
, | +0.222 |
Neg logit contributions | |
advoc | -0.876 |
mathemat | -0.865 |
horizont | -0.779 |
tyr | -0.776 |
nodd | -0.765 |
Token | continue |
Token ID | 2555 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
| +0.040 |
- | +0.033 |
on | +0.030 |
— | +0.027 |
. | +0.027 |
Neg logit contributions | |
advoc | -0.184 |
mathemat | -0.182 |
horizont | -0.165 |
tyr | -0.163 |
nodd | -0.163 |
Token | to |
Token ID | 284 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
advoc | +2.538 |
mathemat | +2.479 |
horizont | +2.287 |
tyr | +2.272 |
nodd | +2.255 |
Neg logit contributions | |
| -0.276 |
- | -0.218 |
on | -0.152 |
— | -0.121 |
in | -0.118 |
Token | suggest |
Token ID | 1950 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
advoc | +0.513 |
mathemat | +0.507 |
tyr | +0.454 |
destro | +0.454 |
horizont | +0.450 |
Neg logit contributions | |
| -0.171 |
- | -0.157 |
on | -0.148 |
in | -0.139 |
. | -0.139 |
Token | that |
Token ID | 326 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
advoc | +5.875 |
mathemat | +5.759 |
horizont | +5.306 |
tyr | +5.291 |
nodd | +5.205 |
Neg logit contributions | |
| -0.831 |
- | -0.668 |
on | -0.547 |
en | -0.455 |
. | -0.451 |
Token | this |
Token ID | 428 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
advoc | +1.898 |
mathemat | +1.865 |
horizont | +1.703 |
tyr | +1.693 |
destro | +1.671 |
Neg logit contributions | |
| -0.372 |
- | -0.318 |
on | -0.279 |
. | -0.245 |
— | -0.242 |
Token | is |
Token ID | 318 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
advoc | +0.149 |
mathemat | +0.146 |
horizont | +0.132 |
tyr | +0.132 |
destro | +0.130 |
Neg logit contributions | |
| -0.042 |
- | -0.038 |
on | -0.035 |
, | -0.032 |
. | -0.032 |
Token | not |
Token ID | 407 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
advoc | +0.291 |
mathemat | +0.289 |
tyr | +0.262 |
nodd | +0.258 |
horizont | +0.258 |
Neg logit contributions | |
| -0.049 |
- | -0.042 |
on | -0.034 |
. | -0.031 |
: | -0.031 |
Token | merely |
Token ID | 6974 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
| +0.020 |
- | +0.016 |
on | +0.013 |
: | +0.012 |
, | +0.011 |
Neg logit contributions | |
advoc | -0.129 |
mathemat | -0.127 |
tyr | -0.116 |
horizont | -0.115 |
nodd | -0.114 |
Token | vested |
Token ID | 32789 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
advoc | +0.456 |
mathemat | +0.447 |
horizont | +0.401 |
tyr | +0.397 |
nodd | +0.395 |
Neg logit contributions | |
| -0.147 |
- | -0.137 |
on | -0.130 |
, | -0.122 |
: | -0.121 |
Token | interest |
Token ID | 1393 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
advoc | +0.031 |
mathemat | +0.030 |
horizont | +0.027 |
tyr | +0.027 |
destro | +0.026 |
Neg logit contributions | |
| -0.009 |
- | -0.009 |
on | -0.009 |
: | -0.008 |
. | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
mathemat | +1.259 |
advoc | +1.255 |
destro | +1.139 |
horizont | +1.133 |
nodd | +1.130 |
Neg logit contributions | |
| -0.096 |
- | -0.080 |
on | -0.050 |
Mar | -0.035 |
: | -0.032 |
Token | doing |
Token ID | 1804 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
| +0.070 |
- | +0.066 |
on | +0.059 |
in | +0.054 |
, | +0.054 |
Neg logit contributions | |
advoc | -0.326 |
mathemat | -0.324 |
destro | -0.291 |
tyr | -0.290 |
horizont | -0.288 |
Token | the |
Token ID | 262 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
| +0.164 |
- | +0.142 |
on | +0.122 |
: | +0.102 |
in | +0.101 |
Neg logit contributions | |
advoc | -1.160 |
mathemat | -1.153 |
horizont | -1.038 |
destro | -1.036 |
tyr | -1.033 |
Token | sort |
Token ID | 3297 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
| +0.026 |
- | +0.023 |
on | +0.022 |
, | +0.021 |
. | +0.020 |
Neg logit contributions | |
advoc | -0.090 |
mathemat | -0.089 |
horizont | -0.079 |
destro | -0.079 |
tyr | -0.079 |
Token | of |
Token ID | 286 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
advoc | +5.501 |
mathemat | +5.349 |
horizont | +4.910 |
rul | +4.864 |
destro | +4.804 |
Neg logit contributions | |
| -0.687 |
on | -0.564 |
- | -0.546 |
in | -0.455 |
: | -0.451 |
Token | N |
Token ID | 399 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
advoc | +1.910 |
mathemat | +1.899 |
horizont | +1.684 |
tyr | +1.676 |
nodd | +1.671 |
Neg logit contributions | |
| -0.564 |
- | -0.507 |
on | -0.478 |
in | -0.443 |
, | -0.442 |
Token | PH |
Token ID | 11909 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
| +0.018 |
on | +0.016 |
- | +0.016 |
in | +0.015 |
, | +0.015 |
Neg logit contributions | |
advoc | -0.061 |
mathemat | -0.060 |
tyr | -0.054 |
horizont | -0.054 |
nodd | -0.054 |
Token | version |
Token ID | 2196 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
| +0.089 |
- | +0.078 |
on | +0.076 |
, | +0.069 |
in | +0.069 |
Neg logit contributions | |
mathemat | -0.391 |
advoc | -0.389 |
tyr | -0.346 |
destro | -0.345 |
nodd | -0.345 |
Token | of |
Token ID | 286 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
advoc | +3.690 |
mathemat | +3.683 |
nodd | +3.299 |
destro | +3.298 |
horizont | +3.295 |
Neg logit contributions | |
| -0.422 |
- | -0.334 |
on | -0.284 |
: | -0.227 |
in | -0.214 |
Token | mar |
Token ID | 1667 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
advoc | +1.233 |
mathemat | +1.218 |
nodd | +1.089 |
horizont | +1.088 |
tyr | +1.088 |
Neg logit contributions | |
| -0.428 |
- | -0.387 |
on | -0.368 |
. | -0.351 |
— | -0.348 |
Token | ina |
Token ID | 1437 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
advoc | +1.276 |
mathemat | +1.264 |
tyr | +1.151 |
horizont | +1.126 |
nodd | +1.114 |
Neg logit contributions | |
| -0.484 |
- | -0.454 |
on | -0.452 |
— | -0.436 |
, | -0.429 |
Token | in |
Token ID | 287 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
advoc | +0.412 |
mathemat | +0.401 |
horizont | +0.373 |
nodd | +0.367 |
rul | +0.365 |
Neg logit contributions | |
| -0.057 |
- | -0.044 |
: | -0.033 |
en | -0.031 |
on | -0.031 |
Token | Ke |
Token ID | 3873 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
advoc | +1.033 |
mathemat | +1.023 |
horizont | +0.924 |
nodd | +0.919 |
tyr | +0.917 |
Neg logit contributions | |
| -0.274 |
- | -0.244 |
on | -0.223 |
. | -0.213 |
— | -0.213 |
Token | ans |
Token ID | 504 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
advoc | +1.958 |
mathemat | +1.921 |
horizont | +1.752 |
nodd | +1.701 |
tyr | +1.696 |
Neg logit contributions | |
| -0.529 |
- | -0.488 |
on | -0.480 |
in | -0.453 |
, | -0.439 |
Token | burg |
Token ID | 7423 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
advoc | +2.707 |
mathemat | +2.639 |
horizont | +2.330 |
destro | +2.293 |
tyr | +2.290 |
Neg logit contributions | |
| -1.393 |
- | -1.281 |
on | -1.241 |
: | -1.218 |
ad | -1.209 |
Token | , |
Token ID | 11 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
advoc | +5.601 |
mathemat | +5.477 |
horizont | +5.056 |
rul | +4.990 |
destro | +4.985 |
Neg logit contributions | |
| -0.780 |
- | -0.603 |
: | -0.447 |
on | -0.396 |
— | -0.391 |
Token | New |
Token ID | 968 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
advoc | +1.854 |
mathemat | +1.828 |
horizont | +1.665 |
nodd | +1.664 |
tyr | +1.659 |
Neg logit contributions | |
| -0.378 |
- | -0.340 |
: | -0.282 |
, | -0.278 |
. | -0.271 |
Token | Jersey |
Token ID | 8221 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
mathemat | +0.507 |
advoc | +0.506 |
nodd | +0.447 |
tyr | +0.445 |
horizont | +0.444 |
Neg logit contributions | |
| -0.237 |
- | -0.216 |
on | -0.215 |
in | -0.204 |
: | -0.201 |
Token | , |
Token ID | 11 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
| +0.190 |
- | +0.153 |
: | +0.095 |
on | +0.094 |
— | +0.084 |
Neg logit contributions | |
advoc | -1.668 |
mathemat | -1.652 |
horizont | -1.515 |
destro | -1.504 |
rul | -1.497 |
Token | following |
Token ID | 1708 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
| +0.125 |
- | +0.114 |
: | +0.090 |
, | +0.086 |
. | +0.084 |
Neg logit contributions | |
advoc | -0.709 |
mathemat | -0.698 |
horizont | -0.640 |
destro | -0.631 |
tyr | -0.630 |
Token | a |
Token ID | 64 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
advoc | +1.329 |
mathemat | +1.313 |
tyr | +1.194 |
destro | +1.191 |
horizont | +1.186 |
Neg logit contributions | |
| -0.216 |
- | -0.195 |
on | -0.188 |
, | -0.166 |
in | -0.162 |
Token | . |
Token ID | 764 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
| +0.009 |
- | +0.008 |
on | +0.007 |
in | +0.006 |
ad | +0.006 |
Neg logit contributions | |
mathemat | -0.046 |
advoc | -0.046 |
destro | -0.041 |
tyr | -0.041 |
nodd | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
advoc | +1.564 |
mathemat | +1.554 |
horizont | +1.405 |
destro | +1.390 |
rul | +1.387 |
Neg logit contributions | |
| -0.369 |
- | -0.334 |
on | -0.306 |
, | -0.281 |
— | -0.278 |
Token |
|
Token ID | 198 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
| +0.124 |
- | +0.108 |
on | +0.106 |
in | +0.095 |
, | +0.090 |
Neg logit contributions | |
advoc | -0.547 |
mathemat | -0.530 |
horizont | -0.497 |
rul | -0.477 |
tyr | -0.471 |
Token | pub |
Token ID | 12984 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
| +0.175 |
on | +0.168 |
- | +0.163 |
in | +0.157 |
, | +0.150 |
Neg logit contributions | |
advoc | -0.482 |
mathemat | -0.473 |
horizont | -0.425 |
nodd | -0.415 |
tyr | -0.414 |
Token | struct |
Token ID | 2878 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
advoc | +0.607 |
mathemat | +0.606 |
tyr | +0.537 |
destro | +0.537 |
nodd | +0.533 |
Neg logit contributions | |
| -0.253 |
- | -0.239 |
on | -0.230 |
— | -0.222 |
, | -0.218 |
Token | Shared |
Token ID | 39403 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
advoc | +4.686 |
mathemat | +4.621 |
destro | +4.170 |
horizont | +4.132 |
rul | +4.118 |
Neg logit contributions | |
| -1.718 |
- | -1.531 |
on | -1.447 |
— | -1.399 |
, | -1.363 |
Token | < |
Token ID | 1279 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
| +0.173 |
- | +0.159 |
on | +0.154 |
, | +0.145 |
in | +0.144 |
Neg logit contributions | |
advoc | -0.507 |
mathemat | -0.497 |
nodd | -0.447 |
destro | -0.446 |
horizont | -0.444 |
Token | ' |
Token ID | 705 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
advoc | +3.396 |
mathemat | +3.345 |
destro | +3.029 |
horizont | +3.021 |
tyr | +3.003 |
Neg logit contributions | |
| -0.658 |
- | -0.525 |
on | -0.481 |
— | -0.445 |
in | -0.427 |
Token | a |
Token ID | 64 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
advoc | +1.765 |
mathemat | +1.732 |
horizont | +1.577 |
rul | +1.571 |
tyr | +1.565 |
Neg logit contributions | |
| -0.277 |
- | -0.250 |
on | -0.222 |
— | -0.204 |
, | -0.198 |
Token | , |
Token ID | 837 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
advoc | +1.482 |
mathemat | +1.474 |
horizont | +1.341 |
tyr | +1.338 |
destro | +1.337 |
Neg logit contributions | |
| -0.134 |
- | -0.105 |
on | -0.091 |
in | -0.070 |
— | -0.063 |
Token | of |
Token ID | 286 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
advoc | +2.122 |
mathemat | +2.107 |
tyr | +1.912 |
destro | +1.897 |
nodd | +1.891 |
Neg logit contributions | |
| -0.301 |
- | -0.277 |
on | -0.207 |
: | -0.205 |
, | -0.204 |
Token | Mad |
Token ID | 4627 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
| +0.539 |
- | +0.510 |
on | +0.477 |
, | +0.448 |
in | +0.441 |
Neg logit contributions | |
advoc | -2.424 |
mathemat | -2.406 |
horizont | -2.167 |
tyr | -2.154 |
nodd | -2.151 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
advoc | +0.311 |
mathemat | +0.309 |
tyr | +0.276 |
nodd | +0.275 |
horizont | +0.275 |
Neg logit contributions | |
| -0.084 |
- | -0.076 |
on | -0.073 |
in | -0.068 |
, | -0.067 |
Token | : |
Token ID | 25 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
advoc | +3.979 |
mathemat | +3.958 |
horizont | +3.622 |
tyr | +3.621 |
destro | +3.575 |
Neg logit contributions | |
| -0.444 |
- | -0.301 |
on | -0.254 |
— | -0.188 |
in | -0.185 |
Token | Fury |
Token ID | 18427 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
| +1.073 |
- | +1.017 |
on | +0.979 |
, | +0.933 |
in | +0.932 |
Neg logit contributions | |
advoc | -1.630 |
mathemat | -1.610 |
tyr | -1.434 |
horizont | -1.433 |
destro | -1.389 |
Token | Road |
Token ID | 5567 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
advoc | +3.235 |
mathemat | +3.187 |
horizont | +2.931 |
tyr | +2.903 |
rul | +2.848 |
Neg logit contributions | |
| -0.915 |
- | -0.780 |
on | -0.699 |
in | -0.637 |
: | -0.627 |
Token | on |
Token ID | 319 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
advoc | +5.750 |
mathemat | +5.672 |
horizont | +5.245 |
tyr | +5.197 |
destro | +5.180 |
Neg logit contributions | |
| -0.650 |
- | -0.468 |
on | -0.350 |
in | -0.262 |
— | -0.249 |
Token | Blu |
Token ID | 12391 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
advoc | +0.140 |
mathemat | +0.139 |
horizont | +0.126 |
tyr | +0.124 |
destro | +0.123 |
Neg logit contributions | |
| -0.035 |
- | -0.030 |
on | -0.029 |
in | -0.026 |
— | -0.026 |
Token | - |
Token ID | 12 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
advoc | +2.360 |
mathemat | +2.334 |
horizont | +2.156 |
tyr | +2.130 |
destro | +2.126 |
Neg logit contributions | |
| -0.100 |
on | -0.054 |
in | -0.014 |
- | -0.008 |
, | -0.003 |
Token | ray |
Token ID | 2433 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
advoc | +1.336 |
mathemat | +1.322 |
horizont | +1.188 |
destro | +1.174 |
nodd | +1.162 |
Neg logit contributions | |
| -0.412 |
- | -0.385 |
on | -0.363 |
, | -0.343 |
— | -0.338 |
Token | , |
Token ID | 11 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
advoc | +0.797 |
mathemat | +0.785 |
horizont | +0.723 |
rul | +0.715 |
destro | +0.713 |
Neg logit contributions | |
| -0.113 |
- | -0.089 |
on | -0.068 |
— | -0.061 |
in | -0.058 |
Token | Who |
Token ID | 5338 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
| +0.208 |
- | +0.193 |
on | +0.184 |
in | +0.168 |
, | +0.168 |
Neg logit contributions | |
advoc | -0.858 |
mathemat | -0.843 |
horizont | -0.765 |
tyr | -0.759 |
rul | -0.758 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
| +0.178 |
- | +0.166 |
on | +0.154 |
: | +0.142 |
. | +0.142 |
Neg logit contributions | |
advoc | -0.702 |
mathemat | -0.691 |
rul | -0.625 |
tyr | -0.619 |
destro | -0.618 |
Token | what |
Token ID | 644 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
| +0.007 |
- | +0.006 |
on | +0.005 |
in | +0.004 |
— | +0.004 |
Neg logit contributions | |
advoc | -0.041 |
mathemat | -0.040 |
horizont | -0.036 |
tyr | -0.036 |
rul | -0.036 |
Token | is |
Token ID | 318 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
advoc | +0.377 |
mathemat | +0.366 |
tyr | +0.333 |
nodd | +0.332 |
horizont | +0.332 |
Neg logit contributions | |
| -0.078 |
- | -0.071 |
on | -0.066 |
in | -0.059 |
: | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
advoc | +0.893 |
mathemat | +0.865 |
tyr | +0.781 |
horizont | +0.776 |
rul | +0.771 |
Neg logit contributions | |
| -0.209 |
- | -0.186 |
on | -0.167 |
— | -0.155 |
: | -0.155 |
Token | isn |
Token ID | 2125 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
advoc | +0.900 |
mathemat | +0.886 |
tyr | +0.792 |
horizont | +0.788 |
destro | +0.787 |
Neg logit contributions | |
| -0.261 |
- | -0.239 |
on | -0.222 |
: | -0.206 |
. | -0.202 |
Token | � |
Token ID | 447 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
advoc | +3.692 |
mathemat | +3.554 |
horizont | +3.185 |
rul | +3.134 |
tyr | +3.012 |
Neg logit contributions | |
| -2.087 |
on | -2.023 |
- | -2.016 |
in | -1.915 |
Mar | -1.869 |
Token | � |
Token ID | 247 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
advoc | +1.119 |
mathemat | +1.071 |
rul | +0.935 |
tyr | +0.923 |
horizont | +0.923 |
Neg logit contributions | |
| -0.858 |
- | -0.838 |
on | -0.815 |
in | -0.787 |
, | -0.784 |
Token | t |
Token ID | 83 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
advoc | +0.947 |
mathemat | +0.923 |
destro | +0.839 |
rul | +0.838 |
tyr | +0.837 |
Neg logit contributions | |
| -0.182 |
- | -0.180 |
on | -0.170 |
in | -0.155 |
, | -0.148 |
Token | hate |
Token ID | 5465 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
advoc | +1.078 |
mathemat | +1.037 |
tyr | +0.938 |
horizont | +0.929 |
nodd | +0.924 |
Neg logit contributions | |
| -0.286 |
- | -0.258 |
on | -0.236 |
, | -0.221 |
: | -0.219 |
Token | speech |
Token ID | 4046 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
| +0.082 |
- | +0.071 |
on | +0.069 |
: | +0.062 |
in | +0.061 |
Neg logit contributions | |
advoc | -0.386 |
mathemat | -0.375 |
tyr | -0.340 |
destro | -0.339 |
horizont | -0.338 |
Token | Flag |
Token ID | 34227 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
| +1.289 |
- | +1.218 |
on | +1.218 |
in | +1.176 |
, | +1.153 |
Neg logit contributions | |
advoc | -2.019 |
mathemat | -1.931 |
horizont | -1.718 |
rul | -1.662 |
tyr | -1.661 |
Token | Reply |
Token ID | 14883 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
advoc | +0.777 |
mathemat | +0.755 |
horizont | +0.681 |
rul | +0.664 |
tyr | +0.662 |
Neg logit contributions | |
| -0.370 |
- | -0.349 |
on | -0.327 |
, | -0.316 |
— | -0.315 |
Token |
|
Token ID | 198 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
advoc | +1.226 |
mathemat | +1.193 |
horizont | +1.109 |
rul | +1.083 |
tyr | +1.069 |
Neg logit contributions | |
| -0.266 |
- | -0.231 |
on | -0.219 |
in | -0.196 |
, | -0.190 |
Token |
|
Token ID | 198 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
advoc | +1.267 |
mathemat | +1.225 |
horizont | +1.150 |
rul | +1.106 |
tyr | +1.097 |
Neg logit contributions | |
| -0.297 |
- | -0.258 |
on | -0.253 |
in | -0.227 |
, | -0.217 |
Token | 19 |
Token ID | 1129 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
advoc | +0.940 |
mathemat | +0.905 |
horizont | +0.835 |
tyr | +0.816 |
rul | +0.811 |
Neg logit contributions | |
| -0.270 |
on | -0.246 |
- | -0.235 |
in | -0.227 |
, | -0.215 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
| +0.025 |
- | +0.023 |
on | +0.022 |
— | +0.021 |
in | +0.021 |
Neg logit contributions | |
advoc | -0.054 |
mathemat | -0.051 |
horizont | -0.046 |
tyr | -0.045 |
rul | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
advoc | +4.795 |
mathemat | +4.672 |
horizont | +4.351 |
rul | +4.227 |
tyr | +4.178 |
Neg logit contributions | |
| -1.133 |
- | -0.983 |
on | -0.920 |
in | -0.827 |
, | -0.807 |
Token |
|
Token ID | 198 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
advoc | +0.692 |
mathemat | +0.668 |
horizont | +0.625 |
rul | +0.603 |
tyr | +0.598 |
Neg logit contributions | |
| -0.158 |
- | -0.136 |
on | -0.134 |
in | -0.121 |
, | -0.115 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
advoc | +0.134 |
mathemat | +0.126 |
horizont | +0.113 |
rul | +0.110 |
tyr | +0.110 |
Neg logit contributions | |
| -0.075 |
on | -0.071 |
- | -0.070 |
in | -0.068 |
, | -0.066 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
advoc | +3.281 |
mathemat | +3.203 |
horizont | +2.878 |
tyr | +2.873 |
rul | +2.849 |
Neg logit contributions | |
| -1.270 |
- | -1.162 |
on | -1.053 |
— | -1.032 |
, | -1.023 |
Token | this |
Token ID | 428 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
| +0.045 |
- | +0.033 |
on | +0.026 |
— | +0.023 |
, | +0.022 |
Neg logit contributions | |
advoc | -0.300 |
mathemat | -0.297 |
horizont | -0.275 |
rul | -0.269 |
tyr | -0.264 |
Token | Flag |
Token ID | 34227 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
| +0.263 |
on | +0.249 |
- | +0.248 |
in | +0.240 |
, | +0.235 |
Neg logit contributions | |
advoc | -0.411 |
mathemat | -0.393 |
horizont | -0.351 |
rul | -0.338 |
tyr | -0.337 |
Token | Reply |
Token ID | 14883 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
advoc | +1.711 |
mathemat | +1.669 |
horizont | +1.505 |
rul | +1.465 |
tyr | +1.459 |
Neg logit contributions | |
| -0.809 |
- | -0.760 |
on | -0.716 |
, | -0.689 |
— | -0.687 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
advoc | +1.907 |
mathemat | +1.858 |
horizont | +1.728 |
rul | +1.685 |
tyr | +1.661 |
Neg logit contributions | |
| -0.415 |
- | -0.361 |
on | -0.345 |
in | -0.309 |
, | -0.297 |
Token |
|
Token ID | 198 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
advoc | +2.096 |
mathemat | +2.027 |
horizont | +1.901 |
rul | +1.831 |
tyr | +1.817 |
Neg logit contributions | |
| -0.486 |
- | -0.424 |
on | -0.414 |
in | -0.373 |
, | -0.356 |
Token | 27 |
Token ID | 1983 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
advoc | +1.568 |
mathemat | +1.513 |
horizont | +1.396 |
tyr | +1.364 |
rul | +1.354 |
Neg logit contributions | |
| -0.429 |
on | -0.390 |
- | -0.373 |
in | -0.358 |
, | -0.339 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
advoc | +0.198 |
mathemat | +0.189 |
horizont | +0.172 |
tyr | +0.168 |
rul | +0.167 |
Neg logit contributions | |
| -0.090 |
- | -0.082 |
on | -0.078 |
in | -0.075 |
— | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
advoc | +4.852 |
mathemat | +4.732 |
horizont | +4.402 |
rul | +4.280 |
tyr | +4.232 |
Neg logit contributions | |
| -1.122 |
- | -0.973 |
on | -0.910 |
in | -0.816 |
, | -0.800 |
Token |
|
Token ID | 198 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
advoc | +1.866 |
mathemat | +1.803 |
horizont | +1.683 |
rul | +1.626 |
tyr | +1.613 |
Neg logit contributions | |
| -0.421 |
- | -0.363 |
on | -0.355 |
in | -0.320 |
, | -0.305 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
advoc | +0.922 |
mathemat | +0.867 |
horizont | +0.773 |
rul | +0.758 |
tyr | +0.758 |
Neg logit contributions | |
| -0.507 |
on | -0.481 |
- | -0.474 |
in | -0.461 |
, | -0.452 |
Token | Share |
Token ID | 8734 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
advoc | +3.849 |
mathemat | +3.766 |
horizont | +3.392 |
tyr | +3.369 |
rul | +3.342 |
Neg logit contributions | |
| -1.471 |
- | -1.348 |
on | -1.222 |
— | -1.190 |
, | -1.186 |
Token | this |
Token ID | 428 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
advoc | +0.673 |
mathemat | +0.664 |
horizont | +0.617 |
rul | +0.602 |
tyr | +0.592 |
Neg logit contributions | |
| -0.099 |
- | -0.074 |
on | -0.057 |
— | -0.051 |
, | -0.049 |
Token | all |
Token ID | 477 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
advoc | +0.991 |
mathemat | +0.981 |
tyr | +0.891 |
horizont | +0.885 |
nodd | +0.884 |
Neg logit contributions | |
| -0.183 |
- | -0.136 |
on | -0.129 |
, | -0.117 |
— | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
advoc | +0.194 |
mathemat | +0.193 |
horizont | +0.178 |
tyr | +0.175 |
nodd | +0.174 |
Neg logit contributions | |
| -0.021 |
- | -0.012 |
— | -0.007 |
on | -0.007 |
en | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
advoc | +0.030 |
mathemat | +0.029 |
horizont | +0.027 |
tyr | +0.026 |
rul | +0.026 |
Neg logit contributions | |
| -0.008 |
- | -0.007 |
on | -0.006 |
, | -0.006 |
— | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
advoc | +0.641 |
mathemat | +0.623 |
horizont | +0.583 |
rul | +0.559 |
tyr | +0.553 |
Neg logit contributions | |
| -0.153 |
- | -0.131 |
on | -0.129 |
in | -0.116 |
, | -0.110 |
Token | ( |
Token ID | 7 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
advoc | +0.690 |
mathemat | +0.675 |
horizont | +0.612 |
tyr | +0.596 |
nodd | +0.595 |
Neg logit contributions | |
| -0.188 |
on | -0.178 |
in | -0.164 |
- | -0.162 |
ad | -0.155 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
advoc | +0.431 |
mathemat | +0.426 |
horizont | +0.380 |
tyr | +0.378 |
nodd | +0.378 |
Neg logit contributions | |
| -0.160 |
- | -0.143 |
on | -0.141 |
in | -0.133 |
, | -0.133 |
Token | : |
Token ID | 25 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
advoc | +5.565 |
mathemat | +5.472 |
horizont | +5.086 |
tyr | +5.011 |
nodd | +4.976 |
Neg logit contributions | |
| -0.699 |
- | -0.437 |
on | -0.366 |
— | -0.309 |
in | -0.308 |
Token | Sherman |
Token ID | 23198 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
| +0.536 |
- | +0.471 |
on | +0.425 |
, | +0.416 |
. | +0.406 |
Neg logit contributions | |
advoc | -1.800 |
mathemat | -1.771 |
horizont | -1.599 |
tyr | -1.591 |
nodd | -1.571 |
Token | suffered |
Token ID | 6989 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
advoc | +1.130 |
mathemat | +1.121 |
horizont | +1.017 |
tyr | +1.006 |
nodd | +0.999 |
Neg logit contributions | |
| -0.296 |
- | -0.244 |
on | -0.221 |
— | -0.207 |
. | -0.207 |
Token | a |
Token ID | 257 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
| +0.017 |
- | +0.013 |
on | +0.010 |
— | +0.010 |
. | +0.009 |
Neg logit contributions | |
advoc | -0.107 |
mathemat | -0.106 |
tyr | -0.097 |
horizont | -0.096 |
nodd | -0.095 |
Token | rupt |
Token ID | 31580 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
advoc | +0.426 |
mathemat | +0.426 |
tyr | +0.386 |
destro | +0.381 |
rul | +0.374 |
Neg logit contributions | |
| -0.176 |
- | -0.155 |
on | -0.148 |
— | -0.142 |
. | -0.141 |
Token | acclaimed |
Token ID | 27023 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
| +0.094 |
on | +0.086 |
- | +0.081 |
: | +0.080 |
in | +0.080 |
Neg logit contributions | |
advoc | -0.226 |
mathemat | -0.223 |
nodd | -0.193 |
horizont | -0.192 |
tyr | -0.192 |
Token | Sheriff |
Token ID | 12874 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
advoc | +0.699 |
mathemat | +0.685 |
horizont | +0.626 |
tyr | +0.615 |
destro | +0.614 |
Neg logit contributions | |
| -0.183 |
- | -0.157 |
on | -0.148 |
in | -0.135 |
— | -0.135 |
Token | of |
Token ID | 286 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
| +0.267 |
- | +0.231 |
on | +0.224 |
in | +0.204 |
— | +0.202 |
Neg logit contributions | |
advoc | -1.174 |
mathemat | -1.157 |
horizont | -1.046 |
tyr | -1.042 |
nodd | -1.037 |
Token | Babylon |
Token ID | 28028 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
| +1.339 |
- | +1.250 |
on | +1.229 |
in | +1.167 |
, | +1.153 |
Neg logit contributions | |
advoc | -2.899 |
mathemat | -2.858 |
tyr | -2.547 |
horizont | -2.535 |
destro | -2.503 |
Token | min |
Token ID | 949 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
| +0.008 |
- | +0.007 |
on | +0.006 |
— | +0.006 |
in | +0.005 |
Neg logit contributions | |
advoc | -0.037 |
mathemat | -0.036 |
horizont | -0.033 |
tyr | -0.033 |
destro | -0.033 |
Token | iser |
Token ID | 5847 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
| +0.037 |
on | +0.035 |
- | +0.034 |
in | +0.033 |
Mar | +0.032 |
Neg logit contributions | |
advoc | -0.092 |
mathemat | -0.089 |
horizont | -0.081 |
tyr | -0.080 |
destro | -0.079 |
Token | ies |
Token ID | 444 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
| +1.622 |
- | +1.567 |
on | +1.515 |
in | +1.394 |
, | +1.361 |
Neg logit contributions | |
advoc | -6.184 |
mathemat | -6.048 |
horizont | -5.512 |
tyr | -5.461 |
rul | -5.367 |
Token | for |
Token ID | 329 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
advoc | +1.626 |
mathemat | +1.601 |
horizont | +1.483 |
destro | +1.455 |
tyr | +1.454 |
Neg logit contributions | |
| -0.200 |
- | -0.146 |
on | -0.109 |
en | -0.090 |
— | -0.086 |
Token | DC |
Token ID | 6257 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
advoc | +0.931 |
mathemat | +0.928 |
horizont | +0.838 |
tyr | +0.827 |
destro | +0.824 |
Neg logit contributions | |
| -0.259 |
- | -0.230 |
on | -0.207 |
. | -0.197 |
— | -0.196 |
Token | 's |
Token ID | 338 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
| +0.332 |
- | +0.284 |
on | +0.255 |
— | +0.226 |
: | +0.220 |
Neg logit contributions | |
mathemat | -1.634 |
advoc | -1.625 |
horizont | -1.477 |
destro | -1.446 |
nodd | -1.446 |
Token | Vert |
Token ID | 24417 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
advoc | +1.154 |
mathemat | +1.153 |
horizont | +1.034 |
destro | +1.013 |
tyr | +1.011 |
Neg logit contributions | |
| -0.400 |
- | -0.360 |
on | -0.334 |
— | -0.318 |
, | -0.316 |
Token | All |
Token ID | 3237 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
advoc | +0.048 |
mathemat | +0.048 |
horizont | +0.042 |
tyr | +0.042 |
nodd | +0.041 |
Neg logit contributions | |
| -0.017 |
on | -0.016 |
- | -0.016 |
in | -0.015 |
, | -0.015 |
Token | photos |
Token ID | 5205 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
| +0.017 |
- | +0.015 |
on | +0.014 |
, | +0.013 |
— | +0.013 |
Neg logit contributions | |
advoc | -0.070 |
mathemat | -0.069 |
tyr | -0.062 |
horizont | -0.062 |
nodd | -0.062 |
Token | taken |
Token ID | 2077 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
| +0.196 |
- | +0.164 |
on | +0.137 |
— | +0.121 |
. | +0.118 |
Neg logit contributions | |
advoc | -1.166 |
mathemat | -1.165 |
destro | -1.042 |
tyr | -1.042 |
horizont | -1.038 |
Token | today |
Token ID | 1909 |
Feature activation | +5.52e-03 |
Pos logit contributions | |
| +0.142 |
- | +0.109 |
on | +0.069 |
— | +0.068 |
, | +0.063 |
Neg logit contributions | |
mathemat | -1.220 |
advoc | -1.219 |
horizont | -1.113 |
tyr | -1.095 |
destro | -1.088 |
Token | unless |
Token ID | 4556 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
advoc | +0.014 |
mathemat | +0.014 |
horizont | +0.012 |
tyr | +0.012 |
destro | +0.012 |
Neg logit contributions | |
| -0.002 |
- | -0.001 |
on | -0.001 |
— | -0.001 |
in | -0.001 |
Token | otherwise |
Token ID | 4306 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
advoc | +0.196 |
mathemat | +0.193 |
tyr | +0.171 |
horizont | +0.171 |
destro | +0.171 |
Neg logit contributions | |
| -0.053 |
- | -0.048 |
on | -0.043 |
, | -0.041 |
. | -0.041 |
Token | noted |
Token ID | 4367 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
| +1.869 |
- | +1.714 |
on | +1.609 |
, | +1.518 |
in | +1.513 |
Neg logit contributions | |
advoc | -5.971 |
mathemat | -5.902 |
destro | -5.207 |
tyr | -5.206 |
horizont | -5.187 |
Token | . |
Token ID | 13 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
| +0.115 |
- | +0.086 |
on | +0.062 |
— | +0.048 |
in | +0.046 |
Neg logit contributions | |
advoc | -1.084 |
mathemat | -1.079 |
horizont | -0.977 |
tyr | -0.970 |
nodd | -0.963 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
advoc | +1.180 |
mathemat | +1.162 |
horizont | +1.051 |
tyr | +1.042 |
nodd | +1.031 |
Neg logit contributions | |
| -0.295 |
- | -0.271 |
on | -0.252 |
, | -0.238 |
in | -0.231 |
Token | The |
Token ID | 464 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
| +0.304 |
on | +0.288 |
- | +0.282 |
in | +0.272 |
, | +0.265 |
Neg logit contributions | |
advoc | -0.828 |
mathemat | -0.815 |
horizont | -0.725 |
tyr | -0.711 |
nodd | -0.707 |
Token | president |
Token ID | 1893 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
advoc | +0.777 |
mathemat | +0.773 |
horizont | +0.688 |
tyr | +0.687 |
destro | +0.680 |
Neg logit contributions | |
| -0.232 |
- | -0.214 |
on | -0.202 |
, | -0.192 |
. | -0.191 |
Token | vouchers |
Token ID | 41262 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
| +0.202 |
- | +0.174 |
on | +0.163 |
— | +0.147 |
. | +0.145 |
Neg logit contributions | |
advoc | -0.879 |
mathemat | -0.869 |
nodd | -0.777 |
horizont | -0.776 |
rul | -0.775 |
Token | are |
Token ID | 389 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
| +0.384 |
- | +0.331 |
on | +0.314 |
. | +0.295 |
: | +0.294 |
Neg logit contributions | |
advoc | -1.318 |
mathemat | -1.304 |
destro | -1.166 |
horizont | -1.158 |
rul | -1.147 |
Token | extended |
Token ID | 7083 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
| +0.282 |
- | +0.251 |
on | +0.227 |
. | +0.219 |
— | +0.219 |
Neg logit contributions | |
advoc | -0.894 |
mathemat | -0.886 |
destro | -0.786 |
horizont | -0.783 |
rul | -0.780 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
advoc | +0.494 |
mathemat | +0.493 |
horizont | +0.450 |
tyr | +0.441 |
nodd | +0.440 |
Neg logit contributions | |
| -0.065 |
- | -0.050 |
on | -0.037 |
m | -0.033 |
en | -0.033 |
Token | par |
Token ID | 1582 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
advoc | +0.527 |
mathemat | +0.526 |
nodd | +0.469 |
tyr | +0.468 |
rul | +0.468 |
Neg logit contributions | |
| -0.097 |
- | -0.084 |
on | -0.071 |
— | -0.067 |
, | -0.066 |
Token | och |
Token ID | 5374 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
| +0.138 |
on | +0.130 |
- | +0.129 |
, | +0.124 |
in | +0.124 |
Neg logit contributions | |
mathemat | -0.254 |
advoc | -0.253 |
horizont | -0.220 |
tyr | -0.219 |
nodd | -0.217 |
Token | ial |
Token ID | 498 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
| +1.663 |
on | +1.538 |
- | +1.523 |
in | +1.413 |
, | +1.400 |
Neg logit contributions | |
mathemat | -5.893 |
advoc | -5.872 |
tyr | -5.191 |
horizont | -5.187 |
nodd | -5.157 |
Token | schools |
Token ID | 4266 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
| +0.898 |
- | +0.799 |
on | +0.786 |
in | +0.730 |
. | +0.729 |
Neg logit contributions | |
advoc | -2.435 |
mathemat | -2.427 |
horizont | -2.138 |
tyr | -2.115 |
nodd | -2.108 |
Token | stand |
Token ID | 1302 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
| +0.121 |
- | +0.103 |
on | +0.089 |
. | +0.084 |
: | +0.083 |
Neg logit contributions | |
advoc | -0.554 |
mathemat | -0.551 |
horizont | -0.495 |
destro | -0.490 |
nodd | -0.488 |
Token | to |
Token ID | 284 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
| +0.025 |
- | +0.018 |
— | +0.013 |
on | +0.013 |
, | +0.012 |
Neg logit contributions | |
advoc | -0.196 |
mathemat | -0.194 |
horizont | -0.179 |
tyr | -0.179 |
nodd | -0.177 |
Token | gain |
Token ID | 4461 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
advoc | +0.313 |
mathemat | +0.312 |
tyr | +0.280 |
destro | +0.275 |
horizont | +0.275 |
Neg logit contributions | |
| -0.122 |
- | -0.110 |
on | -0.103 |
. | -0.097 |
: | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
| +0.099 |
- | +0.071 |
on | +0.065 |
in | +0.043 |
— | +0.033 |
Neg logit contributions | |
advoc | -1.175 |
mathemat | -1.157 |
horizont | -1.080 |
rul | -1.054 |
tyr | -1.037 |
Token | parse |
Token ID | 29572 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
| +0.364 |
- | +0.345 |
on | +0.344 |
in | +0.327 |
, | +0.324 |
Neg logit contributions | |
mathemat | -0.683 |
advoc | -0.679 |
horizont | -0.600 |
nodd | -0.579 |
rul | -0.578 |
Token | _ |
Token ID | 62 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
advoc | +1.092 |
mathemat | +1.065 |
horizont | +0.983 |
rul | +0.954 |
tyr | +0.938 |
Neg logit contributions | |
| -0.328 |
on | -0.298 |
- | -0.294 |
in | -0.277 |
, | -0.268 |
Token | args |
Token ID | 22046 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
advoc | +1.120 |
mathemat | +1.073 |
horizont | +0.951 |
rul | +0.918 |
tyr | +0.907 |
Neg logit contributions | |
| -0.840 |
- | -0.808 |
on | -0.798 |
in | -0.769 |
, | -0.762 |
Token | ()) |
Token ID | 28955 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
| +0.246 |
- | +0.234 |
on | +0.229 |
in | +0.221 |
, | +0.219 |
Neg logit contributions | |
advoc | -0.353 |
mathemat | -0.342 |
horizont | -0.308 |
rul | -0.295 |
tyr | -0.292 |
Token | # |
Token ID | 1303 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
| +0.325 |
- | +0.283 |
on | +0.255 |
, | +0.238 |
in | +0.232 |
Neg logit contributions | |
advoc | -1.665 |
mathemat | -1.641 |
horizont | -1.506 |
tyr | -1.498 |
nodd | -1.477 |
Token | initialize |
Token ID | 41216 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
| +3.567 |
- | +3.354 |
on | +3.267 |
— | +3.186 |
, | +3.165 |
Neg logit contributions | |
advoc | -4.053 |
mathemat | -4.035 |
horizont | -3.491 |
destro | -3.372 |
tyr | -3.342 |
Token | a |
Token ID | 257 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
| +0.004 |
- | +0.003 |
on | +0.002 |
in | +0.002 |
— | +0.002 |
Neg logit contributions | |
advoc | -0.025 |
mathemat | -0.024 |
horizont | -0.023 |
rul | -0.022 |
tyr | -0.022 |
Token | rectangular |
Token ID | 36954 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
| +0.982 |
- | +0.926 |
on | +0.901 |
, | +0.868 |
in | +0.867 |
Neg logit contributions | |
advoc | -1.306 |
mathemat | -1.291 |
horizont | -1.152 |
tyr | -1.090 |
rul | -1.088 |
Token | and |
Token ID | 290 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
advoc | +1.977 |
mathemat | +1.967 |
horizont | +1.821 |
tyr | +1.781 |
rul | +1.778 |
Neg logit contributions | |
| -0.214 |
- | -0.148 |
on | -0.123 |
: | -0.090 |
— | -0.089 |
Token | square |
Token ID | 6616 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
| +0.131 |
- | +0.118 |
on | +0.112 |
in | +0.105 |
, | +0.104 |
Neg logit contributions | |
advoc | -0.445 |
mathemat | -0.439 |
horizont | -0.404 |
rul | -0.392 |
tyr | -0.390 |
Token | will |
Token ID | 481 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
| +0.172 |
- | +0.140 |
on | +0.124 |
. | +0.115 |
m | +0.115 |
Neg logit contributions | |
advoc | -0.703 |
mathemat | -0.694 |
horizont | -0.626 |
rul | -0.618 |
nodd | -0.617 |
Token | be |
Token ID | 307 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
| +0.274 |
- | +0.241 |
on | +0.215 |
m | +0.203 |
. | +0.199 |
Neg logit contributions | |
advoc | -0.902 |
mathemat | -0.892 |
tyr | -0.817 |
horizont | -0.800 |
destro | -0.798 |
Token | the |
Token ID | 262 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
| +0.418 |
- | +0.372 |
on | +0.317 |
— | +0.309 |
. | +0.303 |
Neg logit contributions | |
advoc | -1.583 |
mathemat | -1.561 |
tyr | -1.399 |
nodd | -1.385 |
rul | -1.385 |
Token | equivalent |
Token ID | 7548 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
| +0.245 |
- | +0.217 |
on | +0.198 |
, | +0.186 |
. | +0.185 |
Neg logit contributions | |
advoc | -0.941 |
mathemat | -0.925 |
tyr | -0.831 |
horizont | -0.827 |
nodd | -0.825 |
Token | of |
Token ID | 286 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
| +0.053 |
- | +0.041 |
on | +0.034 |
, | +0.026 |
. | +0.024 |
Neg logit contributions | |
advoc | -0.563 |
mathemat | -0.559 |
horizont | -0.509 |
nodd | -0.507 |
tyr | -0.507 |
Token | Loving |
Token ID | 39202 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
| +0.313 |
- | +0.265 |
on | +0.237 |
. | +0.209 |
— | +0.208 |
Neg logit contributions | |
advoc | -1.507 |
mathemat | -1.484 |
tyr | -1.352 |
nodd | -1.343 |
rul | -1.335 |
Token | v |
Token ID | 410 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
| +1.191 |
- | +0.986 |
on | +0.885 |
— | +0.777 |
in | +0.771 |
Neg logit contributions | |
advoc | -6.392 |
mathemat | -6.311 |
horizont | -5.733 |
tyr | -5.695 |
nodd | -5.673 |
Token | . |
Token ID | 13 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
| +0.102 |
- | +0.069 |
on | +0.050 |
in | +0.029 |
, | +0.027 |
Neg logit contributions | |
advoc | -1.506 |
mathemat | -1.485 |
horizont | -1.369 |
tyr | -1.353 |
nodd | -1.350 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
advoc | +1.354 |
mathemat | +1.321 |
rul | +1.189 |
horizont | +1.184 |
tyr | +1.174 |
Neg logit contributions | |
| -0.551 |
- | -0.503 |
on | -0.478 |
— | -0.452 |
, | -0.445 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
advoc | +0.205 |
mathemat | +0.203 |
rul | +0.185 |
tyr | +0.184 |
horizont | +0.184 |
Neg logit contributions | |
| -0.025 |
- | -0.016 |
on | -0.011 |
— | -0.011 |
m | -0.008 |
Token | which |
Token ID | 543 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
advoc | +0.304 |
mathemat | +0.301 |
tyr | +0.274 |
rul | +0.272 |
nodd | +0.270 |
Neg logit contributions | |
| -0.048 |
- | -0.041 |
, | -0.031 |
: | -0.030 |
. | -0.030 |
Token | for |
Token ID | 329 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
| +0.108 |
- | +0.090 |
on | +0.062 |
Mar | +0.055 |
. | +0.052 |
Neg logit contributions | |
mathemat | -0.943 |
advoc | -0.939 |
horizont | -0.862 |
tyr | -0.854 |
nodd | -0.854 |
Token | a |
Token ID | 257 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
| +0.026 |
- | +0.023 |
on | +0.021 |
— | +0.019 |
, | +0.019 |
Neg logit contributions | |
advoc | -0.130 |
mathemat | -0.129 |
horizont | -0.117 |
nodd | -0.116 |
rul | -0.116 |
Token | chess |
Token ID | 19780 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
advoc | +1.128 |
mathemat | +1.118 |
destro | +1.002 |
horizont | +1.001 |
rul | +1.000 |
Neg logit contributions | |
| -0.377 |
- | -0.341 |
on | -0.321 |
, | -0.304 |
— | -0.303 |
Token | board |
Token ID | 3526 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
| +0.384 |
on | +0.338 |
- | +0.338 |
in | +0.315 |
, | +0.314 |
Neg logit contributions | |
advoc | -1.320 |
mathemat | -1.306 |
horizont | -1.164 |
rul | -1.159 |
nodd | -1.157 |
Token | ( |
Token ID | 357 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
| +0.025 |
- | +0.021 |
on | +0.018 |
, | +0.016 |
. | +0.016 |
Neg logit contributions | |
advoc | -0.145 |
mathemat | -0.144 |
horizont | -0.131 |
nodd | -0.130 |
rul | -0.130 |
Token | along |
Token ID | 24176 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
| +0.216 |
- | +0.202 |
on | +0.196 |
, | +0.183 |
in | +0.181 |
Neg logit contributions | |
advoc | -0.707 |
mathemat | -0.703 |
horizont | -0.627 |
nodd | -0.620 |
destro | -0.619 |
Token | side |
Token ID | 1589 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
| +0.797 |
- | +0.683 |
on | +0.613 |
, | +0.528 |
in | +0.505 |
Neg logit contributions | |
advoc | -6.712 |
mathemat | -6.653 |
horizont | -6.059 |
nodd | -6.026 |
tyr | -6.004 |
Token | our |
Token ID | 674 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
| +0.185 |
- | +0.157 |
on | +0.142 |
— | +0.127 |
. | +0.127 |
Neg logit contributions | |
advoc | -0.924 |
mathemat | -0.921 |
horizont | -0.832 |
rul | -0.826 |
nodd | -0.824 |
Token | earlier |
Token ID | 2961 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
| +0.040 |
- | +0.036 |
on | +0.034 |
— | +0.032 |
. | +0.032 |
Neg logit contributions | |
advoc | -0.124 |
mathemat | -0.123 |
horizont | -0.110 |
rul | -0.109 |
nodd | -0.109 |
Token | requirements |
Token ID | 5359 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
advoc | +1.154 |
mathemat | +1.138 |
nodd | +1.016 |
horizont | +1.015 |
rul | +1.011 |
Neg logit contributions | |
| -0.365 |
- | -0.320 |
on | -0.309 |
— | -0.290 |
in | -0.287 |
Token | ) |
Token ID | 8 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
| +0.064 |
- | +0.052 |
on | +0.042 |
Mar | +0.039 |
. | +0.037 |
Neg logit contributions | |
mathemat | -0.460 |
advoc | -0.459 |
horizont | -0.417 |
rul | -0.414 |
tyr | -0.414 |
Token | to |
Token ID | 284 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
| +0.076 |
- | +0.058 |
on | +0.048 |
, | +0.040 |
— | +0.038 |
Neg logit contributions | |
advoc | -0.679 |
mathemat | -0.671 |
horizont | -0.620 |
rul | -0.608 |
tyr | -0.602 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
| +0.041 |
- | +0.029 |
on | +0.023 |
in | +0.015 |
— | +0.013 |
Neg logit contributions | |
advoc | -0.459 |
mathemat | -0.452 |
horizont | -0.422 |
rul | -0.410 |
tyr | -0.407 |
Token | Sign |
Token ID | 5865 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
| +0.806 |
- | +0.743 |
on | +0.733 |
in | +0.693 |
, | +0.687 |
Neg logit contributions | |
advoc | -2.240 |
mathemat | -2.192 |
horizont | -1.983 |
tyr | -1.937 |
rul | -1.930 |
Token | Up |
Token ID | 3205 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
| +0.235 |
on | +0.202 |
- | +0.196 |
— | +0.185 |
in | +0.183 |
Neg logit contributions | |
advoc | -0.955 |
mathemat | -0.926 |
horizont | -0.850 |
tyr | -0.823 |
rul | -0.821 |
Token | You |
Token ID | 921 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
| +0.668 |
- | +0.591 |
on | +0.566 |
in | +0.523 |
, | +0.511 |
Neg logit contributions | |
advoc | -2.859 |
mathemat | -2.827 |
horizont | -2.565 |
tyr | -2.511 |
nodd | -2.497 |
Token | will |
Token ID | 481 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
| +0.947 |
- | +0.824 |
on | +0.768 |
in | +0.682 |
, | +0.679 |
Neg logit contributions | |
advoc | -4.788 |
mathemat | -4.711 |
horizont | -4.277 |
tyr | -4.206 |
rul | -4.170 |
Token | receive |
Token ID | 3328 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
| +1.920 |
- | +1.801 |
on | +1.720 |
, | +1.631 |
in | +1.614 |
Neg logit contributions | |
advoc | -5.312 |
mathemat | -5.252 |
horizont | -4.722 |
tyr | -4.668 |
destro | -4.609 |
Token | emails |
Token ID | 7237 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
| +1.253 |
- | +1.147 |
on | +1.087 |
, | +1.030 |
— | +1.011 |
Neg logit contributions | |
advoc | -3.564 |
mathemat | -3.524 |
horizont | -3.179 |
tyr | -3.097 |
nodd | -3.095 |
Token | containing |
Token ID | 7268 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
| +1.095 |
- | +1.003 |
on | +0.910 |
, | +0.862 |
— | +0.859 |
Neg logit contributions | |
advoc | -3.537 |
mathemat | -3.484 |
horizont | -3.145 |
rul | -3.091 |
nodd | -3.084 |
Token | news |
Token ID | 1705 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
| +0.642 |
- | +0.574 |
on | +0.523 |
m | +0.491 |
in | +0.484 |
Neg logit contributions | |
advoc | -2.064 |
mathemat | -2.033 |
horizont | -1.832 |
tyr | -1.791 |
nodd | -1.780 |
Token | content |
Token ID | 2695 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
| +1.186 |
- | +1.106 |
on | +1.048 |
, | +0.984 |
in | +0.982 |
Neg logit contributions | |
advoc | -4.070 |
mathemat | -3.992 |
horizont | -3.625 |
nodd | -3.552 |
tyr | -3.548 |
Token | eyes |
Token ID | 48418 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
| +0.340 |
on | +0.317 |
- | +0.315 |
in | +0.297 |
: | +0.295 |
Neg logit contributions | |
advoc | -0.729 |
mathemat | -0.720 |
horizont | -0.632 |
tyr | -0.628 |
rul | -0.624 |
Token | right |
Token ID | 826 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
| +0.197 |
- | +0.158 |
on | +0.114 |
: | +0.093 |
— | +0.083 |
Neg logit contributions | |
advoc | -1.774 |
mathemat | -1.754 |
horizont | -1.602 |
tyr | -1.599 |
nodd | -1.594 |
Token | now |
Token ID | 783 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
advoc | +0.473 |
mathemat | +0.464 |
nodd | +0.424 |
tyr | +0.424 |
horizont | +0.423 |
Neg logit contributions | |
| -0.082 |
- | -0.069 |
on | -0.059 |
: | -0.055 |
— | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
advoc | +0.084 |
mathemat | +0.084 |
nodd | +0.077 |
horizont | +0.076 |
tyr | +0.076 |
Neg logit contributions | |
| -0.007 |
- | -0.006 |
on | -0.004 |
Mar | -0.002 |
in | -0.002 |
Token | if |
Token ID | 611 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
| +0.066 |
- | +0.064 |
on | +0.058 |
: | +0.055 |
, | +0.055 |
Neg logit contributions | |
advoc | -0.245 |
mathemat | -0.243 |
tyr | -0.218 |
destro | -0.217 |
nodd | -0.217 |
Token | anything |
Token ID | 1997 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
| +0.527 |
- | +0.470 |
on | +0.421 |
: | +0.378 |
, | +0.370 |
Neg logit contributions | |
advoc | -2.886 |
mathemat | -2.865 |
nodd | -2.596 |
tyr | -2.579 |
destro | -2.565 |
Token | , |
Token ID | 11 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
| +0.745 |
- | +0.619 |
on | +0.530 |
in | +0.409 |
: | +0.406 |
Neg logit contributions | |
advoc | -6.464 |
mathemat | -6.435 |
tyr | -5.838 |
horizont | -5.812 |
nodd | -5.798 |
Token | � |
Token ID | 447 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
| +0.321 |
- | +0.313 |
on | +0.273 |
: | +0.267 |
, | +0.264 |
Neg logit contributions | |
advoc | -1.291 |
mathemat | -1.283 |
tyr | -1.154 |
nodd | -1.149 |
destro | -1.149 |
Token | � |
Token ID | 251 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
advoc | +0.439 |
mathemat | +0.435 |
tyr | +0.373 |
horizont | +0.371 |
nodd | +0.369 |
Neg logit contributions | |
| -0.312 |
- | -0.302 |
on | -0.293 |
, | -0.283 |
in | -0.283 |
Token | Butler |
Token ID | 17389 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
advoc | +0.774 |
mathemat | +0.764 |
tyr | +0.682 |
nodd | +0.678 |
destro | +0.669 |
Neg logit contributions | |
| -0.316 |
- | -0.294 |
on | -0.281 |
, | -0.268 |
: | -0.267 |
Token | said |
Token ID | 531 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
advoc | +0.046 |
mathemat | +0.046 |
tyr | +0.041 |
nodd | +0.041 |
destro | +0.041 |
Neg logit contributions | |
| -0.014 |
- | -0.013 |
on | -0.013 |
in | -0.012 |
: | -0.011 |
Token | Evil |
Token ID | 10461 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
advoc | +0.517 |
mathemat | +0.510 |
horizont | +0.453 |
tyr | +0.446 |
nodd | +0.442 |
Neg logit contributions | |
| -0.215 |
- | -0.204 |
on | -0.196 |
, | -0.188 |
in | -0.187 |
Token | 4 |
Token ID | 604 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
| +0.086 |
- | +0.077 |
on | +0.071 |
in | +0.065 |
, | +0.065 |
Neg logit contributions | |
advoc | -0.407 |
mathemat | -0.403 |
tyr | -0.366 |
horizont | -0.365 |
destro | -0.362 |
Token | � |
Token ID | 447 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
| +0.272 |
- | +0.256 |
on | +0.239 |
in | +0.221 |
, | +0.219 |
Neg logit contributions | |
advoc | -1.011 |
mathemat | -1.002 |
destro | -0.902 |
tyr | -0.897 |
horizont | -0.893 |
Token | � |
Token ID | 247 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
| +0.116 |
- | +0.113 |
on | +0.110 |
, | +0.107 |
in | +0.106 |
Neg logit contributions | |
advoc | -0.155 |
mathemat | -0.150 |
rul | -0.130 |
horizont | -0.130 |
destro | -0.129 |
Token | s |
Token ID | 82 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
| +0.037 |
- | +0.034 |
on | +0.033 |
in | +0.029 |
, | +0.029 |
Neg logit contributions | |
advoc | -0.186 |
mathemat | -0.184 |
destro | -0.168 |
horizont | -0.166 |
rul | -0.166 |
Token | bliss |
Token ID | 30533 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
| +0.434 |
- | +0.395 |
on | +0.368 |
, | +0.349 |
. | +0.344 |
Neg logit contributions | |
advoc | -1.441 |
mathemat | -1.417 |
tyr | -1.277 |
destro | -1.275 |
horizont | -1.270 |
Token | ful |
Token ID | 913 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
| +1.650 |
- | +1.469 |
on | +1.405 |
, | +1.330 |
— | +1.313 |
Neg logit contributions | |
advoc | -5.422 |
mathemat | -5.390 |
nodd | -4.817 |
horizont | -4.805 |
destro | -4.804 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
| +0.294 |
- | +0.258 |
on | +0.252 |
in | +0.235 |
— | +0.234 |
Neg logit contributions | |
advoc | -0.943 |
mathemat | -0.931 |
horizont | -0.835 |
destro | -0.831 |
nodd | -0.831 |
Token | se |
Token ID | 384 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
| +0.126 |
- | +0.119 |
on | +0.111 |
, | +0.107 |
: | +0.107 |
Neg logit contributions | |
advoc | -0.336 |
mathemat | -0.332 |
tyr | -0.297 |
horizont | -0.295 |
destro | -0.295 |
Token | rene |
Token ID | 25924 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
| +0.416 |
on | +0.390 |
- | +0.387 |
in | +0.367 |
, | +0.362 |
Neg logit contributions | |
advoc | -0.991 |
mathemat | -0.981 |
horizont | -0.881 |
destro | -0.861 |
nodd | -0.860 |
Token | save |
Token ID | 3613 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
| +0.253 |
- | +0.222 |
on | +0.218 |
in | +0.200 |
: | +0.199 |
Neg logit contributions | |
advoc | -0.837 |
mathemat | -0.827 |
horizont | -0.745 |
tyr | -0.741 |
destro | -0.737 |
Token | . |
Token ID | 13 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
| +0.100 |
- | +0.082 |
on | +0.047 |
— | +0.039 |
o | +0.038 |
Neg logit contributions | |
advoc | -0.968 |
mathemat | -0.949 |
horizont | -0.879 |
tyr | -0.867 |
destro | -0.863 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
advoc | +0.116 |
mathemat | +0.113 |
horizont | +0.103 |
tyr | +0.102 |
rul | +0.101 |
Neg logit contributions | |
| -0.025 |
- | -0.024 |
on | -0.022 |
, | -0.020 |
in | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
advoc | +0.454 |
mathemat | +0.441 |
horizont | +0.412 |
rul | +0.397 |
tyr | +0.391 |
Neg logit contributions | |
| -0.102 |
- | -0.091 |
on | -0.089 |
in | -0.080 |
, | -0.076 |
Token | Get |
Token ID | 3855 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
advoc | +0.301 |
mathemat | +0.293 |
horizont | +0.264 |
tyr | +0.257 |
rul | +0.255 |
Neg logit contributions | |
| -0.105 |
on | -0.104 |
- | -0.100 |
in | -0.097 |
, | -0.093 |
Token | The |
Token ID | 383 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
| +0.039 |
- | +0.034 |
on | +0.032 |
, | +0.031 |
in | +0.030 |
Neg logit contributions | |
advoc | -0.162 |
mathemat | -0.159 |
destro | -0.141 |
horizont | -0.141 |
nodd | -0.141 |
Token | Times |
Token ID | 3782 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
| +1.048 |
- | +0.959 |
on | +0.918 |
, | +0.867 |
: | +0.860 |
Neg logit contributions | |
advoc | -3.125 |
mathemat | -3.088 |
horizont | -2.803 |
tyr | -2.723 |
destro | -2.679 |
Token | of |
Token ID | 286 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
| +0.608 |
- | +0.502 |
on | +0.432 |
, | +0.353 |
in | +0.333 |
Neg logit contributions | |
advoc | -6.369 |
mathemat | -6.287 |
horizont | -5.760 |
tyr | -5.672 |
nodd | -5.669 |
Token | Israel |
Token ID | 2692 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
| +1.278 |
- | +1.209 |
on | +1.191 |
in | +1.114 |
, | +1.109 |
Neg logit contributions | |
advoc | -3.394 |
mathemat | -3.302 |
horizont | -2.965 |
tyr | -2.939 |
destro | -2.871 |
Token | 's |
Token ID | 338 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
| +0.436 |
- | +0.381 |
on | +0.337 |
, | +0.291 |
in | +0.290 |
Neg logit contributions | |
advoc | -2.909 |
mathemat | -2.886 |
horizont | -2.615 |
tyr | -2.586 |
nodd | -2.583 |
Token | Daily |
Token ID | 6714 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
| +0.148 |
- | +0.139 |
on | +0.130 |
, | +0.125 |
. | +0.123 |
Neg logit contributions | |
advoc | -0.461 |
mathemat | -0.452 |
horizont | -0.411 |
tyr | -0.404 |
nodd | -0.401 |
Token | Edition |
Token ID | 5061 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
| +0.727 |
- | +0.675 |
on | +0.636 |
, | +0.599 |
in | +0.593 |
Neg logit contributions | |
advoc | -2.661 |
mathemat | -2.649 |
horizont | -2.386 |
tyr | -2.351 |
nodd | -2.350 |
Token | two |
Token ID | 734 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
advoc | +1.411 |
mathemat | +1.367 |
horizont | +1.239 |
nodd | +1.231 |
rul | +1.221 |
Neg logit contributions | |
| -0.311 |
- | -0.269 |
on | -0.248 |
— | -0.230 |
, | -0.228 |
Token | parties |
Token ID | 4671 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
advoc | +1.575 |
mathemat | +1.515 |
horizont | +1.381 |
nodd | +1.365 |
tyr | +1.349 |
Neg logit contributions | |
| -0.392 |
- | -0.336 |
on | -0.314 |
en | -0.288 |
— | -0.283 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
advoc | +1.806 |
mathemat | +1.780 |
horizont | +1.626 |
rul | +1.608 |
tyr | +1.593 |
Neg logit contributions | |
| -0.178 |
- | -0.120 |
on | -0.077 |
en | -0.071 |
Mar | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
| +0.058 |
- | +0.052 |
on | +0.049 |
, | +0.045 |
in | +0.044 |
Neg logit contributions | |
advoc | -0.228 |
mathemat | -0.223 |
horizont | -0.202 |
rul | -0.200 |
tyr | -0.200 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
| +0.078 |
on | +0.068 |
- | +0.068 |
in | +0.061 |
, | +0.059 |
Neg logit contributions | |
advoc | -0.376 |
mathemat | -0.364 |
horizont | -0.337 |
rul | -0.328 |
tyr | -0.324 |
Token | Prep |
Token ID | 37534 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
| +0.095 |
on | +0.093 |
- | +0.087 |
in | +0.086 |
, | +0.083 |
Neg logit contributions | |
advoc | -0.270 |
mathemat | -0.262 |
horizont | -0.236 |
rul | -0.228 |
tyr | -0.228 |
Token | aring |
Token ID | 1723 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
| +1.544 |
- | +1.427 |
on | +1.391 |
in | +1.290 |
, | +1.282 |
Neg logit contributions | |
advoc | -5.337 |
mathemat | -5.256 |
nodd | -4.704 |
tyr | -4.689 |
rul | -4.672 |
Token | for |
Token ID | 329 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
| +0.138 |
- | +0.112 |
on | +0.092 |
, | +0.076 |
— | +0.076 |
Neg logit contributions | |
advoc | -1.139 |
mathemat | -1.113 |
horizont | -1.020 |
tyr | -1.014 |
nodd | -1.014 |
Token | independence |
Token ID | 10404 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
advoc | +0.463 |
mathemat | +0.457 |
horizont | +0.414 |
tyr | +0.413 |
rul | +0.409 |
Neg logit contributions | |
| -0.100 |
- | -0.088 |
on | -0.081 |
— | -0.073 |
. | -0.073 |
Token | : |
Token ID | 25 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
advoc | +0.483 |
mathemat | +0.472 |
rul | +0.431 |
horizont | +0.425 |
tyr | +0.423 |
Neg logit contributions | |
| -0.075 |
- | -0.058 |
on | -0.048 |
— | -0.041 |
en | -0.041 |
Token | 1961 |
Token ID | 20510 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
| +0.037 |
- | +0.034 |
on | +0.030 |
, | +0.030 |
. | +0.029 |
Neg logit contributions | |
advoc | -0.148 |
mathemat | -0.146 |
horizont | -0.132 |
tyr | -0.131 |
rul | -0.130 |
Token | Fresh |
Token ID | 20138 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
advoc | +0.403 |
mathemat | +0.398 |
nodd | +0.357 |
horizont | +0.354 |
destro | +0.353 |
Neg logit contributions | |
| -0.108 |
- | -0.087 |
on | -0.082 |
— | -0.077 |
m | -0.074 |
Token | man |
Token ID | 805 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
| +0.034 |
on | +0.029 |
- | +0.028 |
— | +0.025 |
, | +0.025 |
Neg logit contributions | |
advoc | -0.179 |
mathemat | -0.176 |
horizont | -0.162 |
nodd | -0.161 |
destro | -0.158 |
Token | first |
Token ID | 717 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
advoc | +0.983 |
mathemat | +0.962 |
nodd | +0.882 |
horizont | +0.871 |
destro | +0.868 |
Neg logit contributions | |
| -0.146 |
- | -0.103 |
on | -0.099 |
— | -0.085 |
in | -0.082 |
Token | team |
Token ID | 1074 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
| +0.353 |
on | +0.301 |
- | +0.291 |
: | +0.279 |
— | +0.277 |
Neg logit contributions | |
advoc | -1.281 |
mathemat | -1.249 |
horizont | -1.131 |
nodd | -1.130 |
tyr | -1.126 |
Token | ( |
Token ID | 357 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
| +0.013 |
- | +0.011 |
on | +0.008 |
m | +0.008 |
o | +0.007 |
Neg logit contributions | |
advoc | -0.070 |
mathemat | -0.070 |
horizont | -0.063 |
nodd | -0.063 |
tyr | -0.063 |
Token | along |
Token ID | 24176 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
advoc | +0.136 |
mathemat | +0.134 |
horizont | +0.119 |
tyr | +0.118 |
nodd | +0.117 |
Neg logit contributions | |
| -0.048 |
- | -0.044 |
on | -0.043 |
, | -0.040 |
in | -0.040 |
Token | with |
Token ID | 351 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
| +0.723 |
- | +0.605 |
on | +0.527 |
, | +0.454 |
in | +0.435 |
Neg logit contributions | |
advoc | -6.228 |
mathemat | -6.176 |
horizont | -5.624 |
nodd | -5.585 |
tyr | -5.570 |
Token | Jones |
Token ID | 5437 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
| +0.361 |
- | +0.314 |
on | +0.295 |
— | +0.276 |
. | +0.276 |
Neg logit contributions | |
advoc | -1.213 |
mathemat | -1.201 |
tyr | -1.079 |
horizont | -1.079 |
destro | -1.064 |
Token | and |
Token ID | 290 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
advoc | +0.361 |
mathemat | +0.357 |
horizont | +0.326 |
tyr | +0.326 |
destro | +0.324 |
Neg logit contributions | |
| -0.051 |
- | -0.036 |
on | -0.034 |
. | -0.030 |
: | -0.029 |
Token | Wins |
Token ID | 24423 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
| +0.376 |
- | +0.339 |
on | +0.323 |
, | +0.303 |
— | +0.303 |
Neg logit contributions | |
advoc | -1.128 |
mathemat | -1.113 |
horizont | -1.002 |
tyr | -0.997 |
destro | -0.988 |
Token | low |
Token ID | 9319 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
| +0.396 |
- | +0.349 |
on | +0.341 |
in | +0.313 |
— | +0.311 |
Neg logit contributions | |
advoc | -1.458 |
mathemat | -1.434 |
tyr | -1.296 |
nodd | -1.291 |
horizont | -1.291 |
Token | the |
Token ID | 262 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
| +0.194 |
- | +0.174 |
on | +0.155 |
, | +0.142 |
: | +0.140 |
Neg logit contributions | |
advoc | -0.938 |
mathemat | -0.921 |
tyr | -0.843 |
horizont | -0.842 |
destro | -0.836 |
Token | cops |
Token ID | 14073 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
| +0.052 |
- | +0.049 |
on | +0.045 |
, | +0.044 |
. | +0.043 |
Neg logit contributions | |
advoc | -0.150 |
mathemat | -0.148 |
horizont | -0.133 |
tyr | -0.132 |
destro | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
| +0.129 |
- | +0.103 |
on | +0.077 |
Mar | +0.058 |
: | +0.058 |
Neg logit contributions | |
advoc | -1.137 |
mathemat | -1.126 |
horizont | -1.043 |
tyr | -1.030 |
destro | -1.028 |
Token | If |
Token ID | 1002 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
advoc | +0.456 |
mathemat | +0.444 |
horizont | +0.409 |
tyr | +0.402 |
rul | +0.400 |
Neg logit contributions | |
| -0.118 |
- | -0.108 |
on | -0.100 |
, | -0.093 |
in | -0.091 |
Token | nothing |
Token ID | 2147 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
| +0.181 |
- | +0.153 |
on | +0.134 |
— | +0.115 |
: | +0.114 |
Neg logit contributions | |
advoc | -1.095 |
mathemat | -1.077 |
destro | -0.984 |
horizont | -0.984 |
nodd | -0.979 |
Token | else |
Token ID | 2073 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
| +0.743 |
- | +0.696 |
on | +0.648 |
. | +0.621 |
: | +0.620 |
Neg logit contributions | |
advoc | -1.657 |
mathemat | -1.625 |
destro | -1.442 |
horizont | -1.438 |
tyr | -1.426 |
Token | , |
Token ID | 11 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
| +0.462 |
- | +0.334 |
on | +0.253 |
in | +0.154 |
. | +0.135 |
Neg logit contributions | |
advoc | -6.392 |
mathemat | -6.334 |
destro | -5.786 |
horizont | -5.778 |
tyr | -5.773 |
Token | all |
Token ID | 477 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
| +0.353 |
- | +0.313 |
on | +0.256 |
, | +0.240 |
— | +0.237 |
Neg logit contributions | |
advoc | -2.123 |
mathemat | -2.094 |
tyr | -1.909 |
horizont | -1.906 |
destro | -1.901 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
| +0.351 |
- | +0.270 |
on | +0.250 |
— | +0.232 |
, | +0.228 |
Neg logit contributions | |
advoc | -2.307 |
mathemat | -2.243 |
horizont | -2.064 |
destro | -2.055 |
tyr | -2.051 |
Token | these |
Token ID | 777 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
advoc | +0.256 |
mathemat | +0.249 |
horizont | +0.229 |
tyr | +0.229 |
destro | +0.227 |
Neg logit contributions | |
| -0.036 |
- | -0.030 |
on | -0.026 |
, | -0.023 |
. | -0.023 |
Token | images |
Token ID | 4263 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
| +0.109 |
- | +0.097 |
on | +0.090 |
— | +0.085 |
, | +0.085 |
Neg logit contributions | |
advoc | -0.370 |
mathemat | -0.360 |
horizont | -0.327 |
destro | -0.326 |
tyr | -0.326 |
Token | that |
Token ID | 326 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
| +0.192 |
- | +0.155 |
on | +0.121 |
in | +0.093 |
, | +0.086 |
Neg logit contributions | |
advoc | -1.789 |
mathemat | -1.758 |
horizont | -1.624 |
rul | -1.607 |
tyr | -1.597 |
Token | the |
Token ID | 262 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
| +0.230 |
- | +0.179 |
on | +0.144 |
, | +0.110 |
in | +0.109 |
Neg logit contributions | |
advoc | -2.249 |
mathemat | -2.215 |
horizont | -2.036 |
rul | -2.004 |
tyr | -2.000 |
Token | old |
Token ID | 1468 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
| +0.685 |
- | +0.590 |
on | +0.550 |
— | +0.536 |
, | +0.517 |
Neg logit contributions | |
advoc | -1.977 |
mathemat | -1.932 |
rul | -1.749 |
horizont | -1.732 |
nodd | -1.728 |
Token | address |
Token ID | 2209 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
| +0.452 |
- | +0.369 |
on | +0.340 |
— | +0.315 |
Mar | +0.315 |
Neg logit contributions | |
advoc | -1.900 |
mathemat | -1.858 |
horizont | -1.680 |
tyr | -1.672 |
rul | -1.661 |
Token | https |
Token ID | 3740 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
advoc | +0.397 |
mathemat | +0.394 |
tyr | +0.358 |
nodd | +0.354 |
destro | +0.353 |
Neg logit contributions | |
| -0.087 |
- | -0.076 |
on | -0.066 |
, | -0.064 |
— | -0.061 |
Token | :// |
Token ID | 1378 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
| +1.252 |
- | +1.142 |
on | +1.118 |
in | +1.052 |
, | +1.052 |
Neg logit contributions | |
advoc | -3.396 |
mathemat | -3.335 |
horizont | -2.985 |
rul | -2.923 |
tyr | -2.921 |
Token | . |
Token ID | 764 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
| +1.193 |
- | +1.020 |
on | +0.920 |
, | +0.876 |
in | +0.829 |
Neg logit contributions | |
advoc | -5.643 |
mathemat | -5.559 |
tyr | -5.026 |
nodd | -5.019 |
horizont | -5.005 |
Token | nice |
Token ID | 44460 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
advoc | +0.262 |
mathemat | +0.259 |
tyr | +0.228 |
horizont | +0.226 |
nodd | +0.224 |
Neg logit contributions | |
| -0.177 |
- | -0.163 |
on | -0.159 |
Mar | -0.157 |
— | -0.153 |
Token | hash |
Token ID | 17831 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
| +0.452 |
- | +0.429 |
on | +0.424 |
in | +0.405 |
, | +0.403 |
Neg logit contributions | |
mathemat | -0.793 |
advoc | -0.792 |
horizont | -0.688 |
tyr | -0.680 |
rul | -0.670 |
Token | . |
Token ID | 13 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
advoc | +0.893 |
mathemat | +0.875 |
horizont | +0.818 |
rul | +0.797 |
tyr | +0.788 |
Neg logit contributions | |
| -0.078 |
- | -0.052 |
on | -0.047 |
in | -0.032 |
, | -0.027 |
Token | com |
Token ID | 785 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
| +0.586 |
- | +0.553 |
on | +0.537 |
in | +0.503 |
, | +0.503 |
Neg logit contributions | |
advoc | -1.517 |
mathemat | -1.480 |
horizont | -1.337 |
tyr | -1.292 |
rul | -1.290 |
Token | s |
Token ID | 82 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
advoc | +0.987 |
mathemat | +0.976 |
destro | +0.889 |
horizont | +0.883 |
tyr | +0.877 |
Neg logit contributions | |
| -0.196 |
- | -0.183 |
on | -0.174 |
in | -0.154 |
, | -0.150 |
Token | a |
Token ID | 257 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
| +0.197 |
- | +0.180 |
on | +0.158 |
, | +0.143 |
. | +0.143 |
Neg logit contributions | |
advoc | -0.965 |
mathemat | -0.961 |
tyr | -0.865 |
horizont | -0.860 |
destro | -0.851 |
Token | narrow |
Token ID | 7135 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
| +0.425 |
- | +0.402 |
on | +0.386 |
in | +0.362 |
, | +0.360 |
Neg logit contributions | |
mathemat | -1.261 |
advoc | -1.261 |
tyr | -1.122 |
horizont | -1.113 |
destro | -1.110 |
Token | , |
Token ID | 11 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
advoc | +0.735 |
mathemat | +0.726 |
horizont | +0.649 |
tyr | +0.645 |
nodd | +0.639 |
Neg logit contributions | |
| -0.187 |
on | -0.171 |
- | -0.168 |
in | -0.157 |
. | -0.154 |
Token | par |
Token ID | 1582 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
| +0.039 |
- | +0.037 |
on | +0.035 |
. | +0.033 |
, | +0.033 |
Neg logit contributions | |
advoc | -0.111 |
mathemat | -0.111 |
tyr | -0.098 |
horizont | -0.098 |
nodd | -0.096 |
Token | och |
Token ID | 5374 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
mathemat | +0.614 |
advoc | +0.609 |
tyr | +0.533 |
horizont | +0.526 |
rul | +0.520 |
Neg logit contributions | |
| -0.336 |
- | -0.322 |
on | -0.320 |
, | -0.306 |
in | -0.305 |
Token | ial |
Token ID | 498 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
| +1.497 |
- | +1.402 |
on | +1.399 |
in | +1.300 |
, | +1.258 |
Neg logit contributions | |
mathemat | -5.054 |
advoc | -5.022 |
horizont | -4.477 |
tyr | -4.468 |
destro | -4.424 |
Token | � |
Token ID | 564 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
| +0.723 |
- | +0.671 |
on | +0.658 |
in | +0.613 |
. | +0.603 |
Neg logit contributions | |
advoc | -2.229 |
mathemat | -2.209 |
tyr | -1.950 |
horizont | -1.949 |
nodd | -1.936 |
Token | � |
Token ID | 246 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
advoc | +0.576 |
mathemat | +0.563 |
tyr | +0.486 |
horizont | +0.484 |
rul | +0.482 |
Neg logit contributions | |
| -0.397 |
- | -0.388 |
on | -0.379 |
in | -0.365 |
, | -0.364 |
Token | my |
Token ID | 1820 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
| +0.140 |
- | +0.131 |
on | +0.131 |
in | +0.123 |
, | +0.121 |
Neg logit contributions | |
advoc | -0.406 |
mathemat | -0.397 |
horizont | -0.354 |
tyr | -0.352 |
nodd | -0.349 |
Token | country |
Token ID | 1499 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
| +0.155 |
- | +0.144 |
on | +0.142 |
in | +0.130 |
: | +0.129 |
Neg logit contributions | |
advoc | -0.595 |
mathemat | -0.586 |
tyr | -0.522 |
horizont | -0.520 |
nodd | -0.517 |
Token | of |
Token ID | 286 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
advoc | +0.203 |
mathemat | +0.202 |
nodd | +0.182 |
tyr | +0.182 |
horizont | +0.182 |
Neg logit contributions | |
| -0.021 |
- | -0.017 |
on | -0.015 |
in | -0.012 |
, | -0.012 |
Token | Pro |
Token ID | 1041 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
| +0.022 |
- | +0.020 |
on | +0.018 |
— | +0.017 |
, | +0.017 |
Neg logit contributions | |
advoc | -0.075 |
mathemat | -0.075 |
nodd | -0.066 |
horizont | -0.066 |
destro | -0.066 |
Token | Football |
Token ID | 9957 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
advoc | +0.593 |
mathemat | +0.582 |
horizont | +0.517 |
tyr | +0.507 |
nodd | +0.505 |
Neg logit contributions | |
| -0.255 |
on | -0.236 |
- | -0.229 |
in | -0.224 |
, | -0.223 |
Token | Focus |
Token ID | 17061 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
advoc | +1.571 |
mathemat | +1.529 |
horizont | +1.370 |
nodd | +1.347 |
rul | +1.342 |
Neg logit contributions | |
| -0.655 |
on | -0.562 |
- | -0.555 |
in | -0.537 |
— | -0.529 |
Token | unless |
Token ID | 4556 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
mathemat | +1.276 |
advoc | +1.271 |
horizont | +1.156 |
nodd | +1.139 |
destro | +1.137 |
Neg logit contributions | |
| -0.140 |
- | -0.104 |
on | -0.076 |
m | -0.058 |
in | -0.058 |
Token | otherwise |
Token ID | 4306 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
| +0.052 |
- | +0.047 |
on | +0.043 |
. | +0.040 |
, | +0.040 |
Neg logit contributions | |
advoc | -0.188 |
mathemat | -0.187 |
tyr | -0.165 |
nodd | -0.164 |
destro | -0.164 |
Token | indicated |
Token ID | 8203 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
| +1.600 |
- | +1.467 |
on | +1.398 |
in | +1.306 |
, | +1.304 |
Neg logit contributions | |
advoc | -5.062 |
mathemat | -4.992 |
destro | -4.412 |
tyr | -4.390 |
rul | -4.375 |
Token | . |
Token ID | 13 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
| +0.188 |
- | +0.137 |
on | +0.096 |
in | +0.058 |
en | +0.058 |
Neg logit contributions | |
advoc | -2.096 |
mathemat | -2.090 |
horizont | -1.893 |
destro | -1.889 |
tyr | -1.882 |
Token | All |
Token ID | 1439 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
advoc | +0.806 |
mathemat | +0.793 |
horizont | +0.715 |
tyr | +0.704 |
nodd | +0.701 |
Neg logit contributions | |
| -0.210 |
- | -0.190 |
on | -0.179 |
, | -0.169 |
in | -0.167 |
Token | salary |
Token ID | 9588 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
| +0.314 |
- | +0.272 |
on | +0.267 |
, | +0.254 |
— | +0.249 |
Neg logit contributions | |
advoc | -1.028 |
mathemat | -1.008 |
horizont | -0.896 |
destro | -0.893 |
rul | -0.893 |
Token | - |
Token ID | 12 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
advoc | +0.206 |
mathemat | +0.203 |
horizont | +0.182 |
tyr | +0.181 |
destro | +0.180 |
Neg logit contributions | |
| -0.053 |
on | -0.045 |
- | -0.043 |
in | -0.040 |
— | -0.040 |
Token | ( |
Token ID | 357 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
| +0.097 |
- | +0.078 |
on | +0.067 |
, | +0.057 |
in | +0.056 |
Neg logit contributions | |
advoc | -0.699 |
mathemat | -0.685 |
horizont | -0.636 |
rul | -0.622 |
tyr | -0.613 |
Token | 21 |
Token ID | 2481 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
| +0.407 |
on | +0.375 |
- | +0.363 |
in | +0.344 |
, | +0.329 |
Neg logit contributions | |
advoc | -1.921 |
mathemat | -1.888 |
horizont | -1.739 |
rul | -1.704 |
nodd | -1.699 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
| +0.130 |
- | +0.085 |
on | +0.078 |
in | +0.048 |
— | +0.024 |
Neg logit contributions | |
advoc | -1.736 |
mathemat | -1.702 |
horizont | -1.602 |
rul | -1.563 |
tyr | -1.529 |
Token | 21 |
Token ID | 2310 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
| +0.006 |
- | +0.005 |
on | +0.005 |
in | +0.004 |
, | +0.004 |
Neg logit contributions | |
advoc | -0.043 |
mathemat | -0.042 |
horizont | -0.039 |
rul | -0.039 |
nodd | -0.038 |
Token | )) |
Token ID | 4008 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
| +0.744 |
- | +0.703 |
on | +0.679 |
in | +0.650 |
, | +0.640 |
Neg logit contributions | |
advoc | -1.474 |
mathemat | -1.434 |
horizont | -1.303 |
rul | -1.255 |
tyr | -1.246 |
Token | # |
Token ID | 1303 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
| +0.211 |
- | +0.185 |
on | +0.169 |
, | +0.156 |
in | +0.153 |
Neg logit contributions | |
advoc | -1.082 |
mathemat | -1.070 |
horizont | -0.980 |
tyr | -0.972 |
nodd | -0.961 |
Token | loop |
Token ID | 9052 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
| +1.782 |
- | +1.595 |
on | +1.529 |
in | +1.444 |
, | +1.441 |
Neg logit contributions | |
advoc | -4.695 |
mathemat | -4.690 |
horizont | -4.295 |
tyr | -4.234 |
destro | -4.204 |
Token | over |
Token ID | 625 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
| +0.163 |
- | +0.133 |
on | +0.108 |
, | +0.098 |
: | +0.094 |
Neg logit contributions | |
advoc | -1.178 |
mathemat | -1.166 |
horizont | -1.078 |
rul | -1.060 |
tyr | -1.054 |
Token | the |
Token ID | 262 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
advoc | +1.817 |
mathemat | +1.776 |
horizont | +1.665 |
rul | +1.616 |
tyr | +1.596 |
Neg logit contributions | |
| -0.234 |
- | -0.179 |
on | -0.150 |
— | -0.121 |
in | -0.117 |
Token | input |
Token ID | 5128 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
| +0.330 |
- | +0.305 |
on | +0.290 |
— | +0.277 |
, | +0.277 |
Neg logit contributions | |
advoc | -0.728 |
mathemat | -0.716 |
horizont | -0.646 |
rul | -0.621 |
destro | -0.620 |
Token | image |
Token ID | 2939 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
| +0.389 |
- | +0.332 |
on | +0.312 |
in | +0.287 |
— | +0.287 |
Neg logit contributions | |
advoc | -1.400 |
mathemat | -1.378 |
horizont | -1.270 |
rul | -1.228 |
tyr | -1.220 |
Token | to |
Token ID | 284 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
| +0.123 |
- | +0.094 |
on | +0.075 |
, | +0.063 |
— | +0.061 |
Neg logit contributions | |
advoc | -1.082 |
mathemat | -1.068 |
horizont | -0.989 |
rul | -0.968 |
tyr | -0.958 |
Token | . |
Token ID | 13 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
| +0.036 |
- | +0.026 |
on | +0.020 |
in | +0.013 |
— | +0.011 |
Neg logit contributions | |
advoc | -0.426 |
mathemat | -0.420 |
horizont | -0.392 |
rul | -0.381 |
tyr | -0.379 |
Token | Sign |
Token ID | 5865 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
| +0.663 |
- | +0.611 |
on | +0.605 |
in | +0.573 |
, | +0.565 |
Neg logit contributions | |
advoc | -1.772 |
mathemat | -1.727 |
horizont | -1.573 |
tyr | -1.528 |
rul | -1.523 |
Token | Up |
Token ID | 3205 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
| +0.263 |
on | +0.223 |
- | +0.221 |
— | +0.203 |
, | +0.202 |
Neg logit contributions | |
advoc | -1.091 |
mathemat | -1.058 |
horizont | -0.973 |
tyr | -0.942 |
rul | -0.939 |
Token | You |
Token ID | 921 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
| +0.722 |
- | +0.636 |
on | +0.608 |
in | +0.562 |
, | +0.545 |
Neg logit contributions | |
advoc | -3.041 |
mathemat | -3.008 |
horizont | -2.729 |
tyr | -2.672 |
nodd | -2.658 |
Token | will |
Token ID | 481 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
| +0.927 |
- | +0.801 |
on | +0.741 |
, | +0.660 |
in | +0.657 |
Neg logit contributions | |
advoc | -4.610 |
mathemat | -4.537 |
horizont | -4.117 |
tyr | -4.049 |
rul | -4.017 |
Token | receive |
Token ID | 3328 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
| +1.748 |
- | +1.637 |
on | +1.560 |
, | +1.477 |
in | +1.462 |
Neg logit contributions | |
advoc | -4.702 |
mathemat | -4.652 |
horizont | -4.184 |
tyr | -4.133 |
destro | -4.078 |
Token | emails |
Token ID | 7237 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
| +1.163 |
- | +1.068 |
on | +1.008 |
, | +0.953 |
— | +0.935 |
Neg logit contributions | |
advoc | -3.297 |
mathemat | -3.268 |
horizont | -2.945 |
tyr | -2.878 |
nodd | -2.870 |
Token | containing |
Token ID | 7268 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
| +1.085 |
- | +0.996 |
on | +0.901 |
, | +0.852 |
— | +0.851 |
Neg logit contributions | |
advoc | -3.502 |
mathemat | -3.449 |
horizont | -3.114 |
rul | -3.066 |
nodd | -3.058 |
Token | news |
Token ID | 1705 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
| +0.546 |
- | +0.488 |
on | +0.446 |
m | +0.415 |
in | +0.412 |
Neg logit contributions | |
advoc | -1.793 |
mathemat | -1.770 |
horizont | -1.593 |
tyr | -1.560 |
nodd | -1.550 |
Token | content |
Token ID | 2695 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
| +1.098 |
- | +1.025 |
on | +0.972 |
, | +0.913 |
in | +0.910 |
Neg logit contributions | |
advoc | -3.810 |
mathemat | -3.741 |
horizont | -3.398 |
tyr | -3.327 |
nodd | -3.325 |
Token | did |
Token ID | 750 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
| +0.116 |
- | +0.103 |
on | +0.086 |
. | +0.085 |
: | +0.084 |
Neg logit contributions | |
advoc | -0.504 |
mathemat | -0.500 |
horizont | -0.452 |
rul | -0.450 |
tyr | -0.450 |
Token | not |
Token ID | 407 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
advoc | +0.744 |
mathemat | +0.738 |
tyr | +0.674 |
horizont | +0.669 |
nodd | +0.665 |
Neg logit contributions | |
| -0.171 |
- | -0.144 |
on | -0.125 |
— | -0.116 |
: | -0.113 |
Token | issue |
Token ID | 2071 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
| +0.052 |
- | +0.046 |
on | +0.042 |
Mar | +0.038 |
in | +0.038 |
Neg logit contributions | |
mathemat | -0.166 |
advoc | -0.166 |
tyr | -0.151 |
horizont | -0.150 |
rul | -0.149 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
| +0.073 |
- | +0.061 |
on | +0.050 |
, | +0.045 |
— | +0.045 |
Neg logit contributions | |
advoc | -0.454 |
mathemat | -0.447 |
rul | -0.412 |
tyr | -0.410 |
horizont | -0.407 |
Token | total |
Token ID | 2472 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
advoc | +0.445 |
mathemat | +0.438 |
rul | +0.394 |
horizont | +0.393 |
tyr | +0.392 |
Neg logit contributions | |
| -0.159 |
- | -0.145 |
on | -0.136 |
, | -0.130 |
. | -0.129 |
Token | Loving |
Token ID | 39202 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
| +0.057 |
- | +0.049 |
on | +0.047 |
— | +0.044 |
in | +0.043 |
Neg logit contributions | |
advoc | -0.189 |
mathemat | -0.186 |
horizont | -0.169 |
rul | -0.169 |
tyr | -0.168 |
Token | v |
Token ID | 410 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
| +1.670 |
- | +1.440 |
on | +1.424 |
in | +1.319 |
— | +1.304 |
Neg logit contributions | |
advoc | -4.929 |
mathemat | -4.796 |
horizont | -4.364 |
tyr | -4.333 |
rul | -4.311 |
Token | . |
Token ID | 13 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
| +0.132 |
- | +0.091 |
on | +0.068 |
in | +0.044 |
, | +0.041 |
Neg logit contributions | |
advoc | -1.744 |
mathemat | -1.719 |
horizont | -1.582 |
nodd | -1.570 |
rul | -1.560 |
Token | Virginia |
Token ID | 6025 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
advoc | +1.478 |
mathemat | +1.440 |
horizont | +1.285 |
rul | +1.282 |
destro | +1.277 |
Neg logit contributions | |
| -0.577 |
- | -0.538 |
on | -0.521 |
— | -0.492 |
in | -0.488 |
Token | victory |
Token ID | 5373 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
| +0.119 |
- | +0.107 |
on | +0.101 |
— | +0.095 |
in | +0.095 |
Neg logit contributions | |
advoc | -0.303 |
mathemat | -0.297 |
rul | -0.271 |
tyr | -0.269 |
horizont | -0.266 |
Token | that |
Token ID | 326 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
| +0.094 |
- | +0.069 |
on | +0.056 |
— | +0.052 |
en | +0.051 |
Neg logit contributions | |
advoc | -0.577 |
mathemat | -0.567 |
horizont | -0.524 |
rul | -0.519 |
nodd | -0.518 |
Token | ological |
Token ID | 2770 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
advoc | +0.846 |
mathemat | +0.834 |
tyr | +0.725 |
horizont | +0.720 |
destro | +0.716 |
Neg logit contributions | |
| -0.412 |
- | -0.386 |
on | -0.380 |
in | -0.363 |
, | -0.357 |
Token | profile |
Token ID | 7034 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
advoc | +0.190 |
mathemat | +0.185 |
horizont | +0.166 |
tyr | +0.166 |
destro | +0.163 |
Neg logit contributions | |
| -0.060 |
- | -0.051 |
on | -0.050 |
. | -0.046 |
: | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
advoc | +0.617 |
mathemat | +0.613 |
tyr | +0.555 |
horizont | +0.555 |
destro | +0.553 |
Neg logit contributions | |
| -0.062 |
- | -0.047 |
on | -0.040 |
. | -0.030 |
, | -0.030 |
Token | N |
Token ID | 399 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
| +0.303 |
- | +0.270 |
on | +0.252 |
. | +0.237 |
, | +0.237 |
Neg logit contributions | |
advoc | -1.007 |
mathemat | -0.990 |
tyr | -0.896 |
horizont | -0.892 |
destro | -0.878 |
Token | - |
Token ID | 12 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
| +0.247 |
on | +0.189 |
- | +0.166 |
in | +0.158 |
: | +0.139 |
Neg logit contributions | |
advoc | -1.939 |
mathemat | -1.903 |
tyr | -1.740 |
horizont | -1.733 |
nodd | -1.724 |
Token | cyclop |
Token ID | 22873 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
| +0.783 |
- | +0.748 |
on | +0.738 |
, | +0.704 |
in | +0.702 |
Neg logit contributions | |
advoc | -1.331 |
mathemat | -1.288 |
tyr | -1.154 |
horizont | -1.131 |
nodd | -1.122 |
Token | rop |
Token ID | 1773 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
| +1.434 |
- | +1.293 |
on | +1.290 |
in | +1.205 |
, | +1.173 |
Neg logit contributions | |
advoc | -5.021 |
mathemat | -4.912 |
tyr | -4.471 |
horizont | -4.416 |
nodd | -4.404 |
Token | yl |
Token ID | 2645 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
| +0.385 |
- | +0.353 |
on | +0.352 |
in | +0.336 |
, | +0.323 |
Neg logit contributions | |
advoc | -1.196 |
mathemat | -1.181 |
tyr | -1.086 |
horizont | -1.051 |
nodd | -1.043 |
Token | methyl |
Token ID | 43654 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
advoc | +1.706 |
mathemat | +1.672 |
tyr | +1.527 |
horizont | +1.521 |
destro | +1.507 |
Neg logit contributions | |
| -0.332 |
on | -0.286 |
- | -0.272 |
in | -0.248 |
: | -0.247 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
| +0.153 |
on | +0.132 |
- | +0.123 |
in | +0.115 |
, | +0.113 |
Neg logit contributions | |
advoc | -0.783 |
mathemat | -0.770 |
tyr | -0.700 |
horizont | -0.695 |
destro | -0.689 |
Token | 7 |
Token ID | 22 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
| +0.604 |
- | +0.544 |
on | +0.543 |
in | +0.488 |
, | +0.479 |
Neg logit contributions | |
advoc | -2.627 |
mathemat | -2.584 |
tyr | -2.344 |
horizont | -2.327 |
destro | -2.297 |
Token | products |
Token ID | 3186 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
advoc | +0.466 |
mathemat | +0.461 |
horizont | +0.415 |
nodd | +0.407 |
rul | +0.405 |
Neg logit contributions | |
| -0.149 |
- | -0.129 |
on | -0.129 |
in | -0.120 |
— | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
mathemat | +0.804 |
advoc | +0.802 |
horizont | +0.735 |
destro | +0.722 |
rul | +0.720 |
Neg logit contributions | |
| -0.063 |
- | -0.053 |
on | -0.034 |
Mar | -0.024 |
: | -0.022 |
Token | Ann |
Token ID | 5506 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
advoc | +0.636 |
mathemat | +0.625 |
horizont | +0.567 |
tyr | +0.556 |
destro | +0.555 |
Neg logit contributions | |
| -0.146 |
- | -0.136 |
on | -0.128 |
, | -0.117 |
in | -0.113 |
Token | ounced |
Token ID | 8918 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
| +0.669 |
- | +0.634 |
on | +0.626 |
in | +0.603 |
, | +0.599 |
Neg logit contributions | |
advoc | -1.189 |
mathemat | -1.165 |
horizont | -1.027 |
nodd | -1.013 |
tyr | -1.007 |
Token | partnerships |
Token ID | 22867 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
advoc | +1.127 |
mathemat | +1.119 |
horizont | +1.021 |
rul | +1.010 |
nodd | +1.010 |
Neg logit contributions | |
| -0.132 |
- | -0.108 |
— | -0.076 |
on | -0.075 |
. | -0.072 |
Token | include |
Token ID | 2291 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
advoc | +1.047 |
mathemat | +1.039 |
horizont | +0.940 |
destro | +0.927 |
rul | +0.925 |
Neg logit contributions | |
| -0.195 |
- | -0.174 |
on | -0.143 |
en | -0.133 |
. | -0.128 |
Token | : |
Token ID | 25 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
advoc | +3.036 |
mathemat | +3.011 |
horizont | +2.721 |
nodd | +2.694 |
tyr | +2.674 |
Neg logit contributions | |
| -0.674 |
- | -0.598 |
on | -0.550 |
in | -0.491 |
. | -0.486 |
Token | Aurora |
Token ID | 22218 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
advoc | +1.801 |
mathemat | +1.780 |
horizont | +1.602 |
nodd | +1.592 |
tyr | +1.592 |
Neg logit contributions | |
| -0.407 |
- | -0.375 |
on | -0.347 |
, | -0.321 |
. | -0.311 |
Token | Information |
Token ID | 6188 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
| +0.034 |
- | +0.029 |
on | +0.029 |
in | +0.026 |
— | +0.025 |
Neg logit contributions | |
advoc | -0.148 |
mathemat | -0.147 |
horizont | -0.133 |
nodd | -0.131 |
tyr | -0.130 |
Token | Technology |
Token ID | 8987 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
advoc | +0.633 |
mathemat | +0.629 |
horizont | +0.558 |
tyr | +0.548 |
destro | +0.542 |
Neg logit contributions | |
| -0.247 |
- | -0.225 |
on | -0.218 |
in | -0.205 |
— | -0.203 |
Token | ( |
Token ID | 357 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
advoc | +0.372 |
mathemat | +0.367 |
horizont | +0.332 |
tyr | +0.325 |
nodd | +0.325 |
Neg logit contributions | |
| -0.074 |
- | -0.065 |
on | -0.060 |
in | -0.051 |
. | -0.051 |
Token | - |
Token ID | 12 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
| +0.013 |
on | +0.007 |
- | +0.004 |
in | +0.002 |
, | +0.001 |
Neg logit contributions | |
advoc | -0.309 |
mathemat | -0.307 |
horizont | -0.281 |
nodd | -0.281 |
tyr | -0.280 |
Token | old |
Token ID | 727 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
advoc | +1.043 |
mathemat | +1.017 |
horizont | +0.924 |
rul | +0.902 |
nodd | +0.884 |
Neg logit contributions | |
| -0.394 |
on | -0.376 |
- | -0.375 |
in | -0.354 |
, | -0.343 |
Token | left |
Token ID | 1364 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
advoc | +0.873 |
mathemat | +0.863 |
horizont | +0.783 |
tyr | +0.778 |
nodd | +0.771 |
Neg logit contributions | |
| -0.243 |
- | -0.217 |
on | -0.203 |
: | -0.187 |
. | -0.187 |
Token | guard |
Token ID | 4860 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
advoc | +1.605 |
mathemat | +1.579 |
tyr | +1.439 |
nodd | +1.433 |
horizont | +1.427 |
Neg logit contributions | |
| -0.423 |
on | -0.349 |
- | -0.340 |
— | -0.332 |
: | -0.325 |
Token | is |
Token ID | 318 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
advoc | +1.162 |
mathemat | +1.149 |
horizont | +1.037 |
tyr | +1.035 |
destro | +1.027 |
Neg logit contributions | |
| -0.292 |
- | -0.256 |
on | -0.237 |
: | -0.224 |
. | -0.223 |
Token | quietly |
Token ID | 12703 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
advoc | +1.123 |
mathemat | +1.107 |
tyr | +0.998 |
nodd | +0.987 |
horizont | +0.985 |
Neg logit contributions | |
| -0.244 |
- | -0.213 |
on | -0.174 |
. | -0.170 |
: | -0.169 |
Token | one |
Token ID | 530 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
advoc | +3.438 |
mathemat | +3.373 |
nodd | +3.019 |
tyr | +3.017 |
horizont | +2.993 |
Neg logit contributions | |
| -0.658 |
- | -0.572 |
: | -0.470 |
on | -0.470 |
. | -0.466 |
Token | of |
Token ID | 286 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
| +0.080 |
- | +0.064 |
on | +0.057 |
, | +0.046 |
in | +0.043 |
Neg logit contributions | |
advoc | -0.913 |
mathemat | -0.904 |
nodd | -0.823 |
horizont | -0.823 |
tyr | -0.822 |
Token | the |
Token ID | 262 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
advoc | +2.747 |
mathemat | +2.719 |
tyr | +2.488 |
horizont | +2.469 |
nodd | +2.459 |
Neg logit contributions | |
| -0.341 |
- | -0.264 |
on | -0.244 |
in | -0.195 |
: | -0.191 |
Token | best |
Token ID | 1266 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
advoc | +0.799 |
mathemat | +0.787 |
horizont | +0.703 |
nodd | +0.701 |
tyr | +0.701 |
Neg logit contributions | |
| -0.210 |
- | -0.182 |
on | -0.172 |
: | -0.162 |
— | -0.161 |
Token | in |
Token ID | 287 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
advoc | +1.148 |
mathemat | +1.133 |
horizont | +1.034 |
destro | +1.022 |
nodd | +1.018 |
Neg logit contributions | |
| -0.299 |
- | -0.248 |
on | -0.227 |
: | -0.216 |
, | -0.215 |
Token | In |
Token ID | 554 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
| +0.054 |
- | +0.052 |
on | +0.049 |
, | +0.045 |
in | +0.045 |
Neg logit contributions | |
advoc | -0.197 |
mathemat | -0.193 |
horizont | -0.175 |
tyr | -0.173 |
rul | -0.172 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
advoc | +0.611 |
mathemat | +0.605 |
tyr | +0.549 |
horizont | +0.546 |
nodd | +0.546 |
Neg logit contributions | |
| -0.109 |
- | -0.100 |
on | -0.093 |
, | -0.082 |
in | -0.081 |
Token | reversal |
Token ID | 27138 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
| +0.097 |
- | +0.092 |
on | +0.088 |
in | +0.080 |
, | +0.080 |
Neg logit contributions | |
advoc | -0.331 |
mathemat | -0.330 |
tyr | -0.298 |
rul | -0.295 |
horizont | -0.294 |
Token | of |
Token ID | 286 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
| +0.030 |
- | +0.026 |
on | +0.021 |
in | +0.016 |
, | +0.016 |
Neg logit contributions | |
advoc | -0.350 |
mathemat | -0.348 |
horizont | -0.316 |
tyr | -0.314 |
destro | -0.314 |
Token | the |
Token ID | 262 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
advoc | +0.737 |
mathemat | +0.724 |
rul | +0.648 |
destro | +0.644 |
horizont | +0.644 |
Neg logit contributions | |
| -0.174 |
- | -0.168 |
on | -0.156 |
. | -0.144 |
: | -0.142 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
advoc | +0.686 |
mathemat | +0.675 |
tyr | +0.600 |
horizont | +0.598 |
rul | +0.598 |
Neg logit contributions | |
| -0.207 |
- | -0.201 |
on | -0.189 |
. | -0.180 |
, | -0.178 |
Token | of |
Token ID | 286 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
advoc | +2.938 |
mathemat | +2.903 |
destro | +2.612 |
tyr | +2.599 |
rul | +2.595 |
Neg logit contributions | |
| -0.384 |
- | -0.342 |
on | -0.309 |
: | -0.258 |
. | -0.258 |
Token | rejection |
Token ID | 17927 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
advoc | +1.124 |
mathemat | +1.112 |
tyr | +0.984 |
horizont | +0.978 |
destro | +0.975 |
Neg logit contributions | |
| -0.381 |
- | -0.365 |
on | -0.345 |
. | -0.328 |
: | -0.323 |
Token | that |
Token ID | 326 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
advoc | +0.228 |
mathemat | +0.226 |
horizont | +0.201 |
tyr | +0.201 |
destro | +0.201 |
Neg logit contributions | |
| -0.038 |
- | -0.033 |
on | -0.030 |
: | -0.027 |
. | -0.027 |
Token | can |
Token ID | 460 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
advoc | +3.462 |
mathemat | +3.392 |
destro | +3.035 |
tyr | +3.022 |
rul | +3.016 |
Neg logit contributions | |
| -0.876 |
- | -0.833 |
on | -0.768 |
. | -0.721 |
: | -0.714 |
Token | happen |
Token ID | 1645 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
advoc | +0.619 |
mathemat | +0.612 |
destro | +0.560 |
tyr | +0.552 |
horizont | +0.547 |
Neg logit contributions | |
| -0.191 |
- | -0.183 |
on | -0.176 |
. | -0.162 |
: | -0.160 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
| +0.188 |
- | +0.177 |
on | +0.166 |
, | +0.157 |
in | +0.153 |
Neg logit contributions | |
advoc | -0.636 |
mathemat | -0.625 |
horizont | -0.561 |
tyr | -0.557 |
nodd | -0.551 |
Token | The |
Token ID | 464 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
advoc | +0.585 |
mathemat | +0.576 |
horizont | +0.513 |
tyr | +0.502 |
nodd | +0.499 |
Neg logit contributions | |
| -0.212 |
on | -0.202 |
- | -0.196 |
in | -0.190 |
, | -0.184 |
Token | New |
Token ID | 968 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
advoc | +0.294 |
mathemat | +0.293 |
horizont | +0.260 |
tyr | +0.260 |
destro | +0.258 |
Neg logit contributions | |
| -0.088 |
- | -0.082 |
on | -0.077 |
, | -0.073 |
. | -0.073 |
Token | Xbox |
Token ID | 9445 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
advoc | +1.335 |
mathemat | +1.328 |
horizont | +1.180 |
tyr | +1.172 |
nodd | +1.163 |
Neg logit contributions | |
| -0.598 |
- | -0.556 |
on | -0.547 |
in | -0.520 |
, | -0.515 |
Token | One |
Token ID | 1881 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
| +0.095 |
- | +0.082 |
on | +0.077 |
in | +0.070 |
, | +0.069 |
Neg logit contributions | |
advoc | -0.385 |
mathemat | -0.378 |
tyr | -0.341 |
nodd | -0.340 |
horizont | -0.340 |
Token | Experience |
Token ID | 16386 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
advoc | +1.011 |
mathemat | +0.994 |
tyr | +0.899 |
rul | +0.896 |
horizont | +0.893 |
Neg logit contributions | |
| -0.241 |
- | -0.205 |
on | -0.188 |
in | -0.169 |
— | -0.167 |
Token | is |
Token ID | 318 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
advoc | +3.255 |
mathemat | +3.226 |
horizont | +2.908 |
nodd | +2.897 |
tyr | +2.893 |
Neg logit contributions | |
| -0.664 |
- | -0.579 |
on | -0.495 |
in | -0.441 |
, | -0.440 |
Token | almost |
Token ID | 2048 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
advoc | +0.161 |
mathemat | +0.158 |
tyr | +0.143 |
horizont | +0.142 |
destro | +0.142 |
Neg logit contributions | |
| -0.032 |
- | -0.029 |
on | -0.023 |
— | -0.023 |
, | -0.023 |
Token | here |
Token ID | 994 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
| +0.248 |
- | +0.205 |
on | +0.168 |
— | +0.165 |
, | +0.164 |
Neg logit contributions | |
advoc | -1.361 |
mathemat | -1.350 |
tyr | -1.225 |
nodd | -1.215 |
destro | -1.210 |
Token | – |
Token ID | 784 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
advoc | +2.185 |
mathemat | +2.164 |
horizont | +1.987 |
tyr | +1.965 |
nodd | +1.956 |
Neg logit contributions | |
| -0.237 |
- | -0.186 |
on | -0.136 |
in | -0.100 |
ad | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
advoc | +1.570 |
mathemat | +1.559 |
tyr | +1.414 |
horizont | +1.407 |
nodd | +1.406 |
Neg logit contributions | |
| -0.235 |
- | -0.208 |
on | -0.157 |
: | -0.156 |
, | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
advoc | +1.924 |
mathemat | +1.864 |
horizont | +1.740 |
rul | +1.686 |
tyr | +1.650 |
Neg logit contributions | |
| -0.436 |
- | -0.387 |
on | -0.383 |
in | -0.346 |
, | -0.325 |
Token | Thanks |
Token ID | 9690 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
advoc | +2.025 |
mathemat | +1.987 |
horizont | +1.777 |
tyr | +1.736 |
nodd | +1.736 |
Neg logit contributions | |
| -0.705 |
on | -0.695 |
in | -0.655 |
- | -0.645 |
, | -0.623 |
Token | for |
Token ID | 329 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
advoc | +1.410 |
mathemat | +1.407 |
tyr | +1.271 |
horizont | +1.267 |
rul | +1.266 |
Neg logit contributions | |
| -0.178 |
- | -0.143 |
on | -0.127 |
— | -0.101 |
in | -0.098 |
Token | stopping |
Token ID | 12225 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
advoc | +0.466 |
mathemat | +0.459 |
rul | +0.416 |
tyr | +0.412 |
nodd | +0.410 |
Neg logit contributions | |
| -0.138 |
- | -0.130 |
on | -0.120 |
in | -0.114 |
, | -0.114 |
Token | by |
Token ID | 416 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
advoc | +0.844 |
mathemat | +0.840 |
tyr | +0.769 |
horizont | +0.758 |
rul | +0.758 |
Neg logit contributions | |
| -0.092 |
- | -0.071 |
on | -0.056 |
: | -0.047 |
, | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
| +0.470 |
- | +0.417 |
on | +0.363 |
in | +0.321 |
— | +0.308 |
Neg logit contributions | |
advoc | -2.789 |
mathemat | -2.760 |
tyr | -2.504 |
horizont | -2.501 |
rul | -2.489 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
advoc | +3.091 |
mathemat | +3.067 |
tyr | +2.774 |
rul | +2.756 |
nodd | +2.745 |
Neg logit contributions | |
| -0.524 |
- | -0.497 |
on | -0.426 |
, | -0.404 |
: | -0.401 |
Token | cooking |
Token ID | 10801 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
advoc | +3.437 |
mathemat | +3.352 |
nodd | +3.031 |
horizont | +3.028 |
tyr | +2.983 |
Neg logit contributions | |
| -1.101 |
- | -1.012 |
on | -0.975 |
in | -0.914 |
: | -0.911 |
Token | & |
Token ID | 1222 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
advoc | +0.370 |
mathemat | +0.365 |
horizont | +0.332 |
tyr | +0.330 |
nodd | +0.327 |
Neg logit contributions | |
| -0.078 |
- | -0.070 |
on | -0.064 |
in | -0.058 |
— | -0.056 |
Token | bon |
Token ID | 5351 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
| +0.091 |
- | +0.085 |
on | +0.080 |
, | +0.075 |
in | +0.075 |
Neg logit contributions | |
advoc | -0.306 |
mathemat | -0.298 |
horizont | -0.270 |
tyr | -0.269 |
nodd | -0.268 |
Token | app |
Token ID | 598 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
advoc | +0.554 |
mathemat | +0.541 |
tyr | +0.497 |
nodd | +0.496 |
destro | +0.494 |
Neg logit contributions | |
| -0.120 |
- | -0.111 |
on | -0.110 |
in | -0.100 |
, | -0.099 |
Token | ignment |
Token ID | 16747 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
advoc | +0.805 |
mathemat | +0.795 |
horizont | +0.715 |
rul | +0.688 |
tyr | +0.687 |
Neg logit contributions | |
| -0.390 |
- | -0.373 |
on | -0.362 |
in | -0.345 |
, | -0.344 |
Token | = |
Token ID | 796 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
advoc | +0.082 |
mathemat | +0.080 |
horizont | +0.073 |
rul | +0.071 |
tyr | +0.070 |
Neg logit contributions | |
| -0.032 |
- | -0.029 |
on | -0.029 |
in | -0.027 |
— | -0.026 |
Token | [ |
Token ID | 685 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
| +0.379 |
- | +0.312 |
on | +0.282 |
, | +0.251 |
— | +0.247 |
Neg logit contributions | |
advoc | -2.165 |
mathemat | -2.158 |
horizont | -1.972 |
rul | -1.938 |
destro | -1.930 |
Token | system |
Token ID | 10057 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
| +0.274 |
on | +0.253 |
- | +0.253 |
in | +0.238 |
, | +0.233 |
Neg logit contributions | |
advoc | -0.748 |
mathemat | -0.745 |
horizont | -0.668 |
rul | -0.648 |
tyr | -0.647 |
Token | . |
Token ID | 13 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
advoc | +0.400 |
mathemat | +0.393 |
horizont | +0.369 |
rul | +0.358 |
tyr | +0.353 |
Neg logit contributions | |
| -0.033 |
- | -0.023 |
on | -0.022 |
in | -0.015 |
, | -0.011 |
Token | draw |
Token ID | 19334 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
| +0.066 |
- | +0.063 |
on | +0.062 |
in | +0.059 |
, | +0.058 |
Neg logit contributions | |
advoc | -0.180 |
mathemat | -0.176 |
horizont | -0.160 |
rul | -0.154 |
destro | -0.153 |
Token | ing |
Token ID | 278 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
advoc | +2.262 |
mathemat | +2.215 |
horizont | +2.066 |
rul | +1.994 |
tyr | +1.951 |
Neg logit contributions | |
| -0.448 |
on | -0.396 |
- | -0.396 |
in | -0.349 |
Mar | -0.344 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
advoc | +1.009 |
mathemat | +0.991 |
horizont | +0.930 |
rul | +0.897 |
tyr | +0.882 |
Neg logit contributions | |
| -0.089 |
- | -0.061 |
on | -0.058 |
in | -0.040 |
Mar | -0.030 |
Token | String |
Token ID | 10100 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
advoc | +0.730 |
mathemat | +0.720 |
horizont | +0.651 |
rul | +0.618 |
nodd | +0.602 |
Neg logit contributions | |
| -0.381 |
on | -0.364 |
- | -0.358 |
in | -0.347 |
, | -0.335 |
Token | Al |
Token ID | 2348 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
advoc | +1.900 |
mathemat | +1.843 |
horizont | +1.685 |
rul | +1.626 |
tyr | +1.572 |
Neg logit contributions | |
| -0.743 |
- | -0.691 |
on | -0.685 |
in | -0.644 |
, | -0.628 |
Token | ignment |
Token ID | 16747 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
advoc | +0.470 |
mathemat | +0.464 |
horizont | +0.416 |
rul | +0.402 |
tyr | +0.400 |
Neg logit contributions | |
| -0.225 |
- | -0.216 |
on | -0.209 |
in | -0.199 |
, | -0.199 |
Token | � |
Token ID | 250 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
| +0.172 |
- | +0.167 |
on | +0.163 |
in | +0.158 |
, | +0.158 |
Neg logit contributions | |
advoc | -0.238 |
mathemat | -0.232 |
tyr | -0.202 |
horizont | -0.200 |
nodd | -0.200 |
Token | Down |
Token ID | 8048 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
| +0.229 |
- | +0.217 |
on | +0.209 |
in | +0.197 |
, | +0.193 |
Neg logit contributions | |
advoc | -0.851 |
mathemat | -0.836 |
horizont | -0.753 |
tyr | -0.750 |
nodd | -0.745 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
| +0.264 |
- | +0.238 |
on | +0.193 |
— | +0.183 |
: | +0.176 |
Neg logit contributions | |
advoc | -1.782 |
mathemat | -1.770 |
horizont | -1.612 |
nodd | -1.607 |
tyr | -1.604 |
Token | escal |
Token ID | 12221 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
| +0.671 |
- | +0.629 |
on | +0.591 |
, | +0.561 |
. | +0.561 |
Neg logit contributions | |
advoc | -2.164 |
mathemat | -2.139 |
horizont | -1.933 |
tyr | -1.918 |
nodd | -1.910 |
Token | ators |
Token ID | 2024 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
| +0.475 |
- | +0.456 |
on | +0.443 |
in | +0.414 |
— | +0.411 |
Neg logit contributions | |
advoc | -1.118 |
mathemat | -1.113 |
tyr | -1.000 |
horizont | -0.996 |
destro | -0.982 |
Token | , |
Token ID | 11 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
advoc | +1.013 |
mathemat | +1.002 |
horizont | +0.925 |
nodd | +0.915 |
tyr | +0.912 |
Neg logit contributions | |
| -0.124 |
- | -0.105 |
on | -0.080 |
— | -0.070 |
in | -0.063 |
Token | boys |
Token ID | 6510 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
| +0.004 |
- | +0.004 |
, | +0.003 |
: | +0.003 |
. | +0.003 |
Neg logit contributions | |
advoc | -0.022 |
mathemat | -0.022 |
horizont | -0.020 |
nodd | -0.020 |
tyr | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
| +0.072 |
- | +0.061 |
on | +0.051 |
in | +0.043 |
— | +0.042 |
Neg logit contributions | |
advoc | -0.540 |
mathemat | -0.538 |
nodd | -0.490 |
horizont | -0.487 |
rul | -0.486 |
Token | � |
Token ID | 447 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
advoc | +0.031 |
mathemat | +0.031 |
horizont | +0.028 |
nodd | +0.028 |
tyr | +0.028 |
Neg logit contributions | |
| -0.006 |
- | -0.006 |
, | -0.005 |
on | -0.005 |
: | -0.005 |
Token | � |
Token ID | 251 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
advoc | +0.282 |
mathemat | +0.274 |
tyr | +0.238 |
horizont | +0.236 |
rul | +0.236 |
Neg logit contributions | |
| -0.206 |
- | -0.200 |
on | -0.194 |
, | -0.188 |
in | -0.187 |
Token | he |
Token ID | 339 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
| +0.213 |
- | +0.198 |
on | +0.184 |
, | +0.171 |
in | +0.170 |
Neg logit contributions | |
advoc | -0.925 |
mathemat | -0.912 |
horizont | -0.824 |
tyr | -0.824 |
nodd | -0.822 |
Token | when |
Token ID | 618 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
| +0.143 |
- | +0.114 |
on | +0.074 |
Mar | +0.060 |
en | +0.059 |
Neg logit contributions | |
mathemat | -1.406 |
advoc | -1.398 |
horizont | -1.271 |
tyr | -1.268 |
nodd | -1.268 |
Token | you |
Token ID | 345 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
mathemat | +1.885 |
advoc | +1.870 |
nodd | +1.695 |
tyr | +1.687 |
rul | +1.679 |
Neg logit contributions | |
| -0.354 |
- | -0.316 |
on | -0.257 |
— | -0.244 |
: | -0.244 |
Token | are |
Token ID | 389 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
mathemat | +0.589 |
advoc | +0.579 |
destro | +0.524 |
tyr | +0.523 |
rul | +0.519 |
Neg logit contributions | |
| -0.162 |
- | -0.151 |
on | -0.139 |
: | -0.129 |
. | -0.128 |
Token | not |
Token ID | 407 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
| +0.053 |
- | +0.047 |
— | +0.037 |
: | +0.037 |
, | +0.037 |
Neg logit contributions | |
mathemat | -0.255 |
advoc | -0.254 |
tyr | -0.230 |
nodd | -0.230 |
horizont | -0.227 |
Token | playing |
Token ID | 2712 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
mathemat | +0.383 |
advoc | +0.379 |
tyr | +0.339 |
nodd | +0.337 |
horizont | +0.337 |
Neg logit contributions | |
| -0.089 |
- | -0.079 |
— | -0.065 |
: | -0.065 |
on | -0.064 |
Token | well |
Token ID | 880 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
| +0.115 |
- | +0.097 |
on | +0.077 |
m | +0.069 |
: | +0.068 |
Neg logit contributions | |
advoc | -0.715 |
mathemat | -0.714 |
tyr | -0.641 |
horizont | -0.640 |
nodd | -0.628 |
Token | , |
Token ID | 11 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
| +0.033 |
- | +0.023 |
on | +0.016 |
Mar | +0.012 |
— | +0.011 |
Neg logit contributions | |
advoc | -0.342 |
mathemat | -0.341 |
horizont | -0.311 |
nodd | -0.309 |
tyr | -0.308 |
Token | worry |
Token ID | 5490 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
| +0.197 |
- | +0.187 |
on | +0.151 |
: | +0.150 |
, | +0.146 |
Neg logit contributions | |
mathemat | -1.235 |
advoc | -1.220 |
tyr | -1.103 |
destro | -1.100 |
nodd | -1.094 |
Token | too |
Token ID | 1165 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
| +0.057 |
- | +0.048 |
on | +0.038 |
— | +0.035 |
: | +0.035 |
Neg logit contributions | |
advoc | -0.379 |
mathemat | -0.377 |
horizont | -0.341 |
tyr | -0.340 |
nodd | -0.340 |
Token | much |
Token ID | 881 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
advoc | +1.366 |
mathemat | +1.362 |
horizont | +1.219 |
nodd | +1.216 |
destro | +1.211 |
Neg logit contributions | |
| -0.298 |
- | -0.267 |
on | -0.231 |
in | -0.213 |
: | -0.213 |
Token | about |
Token ID | 546 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
advoc | +0.246 |
mathemat | +0.244 |
nodd | +0.222 |
tyr | +0.222 |
horizont | +0.222 |
Neg logit contributions | |
| -0.029 |
- | -0.023 |
on | -0.016 |
m | -0.014 |
en | -0.014 |
Token | agen |
Token ID | 11286 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
| +0.114 |
- | +0.107 |
on | +0.106 |
in | +0.102 |
— | +0.099 |
Neg logit contributions | |
advoc | -0.208 |
mathemat | -0.201 |
horizont | -0.179 |
tyr | -0.178 |
nodd | -0.176 |
Token | finished |
Token ID | 5201 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
mathemat | +1.149 |
advoc | +1.148 |
tyr | +1.029 |
horizont | +1.025 |
nodd | +1.021 |
Neg logit contributions | |
| -0.248 |
- | -0.215 |
on | -0.204 |
in | -0.183 |
. | -0.182 |
Token | close |
Token ID | 1969 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
advoc | +0.263 |
mathemat | +0.261 |
horizont | +0.234 |
tyr | +0.234 |
destro | +0.231 |
Neg logit contributions | |
| -0.062 |
- | -0.055 |
on | -0.045 |
— | -0.044 |
. | -0.044 |
Token | by |
Token ID | 416 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
| +0.149 |
- | +0.121 |
on | +0.093 |
— | +0.084 |
: | +0.082 |
Neg logit contributions | |
advoc | -1.096 |
mathemat | -1.087 |
horizont | -0.994 |
tyr | -0.980 |
rul | -0.974 |
Token | in |
Token ID | 287 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
advoc | +0.215 |
mathemat | +0.214 |
horizont | +0.195 |
tyr | +0.194 |
destro | +0.193 |
Neg logit contributions | |
| -0.030 |
- | -0.025 |
on | -0.019 |
— | -0.017 |
: | -0.016 |
Token | third |
Token ID | 2368 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
mathemat | +0.377 |
advoc | +0.377 |
horizont | +0.339 |
tyr | +0.338 |
destro | +0.336 |
Neg logit contributions | |
| -0.079 |
- | -0.070 |
on | -0.063 |
— | -0.059 |
. | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
advoc | +0.274 |
mathemat | +0.272 |
horizont | +0.250 |
tyr | +0.244 |
rul | +0.243 |
Neg logit contributions | |
| -0.061 |
- | -0.050 |
on | -0.045 |
— | -0.043 |
Mar | -0.041 |
Token | Sky |
Token ID | 5274 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
advoc | +0.110 |
mathemat | +0.108 |
horizont | +0.098 |
tyr | +0.098 |
destro | +0.097 |
Neg logit contributions | |
| -0.025 |
- | -0.024 |
on | -0.021 |
, | -0.020 |
in | -0.020 |
Token | Pro |
Token ID | 1041 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
mathemat | +0.914 |
advoc | +0.911 |
tyr | +0.815 |
destro | +0.812 |
rul | +0.805 |
Neg logit contributions | |
| -0.214 |
- | -0.188 |
on | -0.182 |
— | -0.166 |
in | -0.166 |
Token | cy |
Token ID | 948 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
advoc | +0.647 |
mathemat | +0.639 |
destro | +0.566 |
horizont | +0.560 |
tyr | +0.560 |
Neg logit contributions | |
| -0.230 |
on | -0.206 |
- | -0.205 |
— | -0.196 |
in | -0.196 |
Token | cling |
Token ID | 8493 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
advoc | +0.926 |
mathemat | +0.897 |
rul | +0.787 |
destro | +0.786 |
tyr | +0.782 |
Neg logit contributions | |
| -0.548 |
- | -0.529 |
on | -0.520 |
, | -0.502 |
in | -0.499 |
Token | - |
Token ID | 12 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
advoc | +1.057 |
mathemat | +1.044 |
destro | +0.959 |
tyr | +0.959 |
horizont | +0.956 |
Neg logit contributions | |
| -0.048 |
on | -0.014 |
- | -0.003 |
, | -0.002 |
. | +0.000 |
Token | in |
Token ID | 259 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
advoc | +0.377 |
mathemat | +0.365 |
horizont | +0.340 |
rul | +0.333 |
destro | +0.331 |
Neg logit contributions | |
| -0.065 |
on | -0.057 |
- | -0.055 |
, | -0.051 |
Mar | -0.049 |
Token | 1200 |
Token ID | 24938 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
advoc | +0.862 |
mathemat | +0.850 |
horizont | +0.759 |
tyr | +0.756 |
nodd | +0.754 |
Neg logit contributions | |
| -0.273 |
- | -0.232 |
on | -0.227 |
in | -0.210 |
. | -0.208 |
Token | W |
Token ID | 54 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
| +0.381 |
on | +0.331 |
- | +0.319 |
in | +0.307 |
, | +0.301 |
Neg logit contributions | |
advoc | -1.160 |
mathemat | -1.139 |
horizont | -1.015 |
tyr | -1.005 |
destro | -0.999 |
Token | amplifier |
Token ID | 33382 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
advoc | +0.091 |
mathemat | +0.089 |
destro | +0.080 |
tyr | +0.079 |
nodd | +0.079 |
Neg logit contributions | |
| -0.031 |
- | -0.026 |
on | -0.026 |
in | -0.024 |
: | -0.024 |
Token | powering |
Token ID | 43067 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
advoc | +0.216 |
mathemat | +0.216 |
horizont | +0.196 |
nodd | +0.195 |
destro | +0.195 |
Neg logit contributions | |
| -0.027 |
- | -0.019 |
on | -0.015 |
en | -0.012 |
Mar | -0.012 |
Token | its |
Token ID | 663 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
| +0.076 |
- | +0.061 |
on | +0.048 |
: | +0.045 |
. | +0.045 |
Neg logit contributions | |
advoc | -0.477 |
mathemat | -0.471 |
horizont | -0.430 |
tyr | -0.427 |
nodd | -0.427 |
Token | 10 |
Token ID | 838 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
advoc | +0.744 |
mathemat | +0.730 |
horizont | +0.660 |
destro | +0.657 |
nodd | +0.656 |
Neg logit contributions | |
| -0.213 |
- | -0.186 |
on | -0.172 |
: | -0.161 |
, | -0.161 |
Token | � |
Token ID | 447 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
| +0.188 |
on | +0.146 |
- | +0.137 |
in | +0.129 |
— | +0.126 |
Neg logit contributions | |
advoc | -0.966 |
mathemat | -0.955 |
horizont | -0.869 |
tyr | -0.860 |
destro | -0.856 |
Token | � |
Token ID | 251 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
advoc | +0.090 |
mathemat | +0.089 |
destro | +0.076 |
horizont | +0.076 |
tyr | +0.075 |
Neg logit contributions | |
| -0.067 |
- | -0.064 |
on | -0.063 |
in | -0.061 |
, | -0.060 |
Token | x |
Token ID | 2124 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
| +0.035 |
- | +0.030 |
on | +0.030 |
in | +0.027 |
, | +0.027 |
Neg logit contributions | |
advoc | -0.137 |
mathemat | -0.135 |
destro | -0.122 |
horizont | -0.121 |
nodd | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
advoc | +0.652 |
mathemat | +0.643 |
horizont | +0.580 |
tyr | +0.570 |
rul | +0.568 |
Neg logit contributions | |
| -0.172 |
- | -0.159 |
on | -0.150 |
, | -0.138 |
. | -0.134 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
| +0.031 |
- | +0.028 |
on | +0.027 |
in | +0.024 |
, | +0.023 |
Neg logit contributions | |
advoc | -0.141 |
mathemat | -0.137 |
horizont | -0.128 |
rul | -0.123 |
tyr | -0.122 |
Token | The |
Token ID | 464 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
| +0.142 |
on | +0.141 |
- | +0.135 |
in | +0.132 |
, | +0.127 |
Neg logit contributions | |
advoc | -0.372 |
mathemat | -0.364 |
horizont | -0.326 |
tyr | -0.314 |
nodd | -0.312 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
| +0.261 |
- | +0.242 |
on | +0.228 |
, | +0.216 |
. | +0.216 |
Neg logit contributions | |
advoc | -0.817 |
mathemat | -0.813 |
horizont | -0.725 |
tyr | -0.718 |
nodd | -0.712 |
Token | - |
Token ID | 12 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
| +0.132 |
on | +0.112 |
- | +0.110 |
in | +0.101 |
— | +0.098 |
Neg logit contributions | |
advoc | -0.571 |
mathemat | -0.556 |
horizont | -0.506 |
tyr | -0.500 |
rul | -0.499 |
Token | year |
Token ID | 1941 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
| +0.650 |
- | +0.613 |
on | +0.600 |
, | +0.562 |
in | +0.551 |
Neg logit contributions | |
advoc | -1.972 |
mathemat | -1.924 |
tyr | -1.717 |
horizont | -1.711 |
nodd | -1.702 |
Token | minimum |
Token ID | 5288 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
| +1.016 |
on | +0.890 |
- | +0.885 |
in | +0.821 |
. | +0.807 |
Neg logit contributions | |
advoc | -3.363 |
mathemat | -3.342 |
horizont | -2.992 |
nodd | -2.958 |
tyr | -2.957 |
Token | income |
Token ID | 3739 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
| +0.385 |
- | +0.331 |
on | +0.328 |
. | +0.305 |
— | +0.304 |
Neg logit contributions | |
advoc | -1.190 |
mathemat | -1.167 |
horizont | -1.051 |
tyr | -1.033 |
destro | -1.024 |
Token | experiment |
Token ID | 6306 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
| +0.049 |
- | +0.042 |
on | +0.039 |
. | +0.035 |
Mar | +0.034 |
Neg logit contributions | |
advoc | -0.225 |
mathemat | -0.220 |
horizont | -0.198 |
tyr | -0.197 |
rul | -0.197 |
Token | starting |
Token ID | 3599 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
advoc | +0.972 |
mathemat | +0.962 |
horizont | +0.866 |
destro | +0.863 |
tyr | +0.862 |
Neg logit contributions | |
| -0.156 |
- | -0.141 |
on | -0.118 |
. | -0.102 |
: | -0.099 |
Token | in |
Token ID | 287 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
| +0.215 |
- | +0.170 |
, | +0.098 |
on | +0.096 |
. | +0.094 |
Neg logit contributions | |
advoc | -2.282 |
mathemat | -2.253 |
horizont | -2.071 |
nodd | -2.050 |
rul | -2.048 |
Token | less |
Token ID | 1342 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
advoc | +0.372 |
mathemat | +0.363 |
nodd | +0.325 |
tyr | +0.324 |
horizont | +0.323 |
Neg logit contributions | |
| -0.134 |
- | -0.123 |
on | -0.110 |
, | -0.108 |
. | -0.108 |
Token | likely |
Token ID | 1884 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
| +0.144 |
- | +0.130 |
on | +0.124 |
, | +0.120 |
: | +0.120 |
Neg logit contributions | |
advoc | -0.329 |
mathemat | -0.319 |
nodd | -0.280 |
horizont | -0.280 |
tyr | -0.278 |
Token | to |
Token ID | 284 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
| +0.049 |
- | +0.043 |
on | +0.035 |
, | +0.028 |
in | +0.028 |
Neg logit contributions | |
advoc | -0.461 |
mathemat | -0.458 |
tyr | -0.416 |
destro | -0.415 |
horizont | -0.415 |
Token | go |
Token ID | 467 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
advoc | +0.120 |
mathemat | +0.119 |
tyr | +0.108 |
horizont | +0.107 |
nodd | +0.107 |
Neg logit contributions | |
| -0.035 |
- | -0.031 |
on | -0.029 |
. | -0.026 |
, | -0.026 |
Token | out |
Token ID | 503 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
advoc | +0.320 |
mathemat | +0.315 |
horizont | +0.287 |
tyr | +0.284 |
nodd | +0.284 |
Neg logit contributions | |
| -0.045 |
- | -0.037 |
: | -0.027 |
, | -0.026 |
on | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
| +0.183 |
- | +0.133 |
on | +0.092 |
: | +0.091 |
en | +0.085 |
Neg logit contributions | |
advoc | -1.737 |
mathemat | -1.692 |
horizont | -1.560 |
nodd | -1.549 |
destro | -1.531 |
Token | a |
Token ID | 257 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
| +0.432 |
- | +0.364 |
on | +0.342 |
, | +0.308 |
. | +0.305 |
Neg logit contributions | |
advoc | -2.576 |
mathemat | -2.486 |
horizont | -2.285 |
destro | -2.264 |
tyr | -2.262 |
Token | limb |
Token ID | 25035 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
| +0.370 |
- | +0.346 |
on | +0.337 |
, | +0.326 |
. | +0.326 |
Neg logit contributions | |
advoc | -0.624 |
mathemat | -0.597 |
destro | -0.530 |
tyr | -0.527 |
horizont | -0.525 |
Token | to |
Token ID | 284 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
advoc | +0.703 |
mathemat | +0.687 |
tyr | +0.625 |
horizont | +0.624 |
nodd | +0.624 |
Neg logit contributions | |
| -0.085 |
- | -0.075 |
on | -0.053 |
en | -0.050 |
Mar | -0.049 |
Token | support |
Token ID | 1104 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
| +0.309 |
- | +0.280 |
on | +0.262 |
. | +0.246 |
, | +0.245 |
Neg logit contributions | |
advoc | -0.952 |
mathemat | -0.929 |
tyr | -0.837 |
nodd | -0.831 |
horizont | -0.828 |
Token | their |
Token ID | 511 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
| +0.325 |
- | +0.294 |
on | +0.272 |
in | +0.248 |
, | +0.248 |
Neg logit contributions | |
advoc | -1.245 |
mathemat | -1.225 |
horizont | -1.112 |
tyr | -1.093 |
nodd | -1.087 |
Token | miss |
Token ID | 2051 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
| +0.562 |
- | +0.513 |
on | +0.494 |
, | +0.454 |
in | +0.454 |
Neg logit contributions | |
advoc | -1.868 |
mathemat | -1.855 |
horizont | -1.661 |
destro | -1.641 |
tyr | -1.640 |
Token | our |
Token ID | 674 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
advoc | +0.167 |
mathemat | +0.165 |
horizont | +0.149 |
tyr | +0.149 |
nodd | +0.147 |
Neg logit contributions | |
| -0.041 |
- | -0.035 |
on | -0.032 |
in | -0.031 |
, | -0.030 |
Token | top |
Token ID | 1353 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
| +0.265 |
- | +0.232 |
on | +0.221 |
, | +0.210 |
in | +0.206 |
Neg logit contributions | |
advoc | -0.866 |
mathemat | -0.843 |
horizont | -0.767 |
nodd | -0.762 |
tyr | -0.754 |
Token | stories |
Token ID | 3923 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
| +0.916 |
- | +0.824 |
on | +0.821 |
, | +0.781 |
in | +0.765 |
Neg logit contributions | |
advoc | -2.713 |
mathemat | -2.637 |
horizont | -2.400 |
tyr | -2.357 |
nodd | -2.333 |
Token | Free |
Token ID | 3232 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
| +0.094 |
- | +0.084 |
on | +0.080 |
, | +0.075 |
en | +0.073 |
Neg logit contributions | |
advoc | -0.361 |
mathemat | -0.357 |
destro | -0.322 |
tyr | -0.318 |
horizont | -0.318 |
Token | Sign |
Token ID | 5865 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
advoc | +0.534 |
mathemat | +0.524 |
horizont | +0.477 |
tyr | +0.463 |
nodd | +0.460 |
Neg logit contributions | |
| -0.181 |
- | -0.165 |
on | -0.158 |
, | -0.150 |
in | -0.149 |
Token | Up |
Token ID | 3205 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
| +0.574 |
- | +0.486 |
on | +0.479 |
, | +0.442 |
— | +0.431 |
Neg logit contributions | |
advoc | -2.427 |
mathemat | -2.382 |
horizont | -2.164 |
tyr | -2.118 |
nodd | -2.089 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
| +0.189 |
- | +0.166 |
on | +0.154 |
in | +0.139 |
— | +0.133 |
Neg logit contributions | |
advoc | -0.878 |
mathemat | -0.869 |
horizont | -0.798 |
tyr | -0.773 |
rul | -0.773 |
Token |
|
Token ID | 198 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
advoc | +0.613 |
mathemat | +0.595 |
horizont | +0.554 |
rul | +0.535 |
tyr | +0.527 |
Neg logit contributions | |
| -0.137 |
- | -0.122 |
on | -0.118 |
in | -0.106 |
, | -0.101 |
Token | The |
Token ID | 464 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
advoc | +0.876 |
mathemat | +0.849 |
horizont | +0.764 |
tyr | +0.738 |
rul | +0.734 |
Neg logit contributions | |
| -0.321 |
on | -0.317 |
- | -0.306 |
in | -0.298 |
, | -0.284 |
Token | picture |
Token ID | 4286 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
advoc | +1.193 |
mathemat | +1.171 |
horizont | +1.064 |
tyr | +1.050 |
rul | +1.044 |
Neg logit contributions | |
| -0.315 |
- | -0.280 |
on | -0.259 |
. | -0.245 |
, | -0.242 |
Token | small |
Token ID | 1402 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
| +0.214 |
- | +0.188 |
on | +0.178 |
— | +0.165 |
, | +0.165 |
Neg logit contributions | |
advoc | -0.713 |
mathemat | -0.705 |
horizont | -0.632 |
nodd | -0.625 |
tyr | -0.625 |
Token | change |
Token ID | 1487 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
| +0.098 |
on | +0.088 |
- | +0.087 |
in | +0.082 |
— | +0.082 |
Neg logit contributions | |
advoc | -0.249 |
mathemat | -0.246 |
horizont | -0.219 |
nodd | -0.215 |
tyr | -0.214 |
Token | into |
Token ID | 656 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
| +0.063 |
- | +0.053 |
on | +0.050 |
— | +0.043 |
, | +0.043 |
Neg logit contributions | |
advoc | -0.314 |
mathemat | -0.311 |
horizont | -0.282 |
nodd | -0.279 |
destro | -0.275 |
Token | circulation |
Token ID | 19133 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
advoc | +0.244 |
mathemat | +0.242 |
horizont | +0.218 |
nodd | +0.215 |
tyr | +0.214 |
Neg logit contributions | |
| -0.060 |
- | -0.051 |
on | -0.048 |
— | -0.044 |
in | -0.043 |
Token | in |
Token ID | 287 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
| +0.076 |
- | +0.053 |
on | +0.041 |
Mar | +0.032 |
m | +0.030 |
Neg logit contributions | |
mathemat | -0.644 |
advoc | -0.642 |
horizont | -0.589 |
nodd | -0.578 |
destro | -0.574 |
Token | as |
Token ID | 355 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
advoc | +0.162 |
mathemat | +0.161 |
horizont | +0.145 |
nodd | +0.144 |
tyr | +0.143 |
Neg logit contributions | |
| -0.036 |
- | -0.030 |
on | -0.028 |
in | -0.025 |
— | -0.025 |
Token | short |
Token ID | 1790 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
| +0.712 |
- | +0.629 |
on | +0.618 |
, | +0.573 |
— | +0.573 |
Neg logit contributions | |
advoc | -2.350 |
mathemat | -2.335 |
horizont | -2.077 |
nodd | -2.072 |
destro | -2.057 |
Token | a |
Token ID | 257 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
| +0.035 |
- | +0.027 |
on | +0.025 |
in | +0.021 |
, | +0.020 |
Neg logit contributions | |
advoc | -0.286 |
mathemat | -0.286 |
horizont | -0.260 |
nodd | -0.259 |
tyr | -0.257 |
Token | time |
Token ID | 640 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
| +0.027 |
- | +0.023 |
on | +0.022 |
in | +0.020 |
, | +0.019 |
Neg logit contributions | |
advoc | -0.118 |
mathemat | -0.117 |
horizont | -0.106 |
tyr | -0.105 |
nodd | -0.105 |
Token | as |
Token ID | 355 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
| +0.022 |
- | +0.016 |
on | +0.014 |
in | +0.010 |
Mar | +0.010 |
Neg logit contributions | |
mathemat | -0.187 |
advoc | -0.187 |
horizont | -0.171 |
nodd | -0.169 |
destro | -0.168 |
Token | possible |
Token ID | 1744 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
advoc | +0.444 |
mathemat | +0.437 |
horizont | +0.389 |
nodd | +0.386 |
tyr | +0.383 |
Neg logit contributions | |
| -0.157 |
- | -0.140 |
on | -0.129 |
— | -0.121 |
, | -0.120 |
Token | convincing |
Token ID | 17101 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
| +0.068 |
- | +0.060 |
on | +0.059 |
. | +0.056 |
— | +0.056 |
Neg logit contributions | |
advoc | -0.176 |
mathemat | -0.172 |
tyr | -0.153 |
horizont | -0.151 |
nodd | -0.149 |
Token | run |
Token ID | 1057 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
| +0.043 |
- | +0.037 |
on | +0.035 |
in | +0.033 |
. | +0.032 |
Neg logit contributions | |
advoc | -0.152 |
mathemat | -0.149 |
tyr | -0.133 |
destro | -0.132 |
horizont | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
| +0.146 |
- | +0.105 |
on | +0.079 |
: | +0.062 |
— | +0.062 |
Neg logit contributions | |
advoc | -1.406 |
mathemat | -1.394 |
horizont | -1.267 |
tyr | -1.258 |
destro | -1.252 |
Token | bar |
Token ID | 2318 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
| +0.001 |
- | +0.001 |
on | +0.001 |
: | +0.001 |
, | +0.001 |
Neg logit contributions | |
advoc | -0.005 |
mathemat | -0.005 |
tyr | -0.005 |
horizont | -0.005 |
destro | -0.005 |
Token | re |
Token ID | 260 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
| +0.054 |
- | +0.047 |
on | +0.046 |
— | +0.043 |
: | +0.042 |
Neg logit contributions | |
advoc | -0.258 |
mathemat | -0.255 |
tyr | -0.227 |
horizont | -0.226 |
destro | -0.224 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
| +0.783 |
on | +0.722 |
- | +0.720 |
in | +0.679 |
: | +0.675 |
Neg logit contributions | |
advoc | -2.462 |
mathemat | -2.447 |
destro | -2.198 |
nodd | -2.189 |
horizont | -2.179 |
Token | through |
Token ID | 832 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
| +0.427 |
- | +0.342 |
on | +0.274 |
— | +0.266 |
: | +0.263 |
Neg logit contributions | |
advoc | -2.558 |
mathemat | -2.522 |
horizont | -2.312 |
tyr | -2.289 |
nodd | -2.267 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
advoc | +0.374 |
mathemat | +0.371 |
horizont | +0.336 |
tyr | +0.335 |
nodd | +0.334 |
Neg logit contributions | |
| -0.054 |
- | -0.041 |
on | -0.034 |
— | -0.031 |
: | -0.029 |
Token | Tampa |
Token ID | 15528 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
| +0.170 |
- | +0.152 |
on | +0.143 |
. | +0.135 |
— | +0.135 |
Neg logit contributions | |
advoc | -0.495 |
mathemat | -0.493 |
horizont | -0.438 |
tyr | -0.433 |
nodd | -0.432 |
Token | Bay |
Token ID | 4696 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
| +0.233 |
on | +0.189 |
- | +0.189 |
in | +0.172 |
— | +0.172 |
Neg logit contributions | |
advoc | -0.944 |
mathemat | -0.935 |
horizont | -0.844 |
nodd | -0.842 |
tyr | -0.841 |
Token | Lightning |
Token ID | 12469 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
mathemat | +0.200 |
advoc | +0.199 |
tyr | +0.175 |
horizont | +0.175 |
destro | +0.173 |
Neg logit contributions | |
| -0.090 |
- | -0.080 |
on | -0.080 |
— | -0.075 |
in | -0.074 |