Token | my |
Token ID | 1820 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
Fourth | +0.078 |
ices | +0.073 |
restaurants | +0.072 |
ics | +0.071 |
site | +0.070 |
Neg logit contributions | |
bead | -0.074 |
aid | -0.066 |
can | -0.063 |
wand | -0.063 |
bracelet | -0.058 |
Token | put |
Token ID | 1234 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
bead | +0.080 |
aid | +0.075 |
can | +0.072 |
wand | +0.068 |
arl | +0.063 |
Neg logit contributions | |
Fourth | -0.098 |
restaurants | -0.091 |
site | -0.091 |
ices | -0.090 |
burgers | -0.088 |
Token | a |
Token ID | 257 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
bead | +0.048 |
can | +0.044 |
aid | +0.042 |
wand | +0.042 |
bud | +0.039 |
Neg logit contributions | |
Fourth | -0.058 |
restaurants | -0.052 |
burgers | -0.052 |
ices | -0.051 |
dogs | -0.051 |
Token | band |
Token ID | 4097 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
bead | +0.025 |
can | +0.024 |
ppy | +0.023 |
och | +0.022 |
aid | +0.021 |
Neg logit contributions | |
Fourth | -0.048 |
burgers | -0.046 |
grill | -0.044 |
site | -0.043 |
restaurants | -0.042 |
Token | - |
Token ID | 12 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
can | +0.272 |
bead | +0.266 |
wand | +0.228 |
bud | +0.226 |
och | +0.214 |
Neg logit contributions | |
Fourth | -0.237 |
ices | -0.227 |
ics | -0.217 |
oving | -0.212 |
dogs | -0.206 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Fourth | +0.032 |
ices | +0.031 |
dogs | +0.031 |
burgers | +0.030 |
restaurants | +0.030 |
Neg logit contributions | |
bead | -0.005 |
can | -0.005 |
wand | -0.004 |
bud | -0.003 |
clip | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
bead | +0.366 |
can | +0.346 |
aid | +0.294 |
wand | +0.287 |
ti | +0.287 |
Neg logit contributions | |
Fourth | -0.608 |
burgers | -0.554 |
ics | -0.553 |
ices | -0.546 |
ales | -0.536 |
Token | Kitty |
Token ID | 21168 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
bead | +0.048 |
can | +0.046 |
aid | +0.046 |
wand | +0.041 |
gently | +0.039 |
Neg logit contributions | |
Fourth | -0.073 |
restaurants | -0.068 |
ices | -0.068 |
site | -0.066 |
oving | -0.064 |
Token | 's |
Token ID | 338 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
bead | +0.087 |
aid | +0.085 |
arl | +0.078 |
can | +0.076 |
wand | +0.074 |
Neg logit contributions | |
Fourth | -0.056 |
burgers | -0.049 |
banks | -0.048 |
restaurants | -0.048 |
ices | -0.048 |
Token | knee |
Token ID | 10329 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
Fourth | +0.182 |
burgers | +0.170 |
youngest | +0.168 |
ices | +0.165 |
banks | +0.165 |
Neg logit contributions | |
aid | -0.223 |
can | -0.222 |
bead | -0.219 |
och | -0.217 |
use | -0.192 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
bead | +0.132 |
aid | +0.120 |
can | +0.110 |
wand | +0.109 |
och | +0.099 |
Neg logit contributions | |
Fourth | -0.178 |
site | -0.164 |
yard | -0.162 |
ics | -0.159 |
ices | -0.159 |
Token | Spot |
Token ID | 32565 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
bead | +0.006 |
can | +0.006 |
wand | +0.006 |
aid | +0.005 |
bracelet | +0.005 |
Neg logit contributions | |
Fourth | -0.007 |
site | -0.007 |
ices | -0.007 |
oving | -0.007 |
burgers | -0.006 |
Token | grow |
Token ID | 1663 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
aid | +0.068 |
bead | +0.068 |
can | +0.057 |
och | +0.056 |
wand | +0.053 |
Neg logit contributions | |
Fourth | -0.105 |
restaurants | -0.102 |
site | -0.100 |
ices | -0.098 |
burgers | -0.098 |
Token | ls |
Token ID | 7278 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
bead | +0.043 |
can | +0.042 |
aid | +0.041 |
wand | +0.038 |
gently | +0.036 |
Neg logit contributions | |
Fourth | -0.052 |
restaurants | -0.047 |
ices | -0.047 |
site | -0.046 |
outskirts | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
Fourth | +0.168 |
ices | +0.162 |
restaurants | +0.154 |
site | +0.154 |
burgers | +0.152 |
Neg logit contributions | |
aid | -0.124 |
bead | -0.117 |
och | -0.097 |
can | -0.097 |
bracelet | -0.092 |
Token | sn |
Token ID | 3013 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
aid | +0.014 |
bead | +0.013 |
och | +0.012 |
can | +0.011 |
arl | +0.011 |
Neg logit contributions | |
Fourth | -0.016 |
restaurants | -0.016 |
burgers | -0.016 |
site | -0.015 |
outskirts | -0.015 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
site | +0.010 |
ices | +0.009 |
ics | +0.009 |
ales | +0.009 |
burgers | +0.009 |
Neg logit contributions | |
bead | -0.012 |
wand | -0.011 |
fairy | -0.011 |
can | -0.011 |
thread | -0.011 |
Token | s |
Token ID | 82 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
bead | +0.541 |
can | +0.528 |
aid | +0.527 |
wand | +0.483 |
gently | +0.464 |
Neg logit contributions | |
Fourth | -0.447 |
restaurants | -0.405 |
ices | -0.403 |
site | -0.394 |
burgers | -0.373 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
Fourth | +0.218 |
ics | +0.213 |
ices | +0.213 |
site | +0.212 |
outskirts | +0.206 |
Neg logit contributions | |
bead | -0.171 |
aid | -0.166 |
och | -0.158 |
can | -0.155 |
wand | -0.140 |
Token | He |
Token ID | 679 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
bead | +0.025 |
aid | +0.024 |
can | +0.024 |
wand | +0.022 |
gently | +0.021 |
Neg logit contributions | |
Fourth | -0.026 |
restaurants | -0.024 |
ices | -0.024 |
site | -0.024 |
burgers | -0.023 |
Token | tries |
Token ID | 8404 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
aid | +0.038 |
bead | +0.037 |
och | +0.034 |
arl | +0.031 |
can | +0.030 |
Neg logit contributions | |
Fourth | -0.049 |
restaurants | -0.048 |
site | -0.047 |
burgers | -0.046 |
outskirts | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | +9.18e-03 |
Pos logit contributions | |
bead | +0.124 |
aid | +0.121 |
och | +0.111 |
can | +0.110 |
wand | +0.109 |
Neg logit contributions | |
restaurants | -0.146 |
site | -0.142 |
burgers | -0.142 |
Fourth | -0.140 |
ices | -0.138 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
Fourth | +0.068 |
restaurants | +0.064 |
ices | +0.064 |
site | +0.063 |
burgers | +0.061 |
Neg logit contributions | |
bead | -0.028 |
aid | -0.027 |
can | -0.026 |
wand | -0.022 |
gently | -0.020 |
Token | grow |
Token ID | 1663 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
bead | +0.020 |
aid | +0.019 |
can | +0.019 |
wand | +0.017 |
gently | +0.016 |
Neg logit contributions | |
Fourth | -0.025 |
restaurants | -0.023 |
ices | -0.023 |
site | -0.023 |
outskirts | -0.022 |
Token | l |
Token ID | 75 |
Feature activation | +7.17e-03 |
Pos logit contributions | |
bead | +0.043 |
aid | +0.041 |
can | +0.038 |
wand | +0.035 |
clip | +0.034 |
Neg logit contributions | |
Fourth | -0.064 |
ices | -0.061 |
restaurants | -0.060 |
site | -0.059 |
burgers | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
bead | +0.008 |
can | +0.008 |
aid | +0.008 |
wand | +0.007 |
gently | +0.006 |
Neg logit contributions | |
Fourth | -0.017 |
ices | -0.016 |
restaurants | -0.016 |
site | -0.016 |
ics | -0.015 |
Token | sn |
Token ID | 3013 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
bead | +0.025 |
aid | +0.024 |
can | +0.022 |
wand | +0.021 |
och | +0.020 |
Neg logit contributions | |
Fourth | -0.031 |
restaurants | -0.029 |
site | -0.028 |
burgers | -0.028 |
ices | -0.028 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Fourth | +0.005 |
oving | +0.005 |
ices | +0.005 |
site | +0.005 |
ics | +0.005 |
Neg logit contributions | |
bead | -0.006 |
can | -0.006 |
wand | -0.006 |
bud | -0.005 |
cape | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
bead | +0.412 |
can | +0.410 |
aid | +0.395 |
wand | +0.365 |
gently | +0.356 |
Neg logit contributions | |
Fourth | -0.583 |
restaurants | -0.544 |
ices | -0.519 |
site | -0.512 |
dogs | -0.508 |
Token | try |
Token ID | 1949 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
bead | +0.021 |
aid | +0.020 |
can | +0.020 |
wand | +0.018 |
och | +0.016 |
Neg logit contributions | |
Fourth | -0.030 |
restaurants | -0.028 |
ices | -0.027 |
site | -0.027 |
burgers | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
bead | +0.234 |
aid | +0.228 |
can | +0.217 |
wand | +0.194 |
och | +0.184 |
Neg logit contributions | |
Fourth | -0.311 |
restaurants | -0.301 |
ices | -0.295 |
site | -0.291 |
burgers | -0.286 |
Token | scare |
Token ID | 19437 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
bead | +0.019 |
aid | +0.018 |
can | +0.018 |
wand | +0.016 |
och | +0.016 |
Neg logit contributions | |
Fourth | -0.024 |
restaurants | -0.023 |
site | -0.022 |
outskirts | -0.021 |
ices | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
Fourth | +0.032 |
restaurants | +0.030 |
ices | +0.030 |
site | +0.029 |
burgers | +0.028 |
Neg logit contributions | |
bead | -0.030 |
aid | -0.029 |
can | -0.028 |
wand | -0.026 |
gently | -0.024 |
Token | disappointment |
Token ID | 18641 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
aid | +0.015 |
bead | +0.015 |
can | +0.014 |
wand | +0.013 |
och | +0.013 |
Neg logit contributions | |
Fourth | -0.013 |
restaurants | -0.012 |
ices | -0.012 |
site | -0.011 |
burgers | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
Fourth | +0.096 |
ices | +0.093 |
site | +0.090 |
restaurants | +0.087 |
burgers | +0.087 |
Neg logit contributions | |
aid | -0.073 |
bead | -0.073 |
can | -0.062 |
arl | -0.055 |
wand | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
bead | +0.013 |
can | +0.013 |
aid | +0.012 |
wand | +0.011 |
gently | +0.011 |
Neg logit contributions | |
Fourth | -0.017 |
restaurants | -0.016 |
ices | -0.015 |
site | -0.015 |
burgers | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
Fourth | +0.015 |
ices | +0.014 |
restaurants | +0.014 |
site | +0.014 |
Everyone | +0.013 |
Neg logit contributions | |
bead | -0.015 |
can | -0.014 |
aid | -0.014 |
wand | -0.013 |
clip | -0.012 |
Token | M |
Token ID | 44 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
Fourth | +0.015 |
ices | +0.014 |
site | +0.014 |
oving | +0.014 |
restaurants | +0.014 |
Neg logit contributions | |
bead | -0.013 |
can | -0.013 |
wand | -0.012 |
aid | -0.012 |
bud | -0.011 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Fourth | +0.062 |
ices | +0.054 |
site | +0.049 |
restaurants | +0.048 |
urg | +0.047 |
Neg logit contributions | |
bead | -0.212 |
can | -0.209 |
aid | -0.204 |
wand | -0.198 |
gently | -0.189 |
Token | on |
Token ID | 261 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
bead | +0.527 |
can | +0.515 |
aid | +0.513 |
wand | +0.469 |
gently | +0.450 |
Neg logit contributions | |
Fourth | -0.459 |
ices | -0.417 |
restaurants | -0.417 |
site | -0.406 |
oving | -0.386 |
Token | 's |
Token ID | 338 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Fourth | +0.046 |
ices | +0.043 |
site | +0.042 |
restaurants | +0.041 |
urg | +0.040 |
Neg logit contributions | |
bead | -0.035 |
aid | -0.033 |
can | -0.033 |
wand | -0.029 |
och | -0.027 |
Token | mum |
Token ID | 25682 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
Fourth | +0.203 |
ices | +0.183 |
site | +0.181 |
restaurants | +0.177 |
urg | +0.177 |
Neg logit contributions | |
aid | -0.255 |
bead | -0.254 |
can | -0.245 |
och | -0.225 |
wand | -0.215 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Fourth | +0.162 |
ices | +0.154 |
site | +0.152 |
restaurants | +0.150 |
oving | +0.146 |
Neg logit contributions | |
bead | -0.128 |
aid | -0.118 |
can | -0.110 |
wand | -0.103 |
arl | -0.100 |
Token | him |
Token ID | 683 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
bead | +0.277 |
aid | +0.262 |
can | +0.249 |
wand | +0.234 |
clip | +0.227 |
Neg logit contributions | |
Fourth | -0.214 |
ices | -0.200 |
restaurants | -0.195 |
Jon | -0.195 |
John | -0.189 |
Token | She |
Token ID | 1375 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
bead | +0.013 |
can | +0.013 |
aid | +0.013 |
wand | +0.011 |
gently | +0.011 |
Neg logit contributions | |
Fourth | -0.027 |
restaurants | -0.025 |
ices | -0.025 |
site | -0.025 |
oving | -0.024 |
Token | got |
Token ID | 1392 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
bead | +0.107 |
aid | +0.100 |
arl | +0.099 |
can | +0.097 |
och | +0.093 |
Neg logit contributions | |
Fourth | -0.115 |
ices | -0.104 |
burgers | -0.103 |
outskirts | -0.102 |
oving | -0.102 |
Token | a |
Token ID | 257 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Fourth | +0.027 |
burgers | +0.025 |
restaurants | +0.025 |
ices | +0.024 |
ics | +0.024 |
Neg logit contributions | |
bead | -0.022 |
can | -0.020 |
wand | -0.019 |
aid | -0.019 |
och | -0.018 |
Token | band |
Token ID | 4097 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
och | +0.024 |
bead | +0.022 |
can | +0.021 |
ppy | +0.021 |
aid | +0.020 |
Neg logit contributions | |
Fourth | -0.040 |
burgers | -0.035 |
preparations | -0.035 |
site | -0.034 |
ices | -0.033 |
Token | - |
Token ID | 12 |
Feature activation | -9.65e-03 |
Pos logit contributions | |
can | +0.278 |
bead | +0.274 |
wand | +0.238 |
bud | +0.232 |
och | +0.228 |
Neg logit contributions | |
Fourth | -0.206 |
ices | -0.203 |
oving | -0.193 |
ics | -0.193 |
urg | -0.183 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Fourth | +0.026 |
ices | +0.025 |
oving | +0.025 |
dogs | +0.024 |
burgers | +0.024 |
Neg logit contributions | |
can | -0.006 |
bead | -0.006 |
wand | -0.005 |
bud | -0.004 |
diary | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
bead | +0.402 |
can | +0.391 |
aid | +0.332 |
wand | +0.323 |
ti | +0.321 |
Neg logit contributions | |
Fourth | -0.537 |
ices | -0.497 |
ics | -0.495 |
burgers | -0.491 |
urg | -0.476 |
Token | put |
Token ID | 1234 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
bead | +0.010 |
can | +0.010 |
aid | +0.009 |
wand | +0.009 |
arl | +0.008 |
Neg logit contributions | |
Fourth | -0.016 |
restaurants | -0.014 |
ices | -0.014 |
burgers | -0.014 |
site | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
bead | +0.047 |
can | +0.044 |
wand | +0.042 |
aid | +0.041 |
bud | +0.041 |
Neg logit contributions | |
Fourth | -0.043 |
Jon | -0.042 |
Joey | -0.039 |
dogs | -0.039 |
icles | -0.038 |
Token | on |
Token ID | 319 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
och | +0.016 |
bead | +0.016 |
can | +0.015 |
arl | +0.014 |
irk | +0.014 |
Neg logit contributions | |
Fourth | -0.020 |
ics | -0.018 |
outskirts | -0.017 |
ices | -0.017 |
allows | -0.017 |
Token | Gig |
Token ID | 19525 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
bead | +0.042 |
aid | +0.041 |
can | +0.041 |
wand | +0.036 |
gently | +0.033 |
Neg logit contributions | |
Fourth | -0.069 |
restaurants | -0.063 |
ices | -0.063 |
site | -0.062 |
outskirts | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ices | +0.050 |
Fourth | +0.049 |
site | +0.047 |
burgers | +0.046 |
Everyone | +0.046 |
Neg logit contributions | |
bead | -0.046 |
aid | -0.041 |
can | -0.039 |
bracelet | -0.036 |
thread | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
bead | +0.049 |
aid | +0.047 |
can | +0.045 |
wand | +0.044 |
bracelet | +0.042 |
Neg logit contributions | |
Fourth | -0.043 |
ices | -0.039 |
site | -0.039 |
restaurants | -0.039 |
Everyone | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
bead | +0.026 |
aid | +0.025 |
can | +0.025 |
wand | +0.023 |
clip | +0.021 |
Neg logit contributions | |
Fourth | -0.029 |
ices | -0.027 |
restaurants | -0.027 |
site | -0.027 |
outskirts | -0.025 |
Token | Rex |
Token ID | 47389 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
bead | +0.023 |
wand | +0.021 |
can | +0.020 |
aid | +0.020 |
bracelet | +0.020 |
Neg logit contributions | |
site | -0.027 |
Fourth | -0.027 |
ices | -0.026 |
oving | -0.025 |
restaurants | -0.025 |
Token | sn |
Token ID | 3013 |
Feature activation | -6.43e-03 |
Pos logit contributions | |
aid | +0.137 |
bead | +0.137 |
och | +0.116 |
can | +0.111 |
wand | +0.106 |
Neg logit contributions | |
Fourth | -0.224 |
restaurants | -0.218 |
site | -0.215 |
burgers | -0.211 |
outskirts | -0.209 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
site | +0.010 |
ics | +0.009 |
ices | +0.009 |
Fourth | +0.009 |
oving | +0.009 |
Neg logit contributions | |
bead | -0.012 |
wand | -0.012 |
can | -0.011 |
thread | -0.011 |
needle | -0.011 |
Token | s |
Token ID | 82 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
bead | +0.570 |
can | +0.557 |
aid | +0.556 |
wand | +0.513 |
gently | +0.494 |
Neg logit contributions | |
Fourth | -0.412 |
restaurants | -0.370 |
ices | -0.368 |
site | -0.359 |
oving | -0.338 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
Fourth | +0.218 |
ics | +0.213 |
site | +0.207 |
outskirts | +0.205 |
ices | +0.204 |
Neg logit contributions | |
bead | -0.170 |
och | -0.168 |
aid | -0.164 |
can | -0.159 |
thread | -0.144 |
Token | He |
Token ID | 679 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
bead | +0.037 |
can | +0.036 |
aid | +0.036 |
wand | +0.032 |
gently | +0.031 |
Neg logit contributions | |
Fourth | -0.041 |
restaurants | -0.038 |
ices | -0.038 |
site | -0.037 |
oving | -0.036 |
Token | does |
Token ID | 857 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
aid | +0.049 |
bead | +0.048 |
och | +0.043 |
can | +0.039 |
arl | +0.038 |
Neg logit contributions | |
Fourth | -0.066 |
restaurants | -0.065 |
site | -0.064 |
burgers | -0.063 |
outskirts | -0.061 |
Token | not |
Token ID | 407 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
bead | +0.263 |
can | +0.251 |
aid | +0.251 |
wand | +0.229 |
och | +0.223 |
Neg logit contributions | |
Fourth | -0.235 |
restaurants | -0.215 |
site | -0.213 |
oving | -0.206 |
ices | -0.204 |
Token | and |
Token ID | 290 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
bead | +0.004 |
aid | +0.003 |
can | +0.003 |
och | +0.003 |
arl | +0.003 |
Neg logit contributions | |
Fourth | -0.005 |
ices | -0.005 |
burgers | -0.004 |
allows | -0.004 |
urg | -0.004 |
Token | put |
Token ID | 1234 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
bead | +0.022 |
can | +0.021 |
aid | +0.020 |
wand | +0.020 |
arl | +0.019 |
Neg logit contributions | |
Fourth | -0.026 |
restaurants | -0.025 |
burgers | -0.024 |
site | -0.023 |
outskirts | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
bead | +0.038 |
aid | +0.035 |
can | +0.034 |
bud | +0.034 |
wand | +0.033 |
Neg logit contributions | |
Fourth | -0.040 |
burgers | -0.036 |
ices | -0.036 |
restaurants | -0.036 |
dogs | -0.035 |
Token | band |
Token ID | 4097 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ppy | +0.019 |
och | +0.018 |
can | +0.018 |
bead | +0.018 |
bug | +0.016 |
Neg logit contributions | |
Fourth | -0.029 |
burgers | -0.026 |
hamb | -0.025 |
site | -0.024 |
restaurants | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
can | +0.264 |
bead | +0.259 |
bud | +0.222 |
wand | +0.219 |
och | +0.207 |
Neg logit contributions | |
Fourth | -0.219 |
ices | -0.214 |
oving | -0.203 |
ics | -0.198 |
allows | -0.185 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Fourth | +0.040 |
ices | +0.039 |
dogs | +0.038 |
burgers | +0.038 |
icles | +0.038 |
Neg logit contributions | |
can | -0.010 |
bead | -0.010 |
wand | -0.010 |
bud | -0.008 |
diary | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
bead | +0.393 |
can | +0.383 |
endant | +0.316 |
tweet | +0.316 |
wand | +0.310 |
Neg logit contributions | |
Fourth | -0.544 |
ices | -0.496 |
ics | -0.486 |
burgers | -0.483 |
ales | -0.466 |
Token | it |
Token ID | 340 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
aid | +0.041 |
bead | +0.041 |
can | +0.039 |
wand | +0.035 |
och | +0.033 |
Neg logit contributions | |
Fourth | -0.055 |
restaurants | -0.049 |
ices | -0.049 |
site | -0.049 |
burgers | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
aid | +0.016 |
bead | +0.016 |
can | +0.014 |
wand | +0.013 |
tweet | +0.013 |
Neg logit contributions | |
Fourth | -0.020 |
site | -0.018 |
ices | -0.018 |
yard | -0.018 |
outskirts | -0.018 |
Token | Mia |
Token ID | 32189 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
can | +0.026 |
bead | +0.025 |
aid | +0.023 |
gently | +0.022 |
wand | +0.021 |
Neg logit contributions | |
Fourth | -0.045 |
restaurants | -0.042 |
ices | -0.041 |
site | -0.041 |
oving | -0.040 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
bead | +0.095 |
arl | +0.092 |
aid | +0.089 |
och | +0.086 |
wand | +0.084 |
Neg logit contributions | |
Fourth | -0.090 |
ices | -0.087 |
restaurants | -0.085 |
ics | -0.082 |
site | -0.082 |
Token | quickly |
Token ID | 2952 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
Fourth | +0.243 |
ices | +0.235 |
site | +0.233 |
oving | +0.228 |
restaurants | +0.225 |
Neg logit contributions | |
bead | -0.247 |
aid | -0.241 |
can | -0.225 |
arl | -0.223 |
wand | -0.214 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
Fourth | +0.028 |
ices | +0.028 |
site | +0.028 |
oving | +0.027 |
restaurants | +0.027 |
Neg logit contributions | |
bead | -0.026 |
can | -0.024 |
aid | -0.024 |
wand | -0.023 |
arl | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
bead | +0.054 |
can | +0.052 |
aid | +0.051 |
wand | +0.046 |
gently | +0.043 |
Neg logit contributions | |
Fourth | -0.074 |
restaurants | -0.069 |
ices | -0.068 |
site | -0.067 |
burgers | -0.065 |
Token | band |
Token ID | 4097 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
aid | +0.027 |
bead | +0.027 |
arl | +0.025 |
can | +0.024 |
och | +0.023 |
Neg logit contributions | |
Fourth | -0.030 |
burgers | -0.026 |
grill | -0.025 |
site | -0.025 |
ices | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
bead | +0.184 |
can | +0.178 |
aid | +0.161 |
wand | +0.151 |
gently | +0.136 |
Neg logit contributions | |
Fourth | -0.311 |
ices | -0.294 |
site | -0.288 |
restaurants | -0.287 |
oving | -0.283 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Fourth | +0.031 |
ices | +0.030 |
dogs | +0.029 |
oving | +0.029 |
burgers | +0.029 |
Neg logit contributions | |
can | -0.005 |
bead | -0.005 |
wand | -0.004 |
bud | -0.003 |
diary | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
bead | +0.343 |
can | +0.321 |
aid | +0.313 |
wand | +0.278 |
thread | +0.245 |
Neg logit contributions | |
Fourth | -0.630 |
ices | -0.587 |
restaurants | -0.577 |
site | -0.577 |
burgers | -0.573 |
Token | helped |
Token ID | 4193 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
bead | +0.013 |
can | +0.012 |
aid | +0.012 |
wand | +0.011 |
arl | +0.010 |
Neg logit contributions | |
Fourth | -0.017 |
restaurants | -0.016 |
ices | -0.016 |
site | -0.015 |
burgers | -0.015 |
Token | Tim |
Token ID | 5045 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
aid | +0.096 |
can | +0.095 |
bead | +0.094 |
gently | +0.089 |
wand | +0.082 |
Neg logit contributions | |
Fourth | -0.135 |
restaurants | -0.122 |
ices | -0.122 |
site | -0.120 |
outskirts | -0.116 |
Token | my |
Token ID | 1820 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
Fourth | +0.144 |
ices | +0.142 |
restaurants | +0.133 |
ics | +0.130 |
oving | +0.130 |
Neg logit contributions | |
bead | -0.134 |
aid | -0.121 |
can | -0.117 |
wand | -0.114 |
ti | -0.108 |
Token | put |
Token ID | 1234 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
bead | +0.069 |
aid | +0.065 |
can | +0.064 |
wand | +0.059 |
och | +0.055 |
Neg logit contributions | |
Fourth | -0.083 |
ices | -0.078 |
restaurants | -0.077 |
site | -0.075 |
oving | -0.074 |
Token | forgive |
Token ID | 20927 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
bead | +0.128 |
aid | +0.103 |
swollen | +0.101 |
wand | +0.099 |
brace | +0.094 |
Neg logit contributions | |
Fourth | -0.243 |
restaurants | -0.218 |
ices | -0.218 |
asted | -0.210 |
asts | -0.209 |
Token | you |
Token ID | 345 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
bead | +0.245 |
aid | +0.237 |
can | +0.211 |
wand | +0.203 |
clip | +0.180 |
Neg logit contributions | |
Fourth | -0.459 |
restaurants | -0.440 |
ices | -0.417 |
site | -0.415 |
burgers | -0.415 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
bead | +0.053 |
aid | +0.053 |
can | +0.045 |
wand | +0.044 |
clip | +0.040 |
Neg logit contributions | |
Fourth | -0.083 |
restaurants | -0.075 |
ices | -0.075 |
burgers | -0.074 |
site | -0.073 |
Token | my |
Token ID | 616 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
bead | +0.028 |
aid | +0.028 |
can | +0.025 |
wand | +0.025 |
gently | +0.023 |
Neg logit contributions | |
Fourth | -0.028 |
restaurants | -0.026 |
burgers | -0.025 |
Andrew | -0.024 |
Jon | -0.024 |
Token | d |
Token ID | 288 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
bead | +0.147 |
aid | +0.145 |
can | +0.126 |
clip | +0.124 |
och | +0.121 |
Neg logit contributions | |
Fourth | -0.172 |
restaurants | -0.146 |
burgers | -0.143 |
site | -0.143 |
ices | -0.141 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Fourth | +0.105 |
ices | +0.102 |
urg | +0.102 |
ales | +0.100 |
icles | +0.097 |
Neg logit contributions | |
can | -0.041 |
bead | -0.039 |
aid | -0.031 |
will | -0.031 |
c | -0.030 |
Token | ings |
Token ID | 654 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
bead | +0.706 |
aid | +0.696 |
can | +0.682 |
wand | +0.647 |
gently | +0.639 |
Neg logit contributions | |
Fourth | -0.252 |
ices | -0.230 |
restaurants | -0.210 |
site | -0.207 |
ics | -0.194 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
Fourth | +0.318 |
burgers | +0.288 |
Everyone | +0.287 |
site | +0.285 |
restaurants | +0.283 |
Neg logit contributions | |
bead | -0.264 |
aid | -0.237 |
wand | -0.234 |
ig | -0.217 |
can | -0.211 |
Token | And |
Token ID | 843 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
bead | +0.020 |
aid | +0.019 |
wand | +0.018 |
bud | +0.017 |
pin | +0.017 |
Neg logit contributions | |
Fourth | -0.019 |
Everyone | -0.017 |
People | -0.016 |
Everybody | -0.016 |
restaurants | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
aid | +0.026 |
bead | +0.025 |
och | +0.023 |
arl | +0.022 |
swollen | +0.022 |
Neg logit contributions | |
Fourth | -0.031 |
restaurants | -0.029 |
everybody | -0.028 |
Everyone | -0.027 |
John | -0.027 |
Token | course |
Token ID | 1781 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
Fourth | +0.125 |
restaurants | +0.119 |
site | +0.115 |
burgers | +0.112 |
ices | +0.111 |
Neg logit contributions | |
bead | -0.072 |
aid | -0.071 |
can | -0.069 |
wand | -0.063 |
och | -0.057 |
Token | They |
Token ID | 1119 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
Fourth | +0.002 |
restaurants | +0.001 |
ices | +0.001 |
site | +0.001 |
burgers | +0.001 |
Neg logit contributions | |
bead | -0.003 |
aid | -0.003 |
can | -0.003 |
wand | -0.002 |
gently | -0.002 |
Token | put |
Token ID | 1234 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Fourth | +0.129 |
restaurants | +0.120 |
burgers | +0.113 |
outskirts | +0.112 |
ics | +0.109 |
Neg logit contributions | |
bead | -0.109 |
aid | -0.099 |
och | -0.094 |
wand | -0.089 |
ig | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
bead | +0.047 |
aid | +0.044 |
can | +0.043 |
bud | +0.041 |
wand | +0.040 |
Neg logit contributions | |
Fourth | -0.038 |
burgers | -0.035 |
restaurants | -0.035 |
dogs | -0.034 |
ices | -0.033 |
Token | band |
Token ID | 4097 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ppy | +0.018 |
bead | +0.018 |
can | +0.017 |
smart | +0.017 |
aid | +0.017 |
Neg logit contributions | |
Fourth | -0.027 |
burgers | -0.026 |
grill | -0.024 |
films | -0.023 |
cinema | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
bead | +0.228 |
can | +0.225 |
bud | +0.196 |
wand | +0.184 |
thread | +0.181 |
Neg logit contributions | |
Fourth | -0.231 |
ices | -0.223 |
ics | -0.220 |
oving | -0.206 |
burgers | -0.206 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Fourth | +0.051 |
ices | +0.049 |
dogs | +0.048 |
burgers | +0.048 |
ales | +0.047 |
Neg logit contributions | |
bead | -0.010 |
can | -0.009 |
wand | -0.008 |
bud | -0.007 |
diary | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
bead | +0.368 |
can | +0.325 |
aid | +0.301 |
diary | +0.291 |
wand | +0.282 |
Neg logit contributions | |
Fourth | -0.572 |
ices | -0.536 |
ics | -0.536 |
burgers | -0.533 |
icles | -0.510 |
Token | Anna |
Token ID | 11735 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
bead | +0.046 |
can | +0.046 |
aid | +0.044 |
wand | +0.041 |
gently | +0.041 |
Neg logit contributions | |
Fourth | -0.052 |
restaurants | -0.049 |
ices | -0.048 |
site | -0.046 |
oving | -0.045 |
Token | 's |
Token ID | 338 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
aid | +0.249 |
bead | +0.245 |
can | +0.216 |
arl | +0.213 |
bud | +0.211 |
Neg logit contributions | |
Fourth | -0.144 |
ices | -0.129 |
burgers | -0.122 |
asts | -0.119 |
restaurants | -0.116 |
Token | finger |
Token ID | 7660 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
Fourth | +0.181 |
urg | +0.161 |
burgers | +0.160 |
banks | +0.157 |
asts | +0.153 |
Neg logit contributions | |
bead | -0.235 |
aid | -0.234 |
can | -0.224 |
och | -0.223 |
smart | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
Fourth | +0.016 |
ices | +0.015 |
burgers | +0.014 |
allows | +0.014 |
icles | +0.014 |
Neg logit contributions | |
bead | -0.013 |
aid | -0.012 |
can | -0.011 |
och | -0.010 |
arl | -0.010 |
Token | your |
Token ID | 534 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
bead | +0.023 |
aid | +0.022 |
can | +0.022 |
wand | +0.019 |
gently | +0.018 |
Neg logit contributions | |
Fourth | -0.045 |
restaurants | -0.042 |
ices | -0.041 |
site | -0.041 |
burgers | -0.040 |
Token | fault |
Token ID | 8046 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
bead | +0.202 |
aid | +0.198 |
can | +0.190 |
wand | +0.175 |
gently | +0.168 |
Neg logit contributions | |
Fourth | -0.188 |
restaurants | -0.170 |
ices | -0.165 |
site | -0.164 |
burgers | -0.159 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Fourth | +0.121 |
restaurants | +0.112 |
ices | +0.112 |
site | +0.110 |
oving | +0.108 |
Neg logit contributions | |
bead | -0.057 |
aid | -0.055 |
can | -0.054 |
wand | -0.046 |
gently | -0.042 |
Token | my |
Token ID | 616 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
bead | +0.019 |
aid | +0.018 |
can | +0.018 |
wand | +0.016 |
gently | +0.015 |
Neg logit contributions | |
Fourth | -0.027 |
restaurants | -0.025 |
ices | -0.025 |
site | -0.025 |
burgers | -0.024 |
Token | d |
Token ID | 288 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
bead | +0.148 |
aid | +0.141 |
can | +0.136 |
wand | +0.125 |
gently | +0.120 |
Neg logit contributions | |
Fourth | -0.173 |
restaurants | -0.157 |
ices | -0.156 |
site | -0.153 |
burgers | -0.151 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Fourth | +0.110 |
ices | +0.106 |
urg | +0.105 |
ales | +0.104 |
oving | +0.101 |
Neg logit contributions | |
bead | -0.033 |
can | -0.031 |
aid | -0.026 |
wand | -0.022 |
gently | -0.021 |
Token | ings |
Token ID | 654 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
bead | +0.666 |
aid | +0.650 |
can | +0.646 |
wand | +0.606 |
gently | +0.592 |
Neg logit contributions | |
Fourth | -0.302 |
ices | -0.267 |
restaurants | -0.260 |
site | -0.254 |
oving | -0.231 |
Token | . |
Token ID | 13 |
Feature activation | +6.07e-03 |
Pos logit contributions | |
Fourth | +0.346 |
burgers | +0.321 |
site | +0.318 |
restaurants | +0.316 |
ices | +0.311 |
Neg logit contributions | |
bead | -0.254 |
aid | -0.224 |
wand | -0.213 |
ig | -0.197 |
can | -0.196 |
Token | You |
Token ID | 921 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
bead | +0.010 |
aid | +0.010 |
can | +0.009 |
wand | +0.009 |
gently | +0.008 |
Neg logit contributions | |
Fourth | -0.011 |
restaurants | -0.010 |
ices | -0.010 |
site | -0.010 |
burgers | -0.010 |
Token | didn |
Token ID | 1422 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
bead | +0.005 |
aid | +0.005 |
can | +0.005 |
wand | +0.004 |
gently | +0.004 |
Neg logit contributions | |
Fourth | -0.010 |
restaurants | -0.010 |
ices | -0.010 |
site | -0.009 |
burgers | -0.009 |
Token | 't |
Token ID | 470 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
can | +0.042 |
bead | +0.042 |
aid | +0.040 |
gently | +0.036 |
wand | +0.035 |
Neg logit contributions | |
Fourth | -0.057 |
ices | -0.055 |
restaurants | -0.054 |
site | -0.051 |
dogs | -0.051 |
Token | 'm |
Token ID | 1101 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
bead | +0.108 |
wand | +0.094 |
aid | +0.093 |
can | +0.087 |
bracelet | +0.086 |
Neg logit contributions | |
Fourth | -0.115 |
restaurants | -0.107 |
ices | -0.103 |
burgers | -0.100 |
oving | -0.099 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
bead | +0.036 |
can | +0.032 |
aid | +0.031 |
wand | +0.028 |
thread | +0.024 |
Neg logit contributions | |
Fourth | -0.078 |
restaurants | -0.073 |
site | -0.071 |
ices | -0.070 |
oving | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
bead | +0.199 |
aid | +0.192 |
wand | +0.160 |
can | +0.153 |
clip | +0.147 |
Neg logit contributions | |
Fourth | -0.320 |
ices | -0.294 |
restaurants | -0.292 |
urg | -0.287 |
site | -0.287 |
Token | my |
Token ID | 616 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
bead | +0.022 |
aid | +0.021 |
can | +0.021 |
wand | +0.019 |
gently | +0.018 |
Neg logit contributions | |
Fourth | -0.024 |
restaurants | -0.022 |
ices | -0.022 |
site | -0.022 |
burgers | -0.021 |
Token | d |
Token ID | 288 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
bead | +0.126 |
aid | +0.118 |
can | +0.117 |
wand | +0.105 |
gently | +0.099 |
Neg logit contributions | |
Fourth | -0.196 |
restaurants | -0.181 |
ices | -0.181 |
site | -0.177 |
burgers | -0.173 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Fourth | +0.118 |
ices | +0.113 |
urg | +0.110 |
site | +0.108 |
ales | +0.108 |
Neg logit contributions | |
bead | -0.029 |
can | -0.027 |
aid | -0.022 |
wand | -0.019 |
gently | -0.016 |
Token | ings |
Token ID | 654 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
bead | +0.665 |
aid | +0.649 |
can | +0.648 |
wand | +0.606 |
gently | +0.590 |
Neg logit contributions | |
Fourth | -0.309 |
ices | -0.269 |
restaurants | -0.266 |
site | -0.257 |
oving | -0.236 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
Fourth | +0.317 |
Everyone | +0.297 |
burgers | +0.295 |
ices | +0.292 |
site | +0.290 |
Neg logit contributions | |
bead | -0.292 |
aid | -0.255 |
endant | -0.241 |
wand | -0.241 |
bracelet | -0.236 |
Token | That |
Token ID | 1320 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
bead | +0.041 |
aid | +0.040 |
wand | +0.036 |
can | +0.036 |
bud | +0.035 |
Neg logit contributions | |
Fourth | -0.048 |
restaurants | -0.042 |
ices | -0.041 |
Everyone | -0.041 |
Jon | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
Fourth | +0.204 |
ices | +0.193 |
urg | +0.192 |
restaurants | +0.189 |
site | +0.188 |
Neg logit contributions | |
can | -0.121 |
bead | -0.102 |
will | -0.097 |
aid | -0.093 |
c | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
Fourth | +0.087 |
burgers | +0.080 |
restaurants | +0.076 |
site | +0.076 |
outskirts | +0.073 |
Neg logit contributions | |
bead | -0.079 |
aid | -0.074 |
can | -0.069 |
wand | -0.068 |
och | -0.068 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
bead | +0.100 |
aid | +0.096 |
can | +0.096 |
wand | +0.085 |
gently | +0.078 |
Neg logit contributions | |
Fourth | -0.141 |
restaurants | -0.130 |
ices | -0.130 |
site | -0.129 |
burgers | -0.125 |
Token | them |
Token ID | 606 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
bead | +0.021 |
aid | +0.020 |
can | +0.020 |
gently | +0.018 |
wand | +0.018 |
Neg logit contributions | |
Fourth | -0.033 |
ices | -0.031 |
restaurants | -0.030 |
oving | -0.030 |
site | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Fourth | +0.149 |
restaurants | +0.137 |
ices | +0.136 |
site | +0.132 |
burgers | +0.130 |
Neg logit contributions | |
bead | -0.136 |
can | -0.130 |
aid | -0.130 |
wand | -0.119 |
gently | -0.112 |
Token | band |
Token ID | 4097 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
bead | +0.027 |
aid | +0.025 |
ppy | +0.024 |
och | +0.024 |
can | +0.024 |
Neg logit contributions | |
Fourth | -0.040 |
burgers | -0.037 |
grill | -0.036 |
restaurants | -0.034 |
hamb | -0.034 |
Token | - |
Token ID | 12 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
bead | +0.221 |
can | +0.215 |
bud | +0.183 |
wand | +0.182 |
aid | +0.177 |
Neg logit contributions | |
Fourth | -0.263 |
ices | -0.253 |
dogs | -0.239 |
burgers | -0.238 |
ics | -0.237 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Fourth | +0.031 |
ices | +0.030 |
dogs | +0.029 |
burgers | +0.029 |
Everyone | +0.029 |
Neg logit contributions | |
bead | -0.005 |
can | -0.005 |
wand | -0.004 |
bud | -0.003 |
diary | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
bead | +0.385 |
can | +0.352 |
aid | +0.325 |
wand | +0.309 |
bud | +0.294 |
Neg logit contributions | |
Fourth | -0.563 |
ices | -0.529 |
burgers | -0.529 |
ics | -0.517 |
dogs | -0.512 |
Token | moved |
Token ID | 3888 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
bead | +0.019 |
can | +0.018 |
aid | +0.017 |
wand | +0.016 |
och | +0.015 |
Neg logit contributions | |
Fourth | -0.025 |
restaurants | -0.024 |
ices | -0.023 |
burgers | -0.023 |
site | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
bead | +0.041 |
aid | +0.037 |
can | +0.035 |
wand | +0.034 |
diary | +0.033 |
Neg logit contributions | |
Fourth | -0.031 |
Jon | -0.030 |
dogs | -0.030 |
ices | -0.029 |
burgers | -0.029 |
Token | little |
Token ID | 1310 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
aid | +0.029 |
bead | +0.026 |
can | +0.026 |
smart | +0.025 |
endant | +0.023 |
Neg logit contributions | |
Fourth | -0.033 |
site | -0.033 |
grill | -0.031 |
burgers | -0.030 |
docks | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
Fourth | +0.035 |
site | +0.034 |
burgers | +0.033 |
bank | +0.033 |
ices | +0.032 |
Neg logit contributions | |
aid | -0.029 |
arl | -0.026 |
bead | -0.024 |
och | -0.023 |
endant | -0.023 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
bead | +0.011 |
aid | +0.011 |
can | +0.010 |
wand | +0.010 |
bud | +0.009 |
Neg logit contributions | |
Fourth | -0.015 |
restaurants | -0.014 |
burgers | -0.014 |
site | -0.013 |
ices | -0.013 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
bead | +0.023 |
aid | +0.022 |
can | +0.022 |
wand | +0.020 |
clip | +0.018 |
Neg logit contributions | |
Fourth | -0.032 |
restaurants | -0.030 |
ices | -0.030 |
site | -0.029 |
burgers | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
bead | +0.145 |
can | +0.141 |
aid | +0.135 |
wand | +0.130 |
bud | +0.124 |
Neg logit contributions | |
Fourth | -0.170 |
restaurants | -0.162 |
ices | -0.157 |
burgers | -0.154 |
ics | -0.148 |
Token | band |
Token ID | 4097 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
bead | +0.033 |
can | +0.030 |
och | +0.030 |
ppy | +0.029 |
ig | +0.029 |
Neg logit contributions | |
Fourth | -0.050 |
burgers | -0.045 |
restaurants | -0.044 |
preparations | -0.041 |
Everyone | -0.041 |
Token | - |
Token ID | 12 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
bead | +0.237 |
can | +0.233 |
bud | +0.202 |
wand | +0.200 |
aid | +0.193 |
Neg logit contributions | |
Fourth | -0.247 |
ices | -0.230 |
restaurants | -0.222 |
burgers | -0.221 |
dogs | -0.218 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Fourth | +0.032 |
ices | +0.031 |
dogs | +0.031 |
Everyone | +0.030 |
burgers | +0.030 |
Neg logit contributions | |
bead | -0.006 |
can | -0.006 |
wand | -0.005 |
bud | -0.004 |
clip | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
bead | +0.375 |
can | +0.348 |
wand | +0.309 |
aid | +0.307 |
bud | +0.290 |
Neg logit contributions | |
Fourth | -0.586 |
burgers | -0.543 |
ices | -0.536 |
ics | -0.532 |
dogs | -0.525 |
Token | her |
Token ID | 607 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
Fourth | +0.108 |
restaurants | +0.101 |
burgers | +0.095 |
site | +0.094 |
urg | +0.094 |
Neg logit contributions | |
bead | -0.089 |
can | -0.083 |
aid | -0.083 |
wand | -0.074 |
clip | -0.069 |
Token | knee |
Token ID | 10329 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
bead | +0.142 |
aid | +0.133 |
och | +0.120 |
arl | +0.118 |
can | +0.118 |
Neg logit contributions | |
Fourth | -0.184 |
burgers | -0.165 |
youngest | -0.164 |
ices | -0.164 |
restaurants | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
bead | +0.128 |
aid | +0.112 |
can | +0.111 |
wand | +0.106 |
och | +0.095 |
Neg logit contributions | |
Fourth | -0.200 |
ices | -0.183 |
burgers | -0.182 |
restaurants | -0.182 |
ics | -0.180 |
Token | She |
Token ID | 1375 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
bead | +0.027 |
aid | +0.026 |
can | +0.026 |
wand | +0.024 |
gently | +0.022 |
Neg logit contributions | |
Fourth | -0.036 |
restaurants | -0.033 |
ices | -0.033 |
site | -0.033 |
outskirts | -0.031 |
Token | 'm |
Token ID | 1101 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
bead | +0.090 |
aid | +0.083 |
wand | +0.077 |
can | +0.075 |
bracelet | +0.069 |
Neg logit contributions | |
Fourth | -0.118 |
restaurants | -0.110 |
ices | -0.105 |
site | -0.103 |
burgers | -0.101 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
bead | +0.035 |
can | +0.033 |
aid | +0.033 |
wand | +0.028 |
gently | +0.026 |
Neg logit contributions | |
Fourth | -0.083 |
restaurants | -0.078 |
ices | -0.077 |
site | -0.076 |
burgers | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
bead | +0.158 |
aid | +0.152 |
can | +0.140 |
wand | +0.124 |
clip | +0.111 |
Neg logit contributions | |
Fourth | -0.352 |
restaurants | -0.331 |
ices | -0.327 |
site | -0.322 |
burgers | -0.317 |
Token | my |
Token ID | 616 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
bead | +0.019 |
can | +0.019 |
aid | +0.018 |
wand | +0.016 |
gently | +0.015 |
Neg logit contributions | |
Fourth | -0.033 |
ices | -0.031 |
restaurants | -0.031 |
site | -0.031 |
oving | -0.030 |
Token | d |
Token ID | 288 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
bead | +0.133 |
aid | +0.126 |
can | +0.115 |
wand | +0.107 |
gently | +0.106 |
Neg logit contributions | |
Fourth | -0.188 |
restaurants | -0.170 |
ices | -0.170 |
site | -0.166 |
burgers | -0.162 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Fourth | +0.111 |
ices | +0.107 |
urg | +0.105 |
ales | +0.103 |
site | +0.101 |
Neg logit contributions | |
bead | -0.033 |
can | -0.032 |
aid | -0.028 |
wand | -0.023 |
gently | -0.023 |
Token | ings |
Token ID | 654 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
bead | +0.659 |
can | +0.645 |
aid | +0.645 |
wand | +0.602 |
gently | +0.585 |
Neg logit contributions | |
Fourth | -0.312 |
ices | -0.271 |
restaurants | -0.270 |
site | -0.260 |
oving | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
Fourth | +0.367 |
burgers | +0.338 |
ices | +0.336 |
restaurants | +0.333 |
site | +0.330 |
Neg logit contributions | |
bead | -0.242 |
aid | -0.225 |
wand | -0.194 |
bracelet | -0.183 |
can | -0.182 |
Token | The |
Token ID | 383 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
bead | +0.033 |
aid | +0.032 |
can | +0.031 |
wand | +0.029 |
gently | +0.027 |
Neg logit contributions | |
Fourth | -0.043 |
restaurants | -0.039 |
ices | -0.038 |
site | -0.038 |
burgers | -0.037 |
Token | tornado |
Token ID | 33718 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
Fourth | +0.079 |
restaurants | +0.068 |
site | +0.067 |
films | +0.064 |
youngest | +0.064 |
Neg logit contributions | |
aid | -0.072 |
ppy | -0.065 |
bead | -0.064 |
gently | -0.064 |
och | -0.062 |
Token | took |
Token ID | 1718 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Fourth | +0.079 |
site | +0.072 |
restaurants | +0.072 |
ices | +0.071 |
ics | +0.071 |
Neg logit contributions | |
bead | -0.043 |
aid | -0.043 |
can | -0.034 |
och | -0.033 |
wand | -0.033 |
Token | 's |
Token ID | 338 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
bead | +0.073 |
can | +0.072 |
aid | +0.070 |
wand | +0.063 |
gently | +0.059 |
Neg logit contributions | |
Fourth | -0.114 |
restaurants | -0.106 |
ices | -0.106 |
site | -0.104 |
burgers | -0.100 |
Token | okay |
Token ID | 8788 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
Fourth | +0.266 |
restaurants | +0.233 |
burgers | +0.225 |
oving | +0.218 |
site | +0.218 |
Neg logit contributions | |
bead | -0.224 |
aid | -0.221 |
och | -0.192 |
wand | -0.192 |
can | -0.190 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
aid | +0.048 |
bead | +0.046 |
och | +0.039 |
clip | +0.038 |
wand | +0.038 |
Neg logit contributions | |
Fourth | -0.060 |
restaurants | -0.055 |
ices | -0.054 |
John | -0.053 |
Joe | -0.053 |
Token | my |
Token ID | 616 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
aid | +0.018 |
bead | +0.018 |
can | +0.017 |
wand | +0.016 |
gently | +0.015 |
Neg logit contributions | |
Fourth | -0.019 |
restaurants | -0.018 |
site | -0.017 |
burgers | -0.016 |
ices | -0.016 |
Token | d |
Token ID | 288 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
bead | +0.159 |
aid | +0.148 |
gently | +0.131 |
can | +0.128 |
wand | +0.126 |
Neg logit contributions | |
Fourth | -0.158 |
restaurants | -0.136 |
ices | -0.136 |
burgers | -0.131 |
site | -0.131 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Fourth | +0.104 |
ices | +0.100 |
urg | +0.098 |
ales | +0.097 |
asts | +0.094 |
Neg logit contributions | |
bead | -0.032 |
can | -0.031 |
aid | -0.027 |
c | -0.023 |
gently | -0.023 |
Token | ings |
Token ID | 654 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
bead | +0.695 |
aid | +0.688 |
can | +0.674 |
wand | +0.634 |
gently | +0.629 |
Neg logit contributions | |
Fourth | -0.257 |
ices | -0.233 |
site | -0.216 |
restaurants | -0.215 |
ics | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
Fourth | +0.331 |
ices | +0.302 |
burgers | +0.295 |
site | +0.292 |
restaurants | +0.291 |
Neg logit contributions | |
bead | -0.283 |
aid | -0.267 |
wand | -0.236 |
bracelet | -0.230 |
endant | -0.230 |
Token | I |
Token ID | 314 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
bead | +0.028 |
aid | +0.027 |
wand | +0.025 |
can | +0.025 |
bud | +0.024 |
Neg logit contributions | |
Fourth | -0.038 |
restaurants | -0.034 |
ices | -0.033 |
Everyone | -0.033 |
dogs | -0.032 |
Token | forgive |
Token ID | 20927 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
bead | +0.126 |
aid | +0.110 |
och | +0.098 |
wand | +0.097 |
arl | +0.093 |
Neg logit contributions | |
Fourth | -0.245 |
ices | -0.224 |
restaurants | -0.222 |
oving | -0.218 |
site | -0.212 |
Token | you |
Token ID | 345 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
bead | +0.204 |
aid | +0.197 |
can | +0.186 |
wand | +0.165 |
clip | +0.145 |
Neg logit contributions | |
Fourth | -0.474 |
restaurants | -0.448 |
ices | -0.436 |
site | -0.432 |
burgers | -0.425 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
bead | +0.020 |
can | +0.019 |
aid | +0.019 |
wand | +0.017 |
gently | +0.016 |
Neg logit contributions | |
Fourth | -0.030 |
restaurants | -0.028 |
ices | -0.028 |
site | -0.028 |
burgers | -0.027 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
can | +0.038 |
bead | +0.037 |
aid | +0.035 |
gently | +0.034 |
wand | +0.033 |
Neg logit contributions | |
Fourth | -0.027 |
restaurants | -0.024 |
site | -0.023 |
oving | -0.023 |
ices | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Fourth | +0.230 |
restaurants | +0.215 |
ices | +0.213 |
site | +0.207 |
burgers | +0.204 |
Neg logit contributions | |
bead | -0.166 |
can | -0.160 |
aid | -0.158 |
wand | -0.143 |
gently | -0.132 |
Token | band |
Token ID | 4097 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
bead | +0.031 |
can | +0.028 |
aid | +0.027 |
och | +0.025 |
ig | +0.025 |
Neg logit contributions | |
Fourth | -0.040 |
burgers | -0.037 |
restaurants | -0.036 |
grill | -0.034 |
hamb | -0.034 |
Token | - |
Token ID | 12 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
bead | +0.236 |
can | +0.230 |
aid | +0.200 |
wand | +0.198 |
bud | +0.194 |
Neg logit contributions | |
Fourth | -0.267 |
ices | -0.250 |
restaurants | -0.240 |
site | -0.238 |
burgers | -0.237 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Fourth | +0.025 |
ices | +0.024 |
dogs | +0.024 |
burgers | +0.023 |
Everyone | +0.023 |
Neg logit contributions | |
bead | -0.004 |
can | -0.004 |
wand | -0.003 |
bud | -0.003 |
clip | -0.002 |
Token | for |
Token ID | 329 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
bead | +0.371 |
can | +0.344 |
aid | +0.324 |
wand | +0.298 |
bud | +0.279 |
Neg logit contributions | |
Fourth | -0.589 |
ices | -0.543 |
burgers | -0.541 |
ics | -0.529 |
dogs | -0.526 |
Token | his |
Token ID | 465 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Fourth | +0.094 |
ices | +0.085 |
restaurants | +0.085 |
site | +0.083 |
oving | +0.080 |
Neg logit contributions | |
bead | -0.104 |
can | -0.103 |
aid | -0.101 |
wand | -0.093 |
gently | -0.090 |
Token | knee |
Token ID | 10329 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
bead | +0.032 |
aid | +0.030 |
can | +0.028 |
och | +0.028 |
arl | +0.027 |
Neg logit contributions | |
Fourth | -0.032 |
burgers | -0.029 |
restaurants | -0.028 |
youngest | -0.028 |
site | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +9.55e-03 |
Pos logit contributions | |
bead | +0.127 |
aid | +0.114 |
can | +0.108 |
wand | +0.103 |
och | +0.091 |
Neg logit contributions | |
Fourth | -0.207 |
ices | -0.191 |
restaurants | -0.188 |
site | -0.188 |
burgers | -0.187 |
Token | a |
Token ID | 257 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
bead | +0.014 |
can | +0.013 |
aid | +0.013 |
wand | +0.012 |
gently | +0.011 |
Neg logit contributions | |
Fourth | -0.020 |
restaurants | -0.019 |
ices | -0.019 |
site | -0.018 |
outskirts | -0.017 |
Token | Billy |
Token ID | 49640 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Fourth | +0.006 |
ices | +0.005 |
restaurants | +0.005 |
site | +0.005 |
oving | +0.005 |
Neg logit contributions | |
bead | -0.004 |
can | -0.004 |
wand | -0.004 |
aid | -0.004 |
bud | -0.004 |
Token | got |
Token ID | 1392 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Fourth | +0.198 |
ices | +0.187 |
restaurants | +0.187 |
site | +0.185 |
oving | +0.179 |
Neg logit contributions | |
bead | -0.151 |
aid | -0.145 |
can | -0.137 |
wand | -0.127 |
och | -0.119 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Fourth | +0.032 |
restaurants | +0.029 |
ices | +0.029 |
site | +0.029 |
oving | +0.028 |
Neg logit contributions | |
bead | -0.024 |
can | -0.023 |
aid | -0.023 |
wand | -0.020 |
gently | -0.020 |
Token | band |
Token ID | 4097 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
aid | +0.021 |
bead | +0.021 |
can | +0.019 |
och | +0.019 |
arl | +0.018 |
Neg logit contributions | |
Fourth | -0.034 |
burgers | -0.032 |
site | -0.031 |
restaurants | -0.030 |
hamb | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
bead | +0.180 |
can | +0.174 |
aid | +0.170 |
wand | +0.150 |
gently | +0.141 |
Neg logit contributions | |
Fourth | -0.318 |
restaurants | -0.296 |
ices | -0.296 |
site | -0.291 |
oving | -0.282 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Fourth | +0.032 |
ices | +0.031 |
oving | +0.030 |
dogs | +0.029 |
burgers | +0.029 |
Neg logit contributions | |
can | -0.005 |
bead | -0.005 |
wand | -0.004 |
bud | -0.003 |
diary | -0.002 |
Token | from |
Token ID | 422 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
bead | +0.360 |
can | +0.340 |
aid | +0.324 |
wand | +0.293 |
ti | +0.262 |
Neg logit contributions | |
Fourth | -0.599 |
ices | -0.560 |
site | -0.546 |
burgers | -0.545 |
restaurants | -0.543 |
Token | his |
Token ID | 465 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
Fourth | +0.088 |
restaurants | +0.081 |
site | +0.080 |
ices | +0.077 |
burgers | +0.075 |
Neg logit contributions | |
bead | -0.084 |
aid | -0.083 |
can | -0.082 |
wand | -0.073 |
och | -0.069 |
Token | pocket |
Token ID | 10000 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
aid | +0.026 |
bead | +0.024 |
can | +0.023 |
arl | +0.021 |
och | +0.021 |
Neg logit contributions | |
Fourth | -0.025 |
site | -0.024 |
youngest | -0.023 |
restaurants | -0.022 |
burgers | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +3.92e-03 |
Pos logit contributions | |
bead | +0.169 |
aid | +0.161 |
can | +0.157 |
wand | +0.138 |
tweet | +0.128 |
Neg logit contributions | |
Fourth | -0.299 |
ices | -0.290 |
site | -0.287 |
restaurants | -0.278 |
yard | -0.273 |
Token | put |
Token ID | 1234 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
bead | +0.006 |
can | +0.005 |
aid | +0.005 |
wand | +0.005 |
gently | +0.005 |
Neg logit contributions | |
Fourth | -0.008 |
restaurants | -0.008 |
ices | -0.008 |
site | -0.007 |
oving | -0.007 |
Token | have |
Token ID | 423 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
bead | +0.054 |
aid | +0.049 |
can | +0.048 |
wand | +0.046 |
och | +0.042 |
Neg logit contributions | |
Fourth | -0.080 |
restaurants | -0.073 |
ices | -0.071 |
site | -0.069 |
burgers | -0.069 |
Token | fun |
Token ID | 1257 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
bead | +0.167 |
can | +0.159 |
aid | +0.159 |
wand | +0.145 |
gently | +0.134 |
Neg logit contributions | |
Fourth | -0.248 |
restaurants | -0.232 |
site | -0.222 |
ices | -0.222 |
burgers | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
bead | +0.056 |
aid | +0.055 |
can | +0.051 |
wand | +0.046 |
och | +0.043 |
Neg logit contributions | |
Fourth | -0.085 |
restaurants | -0.080 |
site | -0.079 |
ices | -0.076 |
burgers | -0.075 |
Token | my |
Token ID | 616 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
bead | +0.021 |
aid | +0.021 |
can | +0.020 |
wand | +0.019 |
gently | +0.018 |
Neg logit contributions | |
Fourth | -0.021 |
restaurants | -0.019 |
site | -0.019 |
ices | -0.019 |
burgers | -0.018 |
Token | d |
Token ID | 288 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
bead | +0.167 |
aid | +0.163 |
can | +0.151 |
och | +0.138 |
wand | +0.138 |
Neg logit contributions | |
Fourth | -0.152 |
ices | -0.129 |
restaurants | -0.128 |
site | -0.128 |
burgers | -0.126 |
Token | arl |
Token ID | 7063 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Fourth | +0.115 |
ices | +0.109 |
urg | +0.107 |
site | +0.106 |
ales | +0.105 |
Neg logit contributions | |
bead | -0.032 |
can | -0.031 |
aid | -0.028 |
wand | -0.023 |
gently | -0.022 |
Token | ings |
Token ID | 654 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
bead | +0.653 |
aid | +0.638 |
can | +0.638 |
wand | +0.596 |
gently | +0.579 |
Neg logit contributions | |
Fourth | -0.318 |
restaurants | -0.276 |
ices | -0.275 |
site | -0.265 |
burgers | -0.244 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
Fourth | +0.341 |
restaurants | +0.315 |
site | +0.310 |
ices | +0.303 |
burgers | +0.301 |
Neg logit contributions | |
bead | -0.276 |
aid | -0.259 |
can | -0.249 |
wand | -0.241 |
gently | -0.218 |
Token | Their |
Token ID | 5334 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
Fourth | +0.018 |
ices | +0.017 |
restaurants | +0.016 |
site | +0.016 |
oving | +0.016 |
Neg logit contributions | |
bead | -0.019 |
can | -0.019 |
aid | -0.018 |
gently | -0.017 |
wand | -0.017 |
Token | mother |
Token ID | 2802 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
Fourth | +0.049 |
restaurants | +0.045 |
ices | +0.044 |
site | +0.043 |
burgers | +0.041 |
Neg logit contributions | |
bead | -0.057 |
aid | -0.056 |
can | -0.056 |
wand | -0.051 |
gently | -0.049 |
Token | asked |
Token ID | 1965 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
Fourth | +0.088 |
site | +0.087 |
ices | +0.084 |
restaurants | +0.084 |
burgers | +0.081 |
Neg logit contributions | |
bead | -0.124 |
aid | -0.114 |
can | -0.113 |
wand | -0.109 |
arl | -0.109 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
bead | +0.045 |
aid | +0.044 |
can | +0.042 |
wand | +0.039 |
arl | +0.036 |
Neg logit contributions | |
Fourth | -0.057 |
restaurants | -0.053 |
ices | -0.052 |
site | -0.051 |
outskirts | -0.050 |
Token | Lily |
Token ID | 20037 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
can | +0.023 |
bead | +0.023 |
aid | +0.023 |
gently | +0.020 |
wand | +0.019 |
Neg logit contributions | |
Fourth | -0.036 |
site | -0.035 |
ices | -0.035 |
restaurants | -0.034 |
oving | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
bead | +0.131 |
can | +0.128 |
aid | +0.125 |
wand | +0.115 |
bud | +0.107 |
Neg logit contributions | |
Fourth | -0.184 |
restaurants | -0.173 |
ices | -0.169 |
burgers | -0.164 |
site | -0.161 |
Token | band |
Token ID | 4097 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
bead | +0.034 |
aid | +0.030 |
och | +0.030 |
can | +0.029 |
ppy | +0.029 |
Neg logit contributions | |
Fourth | -0.049 |
burgers | -0.043 |
restaurants | -0.042 |
grill | -0.041 |
hamb | -0.040 |
Token | - |
Token ID | 12 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
bead | +0.218 |
can | +0.216 |
aid | +0.182 |
wand | +0.181 |
bud | +0.178 |
Neg logit contributions | |
Fourth | -0.270 |
ices | -0.249 |
restaurants | -0.240 |
ics | -0.236 |
dogs | -0.236 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Fourth | +0.033 |
ices | +0.032 |
dogs | +0.031 |
Everyone | +0.031 |
burgers | +0.030 |
Neg logit contributions | |
bead | -0.006 |
can | -0.006 |
wand | -0.004 |
bud | -0.004 |
clip | -0.002 |
Token | for |
Token ID | 329 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
bead | +0.359 |
can | +0.337 |
aid | +0.308 |
wand | +0.290 |
thread | +0.270 |
Neg logit contributions | |
Fourth | -0.613 |
ices | -0.557 |
burgers | -0.551 |
ics | -0.548 |
restaurants | -0.541 |
Token | her |
Token ID | 607 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
Fourth | +0.103 |
restaurants | +0.095 |
ices | +0.090 |
site | +0.090 |
burgers | +0.089 |
Neg logit contributions | |
bead | -0.090 |
can | -0.086 |
aid | -0.085 |
wand | -0.077 |
clip | -0.071 |
Token | knee |
Token ID | 10329 |
Feature activation | +9.26e-02 |
Pos logit contributions | |
bead | +0.143 |
aid | +0.141 |
och | +0.125 |
arl | +0.122 |
can | +0.119 |
Neg logit contributions | |
Fourth | -0.175 |
youngest | -0.157 |
restaurants | -0.150 |
burgers | -0.148 |
ices | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
bead | +0.128 |
aid | +0.114 |
can | +0.112 |
wand | +0.105 |
och | +0.095 |
Neg logit contributions | |
Fourth | -0.197 |
ices | -0.178 |
ics | -0.177 |
restaurants | -0.177 |
burgers | -0.176 |
Token | They |
Token ID | 1119 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
can | +0.020 |
bead | +0.019 |
aid | +0.018 |
gently | +0.017 |
wand | +0.016 |
Neg logit contributions | |
Fourth | -0.027 |
ices | -0.026 |
restaurants | -0.025 |
site | -0.025 |
oving | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +8.45e-03 |
Pos logit contributions | |
bead | +0.155 |
aid | +0.152 |
can | +0.133 |
wand | +0.126 |
gently | +0.114 |
Neg logit contributions | |
Fourth | -0.338 |
restaurants | -0.313 |
ices | -0.313 |
site | -0.306 |
burgers | -0.300 |
Token | be |
Token ID | 307 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
aid | +0.012 |
bead | +0.012 |
wand | +0.010 |
can | +0.010 |
och | +0.009 |
Neg logit contributions | |
Fourth | -0.018 |
restaurants | -0.017 |
burgers | -0.016 |
site | -0.016 |
ices | -0.016 |
Token | careful |
Token ID | 8161 |
Feature activation | +9.97e-02 |
Pos logit contributions | |
bead | +0.094 |
can | +0.090 |
aid | +0.086 |
wand | +0.076 |
gently | +0.068 |
Neg logit contributions | |
Fourth | -0.218 |
restaurants | -0.205 |
ices | -0.202 |
site | -0.199 |
burgers | -0.196 |
Token | ! |
Token ID | 0 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
can | +0.114 |
bead | +0.111 |
aid | +0.106 |
wand | +0.094 |
gently | +0.090 |
Neg logit contributions | |
Fourth | -0.237 |
restaurants | -0.225 |
ices | -0.221 |
site | -0.218 |
outskirts | -0.212 |
Token | Sp |
Token ID | 1338 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
Fourth | +0.166 |
restaurants | +0.156 |
ices | +0.155 |
site | +0.155 |
ics | +0.151 |
Neg logit contributions | |
can | -0.125 |
bead | -0.122 |
aid | -0.116 |
wand | -0.100 |
gently | -0.098 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Fourth | +0.015 |
restaurants | +0.014 |
outskirts | +0.013 |
burgers | +0.013 |
Andrew | +0.013 |
Neg logit contributions | |
bead | -0.018 |
aid | -0.017 |
can | -0.016 |
arl | -0.015 |
wand | -0.015 |
Token | food |
Token ID | 2057 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
Fourth | +0.596 |
outskirts | +0.523 |
ices | +0.522 |
site | +0.516 |
restaurants | +0.515 |
Neg logit contributions | |
can | -0.582 |
bead | -0.533 |
aid | -0.523 |
wand | -0.473 |
will | -0.471 |
Token | can |
Token ID | 460 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Fourth | +0.147 |
restaurants | +0.139 |
ices | +0.137 |
site | +0.136 |
burgers | +0.133 |
Neg logit contributions | |
bead | -0.052 |
aid | -0.050 |
can | -0.046 |
wand | -0.040 |
gently | -0.036 |
Token | make |
Token ID | 787 |
Feature activation | -6.79e-03 |
Pos logit contributions | |
can | +0.288 |
bead | +0.264 |
aid | +0.245 |
gently | +0.236 |
c | +0.235 |
Neg logit contributions | |
ices | -0.497 |
Fourth | -0.485 |
restaurants | -0.468 |
site | -0.462 |
oving | -0.461 |
Token | your |
Token ID | 534 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Fourth | +0.017 |
ices | +0.017 |
site | +0.016 |
dogs | +0.016 |
outskirts | +0.016 |
Neg logit contributions | |
can | -0.007 |
bead | -0.006 |
better | -0.006 |
aid | -0.006 |
gently | -0.005 |
Token | tum |
Token ID | 11814 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
can | +0.186 |
bead | +0.176 |
aid | +0.167 |
wand | +0.164 |
c | +0.160 |
Neg logit contributions | |
Fourth | -0.184 |
ices | -0.175 |
site | -0.170 |
oving | -0.169 |
restaurants | -0.164 |
Token | new |
Token ID | 649 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
bead | +0.188 |
aid | +0.181 |
can | +0.180 |
wand | +0.157 |
gently | +0.144 |
Neg logit contributions | |
Fourth | -0.350 |
restaurants | -0.329 |
ices | -0.326 |
site | -0.321 |
burgers | -0.312 |
Token | things |
Token ID | 1243 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
bead | +0.035 |
can | +0.035 |
aid | +0.034 |
wand | +0.031 |
gently | +0.030 |
Neg logit contributions | |
Fourth | -0.042 |
restaurants | -0.038 |
ices | -0.038 |
site | -0.037 |
outskirts | -0.036 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
Fourth | +0.035 |
site | +0.033 |
restaurants | +0.033 |
burgers | +0.032 |
ics | +0.032 |
Neg logit contributions | |
aid | -0.026 |
bead | -0.026 |
wand | -0.022 |
diary | -0.021 |
can | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
Fourth | +0.027 |
restaurants | +0.025 |
ices | +0.025 |
site | +0.024 |
burgers | +0.024 |
Neg logit contributions | |
bead | -0.011 |
aid | -0.011 |
can | -0.010 |
wand | -0.009 |
gently | -0.008 |
Token | Sp |
Token ID | 1338 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
bead | +0.010 |
aid | +0.010 |
can | +0.010 |
wand | +0.009 |
gently | +0.008 |
Neg logit contributions | |
Fourth | -0.013 |
restaurants | -0.012 |
ices | -0.012 |
site | -0.011 |
burgers | -0.011 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Fourth | +0.020 |
restaurants | +0.018 |
outskirts | +0.018 |
youngest | +0.017 |
Jon | +0.017 |
Neg logit contributions | |
bead | -0.022 |
aid | -0.022 |
can | -0.021 |
arl | -0.020 |
ppy | -0.019 |
Token | food |
Token ID | 2057 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
Fourth | +0.721 |
restaurants | +0.669 |
ices | +0.665 |
site | +0.655 |
outskirts | +0.636 |
Neg logit contributions | |
bead | -0.413 |
can | -0.405 |
aid | -0.396 |
wand | -0.348 |
gently | -0.328 |
Token | is |
Token ID | 318 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
Fourth | +0.152 |
restaurants | +0.144 |
site | +0.143 |
burgers | +0.141 |
ices | +0.139 |
Neg logit contributions | |
aid | -0.069 |
bead | -0.067 |
wand | -0.052 |
och | -0.049 |
bracelet | -0.049 |
Token | good |
Token ID | 922 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
bead | +0.043 |
aid | +0.043 |
can | +0.039 |
och | +0.036 |
wand | +0.036 |
Neg logit contributions | |
Fourth | -0.054 |
burgers | -0.050 |
restaurants | -0.049 |
site | -0.048 |
ices | -0.046 |
Token | for |
Token ID | 329 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
bead | +0.125 |
aid | +0.121 |
can | +0.115 |
wand | +0.102 |
gently | +0.097 |
Neg logit contributions | |
Fourth | -0.220 |
restaurants | -0.206 |
ices | -0.204 |
site | -0.200 |
burgers | -0.198 |
Token | you |
Token ID | 345 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
Fourth | +0.155 |
ices | +0.148 |
restaurants | +0.143 |
site | +0.142 |
outskirts | +0.140 |
Neg logit contributions | |
can | -0.071 |
bead | -0.071 |
aid | -0.066 |
wand | -0.059 |
gently | -0.058 |
Token | ' |
Token ID | 705 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
bead | +0.095 |
aid | +0.094 |
can | +0.087 |
wand | +0.081 |
arl | +0.080 |
Neg logit contributions | |
Fourth | -0.106 |
restaurants | -0.103 |
site | -0.097 |
ices | -0.097 |
burgers | -0.095 |
Token | accept |
Token ID | 13635 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
bead | +0.086 |
can | +0.083 |
wand | +0.080 |
aid | +0.079 |
gently | +0.072 |
Neg logit contributions | |
Fourth | -0.097 |
restaurants | -0.090 |
ices | -0.089 |
site | -0.085 |
dogs | -0.084 |
Token | ' |
Token ID | 6 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
Fourth | +0.049 |
restaurants | +0.045 |
ices | +0.045 |
site | +0.044 |
burgers | +0.042 |
Neg logit contributions | |
bead | -0.037 |
can | -0.036 |
aid | -0.036 |
wand | -0.032 |
gently | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Fourth | +0.111 |
restaurants | +0.102 |
ices | +0.101 |
site | +0.100 |
outskirts | +0.097 |
Neg logit contributions | |
bead | -0.072 |
aid | -0.068 |
can | -0.065 |
wand | -0.060 |
gently | -0.054 |
Token | ' |
Token ID | 705 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
bead | +0.019 |
aid | +0.018 |
can | +0.016 |
wand | +0.016 |
och | +0.015 |
Neg logit contributions | |
Fourth | -0.021 |
restaurants | -0.020 |
site | -0.019 |
ices | -0.018 |
outskirts | -0.018 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
bead | +0.088 |
can | +0.084 |
wand | +0.082 |
aid | +0.079 |
bud | +0.072 |
Neg logit contributions | |
Fourth | -0.093 |
ices | -0.085 |
restaurants | -0.085 |
site | -0.080 |
dogs | -0.080 |
Token | '. |
Token ID | 4458 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
Fourth | +0.586 |
restaurants | +0.537 |
ices | +0.533 |
site | +0.523 |
burgers | +0.501 |
Neg logit contributions | |
bead | -0.544 |
can | -0.529 |
aid | -0.527 |
wand | -0.479 |
gently | -0.458 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Fourth | +0.124 |
ices | +0.109 |
restaurants | +0.108 |
Everyone | +0.106 |
outskirts | +0.104 |
Neg logit contributions | |
bead | -0.169 |
aid | -0.164 |
can | -0.162 |
wand | -0.155 |
bud | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
Fourth | +0.223 |
restaurants | +0.216 |
ices | +0.208 |
site | +0.202 |
outskirts | +0.195 |
Neg logit contributions | |
aid | -0.168 |
bead | -0.161 |
arl | -0.146 |
can | -0.139 |
och | -0.136 |
Token | she |
Token ID | 673 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
bead | +0.028 |
aid | +0.027 |
can | +0.026 |
wand | +0.024 |
arl | +0.023 |
Neg logit contributions | |
Fourth | -0.039 |
restaurants | -0.037 |
ices | -0.034 |
site | -0.034 |
burgers | -0.034 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
bead | +0.098 |
aid | +0.098 |
can | +0.090 |
wand | +0.083 |
arl | +0.080 |
Neg logit contributions | |
Fourth | -0.124 |
restaurants | -0.117 |
ices | -0.115 |
site | -0.113 |
urg | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
Fourth | +0.166 |
ices | +0.163 |
restaurants | +0.153 |
site | +0.151 |
burgers | +0.146 |
Neg logit contributions | |
bead | -0.114 |
aid | -0.108 |
can | -0.103 |
wand | -0.096 |
och | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
bead | +0.050 |
aid | +0.049 |
can | +0.048 |
wand | +0.045 |
ig | +0.041 |
Neg logit contributions | |
Fourth | -0.052 |
restaurants | -0.048 |
site | -0.048 |
ices | -0.047 |
outskirts | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
bead | +0.027 |
aid | +0.026 |
can | +0.026 |
wand | +0.024 |
clip | +0.022 |
Neg logit contributions | |
Fourth | -0.031 |
ices | -0.029 |
restaurants | -0.029 |
site | -0.029 |
outskirts | -0.027 |
Token | " |
Token ID | 1 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
bead | +0.021 |
can | +0.020 |
wand | +0.020 |
aid | +0.020 |
thread | +0.018 |
Neg logit contributions | |
site | -0.031 |
Fourth | -0.031 |
ices | -0.030 |
restaurants | -0.028 |
outskirts | -0.028 |
Token | Sp |
Token ID | 4561 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
bead | +0.110 |
can | +0.107 |
aid | +0.105 |
wand | +0.097 |
gently | +0.090 |
Neg logit contributions | |
Fourth | -0.155 |
restaurants | -0.143 |
ices | -0.143 |
site | -0.140 |
burgers | -0.136 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
bead | +0.171 |
can | +0.168 |
aid | +0.168 |
wand | +0.157 |
gently | +0.153 |
Neg logit contributions | |
Fourth | -0.062 |
restaurants | -0.051 |
ices | -0.049 |
site | -0.048 |
outskirts | -0.044 |
Token | means |
Token ID | 1724 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
Fourth | +0.620 |
restaurants | +0.571 |
ices | +0.567 |
site | +0.557 |
burgers | +0.534 |
Neg logit contributions | |
bead | -0.512 |
can | -0.498 |
aid | -0.495 |
wand | -0.446 |
gently | -0.426 |
Token | it |
Token ID | 340 |
Feature activation | +6.60e-03 |
Pos logit contributions | |
Fourth | +0.172 |
restaurants | +0.159 |
ices | +0.155 |
site | +0.154 |
burgers | +0.151 |
Neg logit contributions | |
bead | -0.168 |
aid | -0.165 |
can | -0.160 |
wand | -0.148 |
gently | -0.141 |
Token | makes |
Token ID | 1838 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
bead | +0.008 |
aid | +0.007 |
can | +0.007 |
wand | +0.006 |
gently | +0.006 |
Neg logit contributions | |
Fourth | -0.016 |
restaurants | -0.015 |
ices | -0.014 |
site | -0.014 |
burgers | -0.014 |
Token | your |
Token ID | 534 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Fourth | +0.012 |
ices | +0.011 |
restaurants | +0.011 |
site | +0.011 |
oving | +0.010 |
Neg logit contributions | |
can | -0.007 |
bead | -0.007 |
aid | -0.006 |
gently | -0.006 |
wand | -0.006 |
Token | mouth |
Token ID | 5422 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
bead | +0.171 |
can | +0.167 |
aid | +0.165 |
wand | +0.150 |
gently | +0.143 |
Neg logit contributions | |
Fourth | -0.200 |
restaurants | -0.184 |
ices | -0.183 |
site | -0.179 |
oving | -0.172 |
Token | something |
Token ID | 1223 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
Fourth | +0.118 |
ices | +0.107 |
restaurants | +0.107 |
site | +0.104 |
oving | +0.103 |
Neg logit contributions | |
bead | -0.079 |
can | -0.079 |
aid | -0.078 |
wand | -0.069 |
gently | -0.068 |
Token | y |
Token ID | 331 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
Fourth | +0.181 |
site | +0.169 |
burgers | +0.167 |
restaurants | +0.166 |
ices | +0.160 |
Neg logit contributions | |
bead | -0.141 |
aid | -0.140 |
can | -0.126 |
arl | -0.117 |
wand | -0.115 |
Token | ummy |
Token ID | 13513 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
Fourth | +0.047 |
restaurants | +0.042 |
ices | +0.039 |
site | +0.039 |
outskirts | +0.037 |
Neg logit contributions | |
bead | -0.099 |
can | -0.097 |
aid | -0.094 |
wand | -0.089 |
bud | -0.089 |
Token | - |
Token ID | 12 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
Fourth | +0.497 |
restaurants | +0.473 |
burgers | +0.464 |
ices | +0.462 |
site | +0.461 |
Neg logit contributions | |
aid | -0.308 |
bead | -0.302 |
can | -0.270 |
wand | -0.243 |
och | -0.233 |
Token | sp |
Token ID | 2777 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
Fourth | +0.026 |
restaurants | +0.024 |
ices | +0.023 |
site | +0.023 |
urg | +0.022 |
Neg logit contributions | |
aid | -0.027 |
bead | -0.026 |
can | -0.026 |
gently | -0.023 |
wand | -0.023 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
restaurants | +0.018 |
Fourth | +0.018 |
burgers | +0.015 |
outskirts | +0.015 |
site | +0.014 |
Neg logit contributions | |
aid | -0.035 |
bead | -0.034 |
can | -0.033 |
och | -0.031 |
gently | -0.031 |
Token | inside |
Token ID | 2641 |
Feature activation | +4.45e-03 |
Pos logit contributions | |
Fourth | +0.745 |
restaurants | +0.689 |
ices | +0.682 |
site | +0.670 |
oving | +0.666 |
Neg logit contributions | |
can | -0.391 |
bead | -0.380 |
aid | -0.362 |
wand | -0.322 |
gently | -0.304 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
can | +0.004 |
bead | +0.004 |
aid | +0.004 |
wand | +0.003 |
gently | +0.003 |
Neg logit contributions | |
Fourth | -0.011 |
ices | -0.011 |
restaurants | -0.011 |
site | -0.010 |
oving | -0.010 |
Token | The |
Token ID | 383 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
can | +0.019 |
bead | +0.019 |
aid | +0.018 |
gently | +0.016 |
wand | +0.016 |
Neg logit contributions | |
Fourth | -0.025 |
ices | -0.023 |
oving | -0.023 |
restaurants | -0.023 |
site | -0.022 |
Token | chicken |
Token ID | 9015 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
Fourth | +0.094 |
restaurants | +0.086 |
site | +0.084 |
burgers | +0.084 |
ices | +0.083 |
Neg logit contributions | |
bead | -0.073 |
aid | -0.071 |
can | -0.069 |
wand | -0.060 |
och | -0.060 |
Token | was |
Token ID | 373 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
Fourth | +0.201 |
restaurants | +0.186 |
ices | +0.183 |
site | +0.178 |
oving | +0.174 |
Neg logit contributions | |
can | -0.116 |
bead | -0.116 |
aid | -0.108 |
wand | -0.100 |
gently | -0.099 |
Token | her |
Token ID | 607 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
Fourth | +0.150 |
restaurants | +0.141 |
ices | +0.140 |
site | +0.136 |
burgers | +0.132 |
Neg logit contributions | |
bead | -0.091 |
aid | -0.086 |
can | -0.084 |
wand | -0.076 |
clip | -0.067 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
bead | +0.205 |
aid | +0.200 |
can | +0.186 |
wand | +0.179 |
och | +0.179 |
Neg logit contributions | |
Fourth | -0.122 |
restaurants | -0.109 |
burgers | -0.102 |
ices | -0.101 |
site | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
Fourth | +0.032 |
restaurants | +0.030 |
ices | +0.030 |
burgers | +0.029 |
site | +0.029 |
Neg logit contributions | |
bead | -0.024 |
aid | -0.023 |
wand | -0.020 |
can | -0.020 |
cape | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
can | +0.070 |
bead | +0.069 |
aid | +0.066 |
gently | +0.061 |
wand | +0.058 |
Neg logit contributions | |
Fourth | -0.096 |
restaurants | -0.091 |
ices | -0.089 |
site | -0.087 |
oving | -0.086 |
Token | Sp |
Token ID | 4561 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
bead | +0.029 |
can | +0.029 |
aid | +0.029 |
wand | +0.024 |
gently | +0.024 |
Neg logit contributions | |
Fourth | -0.050 |
restaurants | -0.047 |
ices | -0.046 |
site | -0.046 |
urg | -0.045 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
bead | +0.155 |
aid | +0.152 |
can | +0.151 |
wand | +0.138 |
gently | +0.136 |
Neg logit contributions | |
Fourth | -0.111 |
restaurants | -0.097 |
site | -0.091 |
outskirts | -0.090 |
ices | -0.090 |
Token | means |
Token ID | 1724 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
Fourth | +0.589 |
restaurants | +0.522 |
ices | +0.519 |
outskirts | +0.511 |
site | +0.510 |
Neg logit contributions | |
can | -0.565 |
bead | -0.539 |
aid | -0.526 |
wand | -0.484 |
gently | -0.467 |
Token | it |
Token ID | 340 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Fourth | +0.183 |
restaurants | +0.170 |
ices | +0.169 |
site | +0.166 |
oving | +0.160 |
Neg logit contributions | |
bead | -0.130 |
can | -0.127 |
aid | -0.125 |
wand | -0.112 |
gently | -0.107 |
Token | 's |
Token ID | 338 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
can | +0.022 |
bead | +0.021 |
aid | +0.019 |
wand | +0.018 |
gently | +0.018 |
Neg logit contributions | |
Fourth | -0.035 |
restaurants | -0.032 |
ices | -0.032 |
site | -0.032 |
dogs | -0.030 |
Token | going |
Token ID | 1016 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Fourth | +0.267 |
ices | +0.254 |
restaurants | +0.250 |
site | +0.246 |
outskirts | +0.238 |
Neg logit contributions | |
can | -0.178 |
bead | -0.175 |
aid | -0.164 |
wand | -0.153 |
gently | -0.148 |
Token | to |
Token ID | 284 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
Fourth | +0.051 |
restaurants | +0.048 |
site | +0.047 |
ices | +0.047 |
burgers | +0.046 |
Neg logit contributions | |
bead | -0.026 |
aid | -0.025 |
can | -0.022 |
wand | -0.021 |
bud | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
bead | +0.231 |
aid | +0.204 |
can | +0.183 |
endant | +0.182 |
wand | +0.178 |
Neg logit contributions | |
Fourth | -0.341 |
ices | -0.316 |
burgers | -0.308 |
dogs | -0.306 |
icles | -0.296 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
bead | +0.024 |
aid | +0.023 |
wand | +0.021 |
can | +0.021 |
bracelet | +0.020 |
Neg logit contributions | |
Fourth | -0.024 |
restaurants | -0.022 |
ices | -0.022 |
Everyone | -0.021 |
site | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e-03 |
Pos logit contributions | |
bead | +0.005 |
aid | +0.004 |
can | +0.004 |
wand | +0.004 |
clip | +0.004 |
Neg logit contributions | |
Fourth | -0.004 |
restaurants | -0.004 |
ices | -0.004 |
site | -0.004 |
Everyone | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
bead | +0.003 |
wand | +0.003 |
bracelet | +0.003 |
diary | +0.003 |
necklace | +0.003 |
Neg logit contributions | |
Fourth | -0.003 |
site | -0.003 |
ices | -0.003 |
restaurants | -0.003 |
Everyone | -0.003 |
Token | Sp |
Token ID | 4561 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
can | +0.115 |
bead | +0.113 |
ig | +0.111 |
diary | +0.108 |
wand | +0.108 |
Neg logit contributions | |
Fourth | -0.120 |
dogs | -0.110 |
ices | -0.106 |
restaurants | -0.105 |
burgers | -0.105 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
bead | +0.181 |
can | +0.179 |
aid | +0.179 |
wand | +0.167 |
gently | +0.164 |
Neg logit contributions | |
Fourth | -0.051 |
restaurants | -0.040 |
ices | -0.037 |
site | -0.036 |
outskirts | -0.033 |
Token | is |
Token ID | 318 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
Fourth | +0.639 |
restaurants | +0.592 |
ices | +0.587 |
site | +0.577 |
burgers | +0.557 |
Neg logit contributions | |
bead | -0.484 |
can | -0.467 |
aid | -0.466 |
wand | -0.418 |
gently | -0.397 |
Token | good |
Token ID | 922 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
bead | +0.039 |
aid | +0.037 |
can | +0.036 |
wand | +0.033 |
bud | +0.030 |
Neg logit contributions | |
Fourth | -0.063 |
restaurants | -0.058 |
burgers | -0.057 |
site | -0.057 |
ices | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
bead | +0.108 |
can | +0.104 |
aid | +0.103 |
wand | +0.088 |
gently | +0.082 |
Neg logit contributions | |
Fourth | -0.237 |
restaurants | -0.222 |
ices | -0.220 |
site | -0.217 |
burgers | -0.211 |
Token | but |
Token ID | 475 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
bead | +0.016 |
aid | +0.016 |
can | +0.014 |
wand | +0.013 |
gently | +0.013 |
Neg logit contributions | |
Fourth | -0.024 |
restaurants | -0.022 |
site | -0.022 |
ices | -0.022 |
burgers | -0.022 |
Token | not |
Token ID | 407 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
Fourth | +0.171 |
restaurants | +0.157 |
burgers | +0.155 |
site | +0.153 |
ices | +0.151 |
Neg logit contributions | |
aid | -0.103 |
bead | -0.101 |
wand | -0.086 |
can | -0.085 |
och | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
bead | +0.000 |
aid | +0.000 |
can | +0.000 |
wand | +0.000 |
och | +0.000 |
Neg logit contributions | |
Fourth | -0.001 |
ices | -0.001 |
restaurants | -0.001 |
site | -0.001 |
burgers | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.30e-03 |
Pos logit contributions | |
can | +0.027 |
bead | +0.025 |
aid | +0.024 |
gently | +0.022 |
wand | +0.021 |
Neg logit contributions | |
Fourth | -0.044 |
restaurants | -0.042 |
ices | -0.041 |
site | -0.041 |
ics | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
can | +0.007 |
bead | +0.007 |
aid | +0.007 |
gently | +0.006 |
wand | +0.005 |
Neg logit contributions | |
Fourth | -0.015 |
restaurants | -0.014 |
ices | -0.014 |
dogs | -0.014 |
site | -0.014 |
Token | " |
Token ID | 1 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
bead | +0.006 |
aid | +0.005 |
can | +0.005 |
wand | +0.005 |
bracelet | +0.004 |
Neg logit contributions | |
Fourth | -0.013 |
ices | -0.012 |
restaurants | -0.012 |
site | -0.012 |
burgers | -0.012 |
Token | Sp |
Token ID | 4561 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
bead | +0.110 |
can | +0.107 |
aid | +0.105 |
wand | +0.097 |
gently | +0.090 |
Neg logit contributions | |
Fourth | -0.153 |
restaurants | -0.140 |
ices | -0.140 |
site | -0.136 |
burgers | -0.134 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
bead | +0.178 |
aid | +0.176 |
can | +0.176 |
wand | +0.163 |
gently | +0.160 |
Neg logit contributions | |
Fourth | -0.063 |
restaurants | -0.052 |
ices | -0.046 |
site | -0.046 |
outskirts | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
Fourth | +0.727 |
restaurants | +0.674 |
ices | +0.670 |
site | +0.659 |
outskirts | +0.645 |
Neg logit contributions | |
bead | -0.392 |
can | -0.390 |
aid | -0.375 |
wand | -0.328 |
gently | -0.311 |
Token | spicy |
Token ID | 26880 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
bead | +0.031 |
aid | +0.030 |
can | +0.028 |
wand | +0.027 |
gently | +0.025 |
Neg logit contributions | |
Fourth | -0.033 |
burgers | -0.030 |
restaurants | -0.030 |
site | -0.029 |
dogs | -0.028 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Fourth | +0.250 |
restaurants | +0.229 |
ices | +0.228 |
site | +0.225 |
outskirts | +0.220 |
Neg logit contributions | |
can | -0.185 |
bead | -0.184 |
aid | -0.177 |
wand | -0.160 |
gently | -0.153 |
Token | they |
Token ID | 484 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
Fourth | +0.224 |
restaurants | +0.208 |
ices | +0.207 |
site | +0.204 |
oving | +0.197 |
Neg logit contributions | |
bead | -0.137 |
can | -0.133 |
aid | -0.131 |
wand | -0.116 |
gently | -0.110 |
Token | shouted |
Token ID | 17293 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
Fourth | +0.179 |
restaurants | +0.169 |
ices | +0.169 |
site | +0.169 |
dogs | +0.160 |
Neg logit contributions | |
can | -0.101 |
bead | -0.100 |
aid | -0.099 |
gently | -0.088 |
wand | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
ices | +0.101 |
Fourth | +0.099 |
site | +0.092 |
urg | +0.091 |
ics | +0.090 |
Neg logit contributions | |
bead | -0.086 |
can | -0.081 |
aid | -0.081 |
thread | -0.072 |
bracelet | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
aid | +0.048 |
bead | +0.047 |
can | +0.046 |
wand | +0.044 |
bud | +0.043 |
Neg logit contributions | |
Fourth | -0.042 |
ices | -0.039 |
Everyone | -0.038 |
site | -0.037 |
restaurants | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
bead | +0.021 |
aid | +0.020 |
can | +0.020 |
wand | +0.019 |
clip | +0.017 |
Neg logit contributions | |
Fourth | -0.024 |
ices | -0.022 |
restaurants | -0.022 |
site | -0.022 |
burgers | -0.021 |
Token | " |
Token ID | 1 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
can | +0.016 |
aid | +0.016 |
wand | +0.015 |
bead | +0.015 |
diary | +0.014 |
Neg logit contributions | |
Fourth | -0.022 |
ices | -0.021 |
site | -0.021 |
restaurants | -0.020 |
burgers | -0.020 |
Token | Sp |
Token ID | 4561 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
can | +0.109 |
bead | +0.108 |
aid | +0.103 |
wand | +0.097 |
ig | +0.091 |
Neg logit contributions | |
Fourth | -0.146 |
ices | -0.130 |
restaurants | -0.130 |
site | -0.129 |
dogs | -0.125 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
bead | +0.156 |
can | +0.153 |
aid | +0.152 |
wand | +0.141 |
gently | +0.137 |
Neg logit contributions | |
Fourth | -0.093 |
restaurants | -0.082 |
ices | -0.074 |
outskirts | -0.074 |
burgers | -0.073 |
Token | ? |
Token ID | 30 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
Fourth | +0.717 |
restaurants | +0.668 |
ices | +0.663 |
site | +0.653 |
outskirts | +0.632 |
Neg logit contributions | |
bead | -0.399 |
can | -0.388 |
aid | -0.382 |
wand | -0.335 |
gently | -0.315 |
Token | Like |
Token ID | 4525 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
bead | +0.091 |
aid | +0.088 |
can | +0.087 |
wand | +0.080 |
gently | +0.076 |
Neg logit contributions | |
Fourth | -0.100 |
restaurants | -0.091 |
ices | -0.091 |
site | -0.089 |
burgers | -0.086 |
Token | what |
Token ID | 644 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
bead | +0.025 |
aid | +0.024 |
can | +0.023 |
wand | +0.021 |
och | +0.020 |
Neg logit contributions | |
Fourth | -0.030 |
restaurants | -0.028 |
site | -0.028 |
burgers | -0.027 |
ices | -0.027 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
bead | +0.061 |
aid | +0.061 |
can | +0.054 |
wand | +0.051 |
gently | +0.047 |
Neg logit contributions | |
Fourth | -0.118 |
restaurants | -0.111 |
ices | -0.108 |
site | -0.108 |
burgers | -0.106 |
Token | Ben |
Token ID | 3932 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
aid | +0.010 |
bead | +0.009 |
can | +0.009 |
wand | +0.008 |
clip | +0.008 |
Neg logit contributions | |
Fourth | -0.012 |
restaurants | -0.011 |
site | -0.011 |
ices | -0.011 |
outskirts | -0.010 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
bead | +0.054 |
aid | +0.053 |
can | +0.051 |
wand | +0.048 |
gently | +0.044 |
Neg logit contributions | |
Fourth | -0.064 |
restaurants | -0.058 |
ices | -0.057 |
site | -0.057 |
burgers | -0.055 |
Token | Red |
Token ID | 2297 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
bead | +0.044 |
aid | +0.044 |
can | +0.041 |
wand | +0.039 |
gently | +0.035 |
Neg logit contributions | |
Fourth | -0.059 |
restaurants | -0.055 |
ices | -0.053 |
site | -0.053 |
burgers | -0.052 |
Token | dy |
Token ID | 9892 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
bead | +0.063 |
aid | +0.063 |
can | +0.056 |
wand | +0.053 |
bud | +0.050 |
Neg logit contributions | |
Fourth | -0.102 |
restaurants | -0.096 |
ices | -0.094 |
site | -0.094 |
burgers | -0.093 |
Token | or |
Token ID | 393 |
Feature activation | +1.93e-03 |
Pos logit contributions | |
Fourth | +0.109 |
restaurants | +0.103 |
ices | +0.100 |
burgers | +0.100 |
site | +0.100 |
Neg logit contributions | |
bead | -0.060 |
aid | -0.059 |
can | -0.050 |
wand | -0.048 |
och | -0.045 |
Token | Sp |
Token ID | 1338 |
Feature activation | +3.15e-03 |
Pos logit contributions | |
aid | +0.003 |
bead | +0.003 |
wand | +0.003 |
arl | +0.003 |
ig | +0.003 |
Neg logit contributions | |
Fourth | -0.004 |
restaurants | -0.003 |
burgers | -0.003 |
site | -0.003 |
Andrew | -0.003 |
Token | icy |
Token ID | 4611 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
bead | +0.007 |
aid | +0.007 |
can | +0.007 |
arl | +0.006 |
ppy | +0.006 |
Neg logit contributions | |
Fourth | -0.004 |
restaurants | -0.003 |
outskirts | -0.003 |
docks | -0.003 |
youngest | -0.003 |
Token | or |
Token ID | 393 |
Feature activation | -9.94e-05 |
Pos logit contributions | |
Fourth | +0.629 |
restaurants | +0.577 |
ices | +0.575 |
site | +0.565 |
outskirts | +0.551 |
Neg logit contributions | |
bead | -0.459 |
can | -0.458 |
aid | -0.443 |
wand | -0.395 |
gently | -0.379 |
Token | Hot |
Token ID | 6964 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
Fourth | +0.000 |
restaurants | +0.000 |
burgers | +0.000 |
site | +0.000 |
dogs | +0.000 |
Neg logit contributions | |
aid | -0.000 |
bead | -0.000 |
can | -0.000 |
och | -0.000 |
wand | -0.000 |
Token | ." |
Token ID | 526 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
Fourth | +0.200 |
restaurants | +0.183 |
ices | +0.183 |
site | +0.180 |
outskirts | +0.177 |
Neg logit contributions | |
can | -0.137 |
bead | -0.135 |
aid | -0.131 |
wand | -0.116 |
gently | -0.110 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
Fourth | +0.027 |
restaurants | +0.025 |
ices | +0.025 |
site | +0.024 |
burgers | +0.024 |
Neg logit contributions | |
bead | -0.021 |
can | -0.020 |
aid | -0.020 |
wand | -0.018 |
gently | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
bead | +0.122 |
can | +0.119 |
aid | +0.117 |
wand | +0.103 |
gently | +0.098 |
Neg logit contributions | |
Fourth | -0.210 |
restaurants | -0.196 |
ices | -0.194 |
site | -0.191 |
burgers | -0.184 |
Token | you |
Token ID | 345 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
Fourth | +0.066 |
restaurants | +0.060 |
site | +0.058 |
burgers | +0.058 |
ices | +0.057 |
Neg logit contributions | |
aid | -0.041 |
bead | -0.040 |
wand | -0.035 |
och | -0.034 |
can | -0.033 |
Token | know |
Token ID | 760 |
Feature activation | +7.54e-03 |
Pos logit contributions | |
bead | +0.037 |
aid | +0.036 |
can | +0.034 |
wand | +0.031 |
gently | +0.029 |
Neg logit contributions | |
Fourth | -0.075 |
restaurants | -0.070 |
ices | -0.069 |
site | -0.068 |
burgers | -0.066 |
Token | what |
Token ID | 644 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
aid | +0.011 |
bead | +0.011 |
wand | +0.010 |
can | +0.010 |
och | +0.009 |
Neg logit contributions | |
Fourth | -0.015 |
restaurants | -0.015 |
burgers | -0.014 |
site | -0.014 |
ices | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
aid | +0.068 |
bead | +0.066 |
wand | +0.058 |
can | +0.058 |
arl | +0.055 |
Neg logit contributions | |
Fourth | -0.102 |
restaurants | -0.097 |
burgers | -0.092 |
site | -0.091 |
ices | -0.091 |
Token | y |
Token ID | 331 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
bead | +0.036 |
aid | +0.036 |
can | +0.034 |
wand | +0.030 |
gently | +0.028 |
Neg logit contributions | |
Fourth | -0.057 |
restaurants | -0.053 |
site | -0.051 |
ices | -0.051 |
burgers | -0.050 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Fourth | +0.048 |
restaurants | +0.040 |
site | +0.039 |
ices | +0.038 |
outskirts | +0.036 |
Neg logit contributions | |
bead | -0.117 |
can | -0.115 |
aid | -0.114 |
wand | -0.106 |
gently | -0.103 |
Token | ier |
Token ID | 959 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
Fourth | +0.548 |
ices | +0.522 |
restaurants | +0.512 |
dogs | +0.483 |
site | +0.478 |
Neg logit contributions | |
bead | -0.496 |
aid | -0.467 |
can | -0.460 |
wand | -0.435 |
gently | -0.424 |
Token | ? |
Token ID | 30 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
Fourth | +0.018 |
restaurants | +0.017 |
ices | +0.017 |
site | +0.017 |
burgers | +0.016 |
Neg logit contributions | |
bead | -0.011 |
aid | -0.011 |
can | -0.010 |
wand | -0.009 |
thread | -0.008 |
Token | You |
Token ID | 921 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
bead | +0.090 |
aid | +0.088 |
can | +0.085 |
wand | +0.083 |
bud | +0.078 |
Neg logit contributions | |
Fourth | -0.097 |
restaurants | -0.089 |
ices | -0.088 |
site | -0.084 |
dogs | -0.083 |
Token | are |
Token ID | 389 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
Fourth | +0.003 |
restaurants | +0.003 |
ices | +0.003 |
site | +0.003 |
burgers | +0.003 |
Neg logit contributions | |
bead | -0.001 |
aid | -0.001 |
can | -0.001 |
wand | -0.001 |
gently | -0.001 |
Token | y |
Token ID | 331 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
bead | +0.071 |
aid | +0.068 |
can | +0.066 |
wand | +0.058 |
och | +0.055 |
Neg logit contributions | |
Fourth | -0.107 |
restaurants | -0.100 |
burgers | -0.096 |
site | -0.096 |
outskirts | -0.092 |
Token | ier |
Token ID | 959 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
Fourth | +0.548 |
ices | +0.522 |
restaurants | +0.512 |
dogs | +0.483 |
site | +0.478 |
Neg logit contributions | |
bead | -0.496 |
aid | -0.467 |
can | -0.460 |
wand | -0.435 |
gently | -0.424 |
Token | ? |
Token ID | 30 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
Fourth | +0.018 |
restaurants | +0.017 |
ices | +0.017 |
site | +0.017 |
burgers | +0.016 |
Neg logit contributions | |
bead | -0.011 |
aid | -0.011 |
can | -0.010 |
wand | -0.009 |
thread | -0.008 |
Token | You |
Token ID | 921 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
bead | +0.090 |
aid | +0.088 |
can | +0.085 |
wand | +0.083 |
bud | +0.078 |
Neg logit contributions | |
Fourth | -0.097 |
restaurants | -0.089 |
ices | -0.088 |
site | -0.084 |
dogs | -0.083 |
Token | are |
Token ID | 389 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
Fourth | +0.003 |
restaurants | +0.003 |
ices | +0.003 |
site | +0.003 |
burgers | +0.003 |
Neg logit contributions | |
bead | -0.001 |
aid | -0.001 |
can | -0.001 |
wand | -0.001 |
gently | -0.001 |
Token | y |
Token ID | 331 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
bead | +0.071 |
aid | +0.068 |
can | +0.066 |
wand | +0.058 |
och | +0.055 |
Neg logit contributions | |
Fourth | -0.107 |
restaurants | -0.100 |
burgers | -0.096 |
site | -0.096 |
outskirts | -0.092 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Fourth | +0.050 |
site | +0.041 |
restaurants | +0.041 |
ices | +0.039 |
outskirts | +0.037 |
Neg logit contributions | |
bead | -0.118 |
aid | -0.115 |
can | -0.115 |
wand | -0.107 |
gently | -0.104 |
Token | ier |
Token ID | 959 |
Feature activation | -8.60e-03 |
Pos logit contributions | |
Fourth | +0.542 |
ices | +0.521 |
restaurants | +0.508 |
dogs | +0.483 |
urg | +0.479 |
Neg logit contributions | |
bead | -0.504 |
can | -0.475 |
aid | -0.472 |
wand | -0.432 |
thread | -0.426 |
Token | . |
Token ID | 13 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
Fourth | +0.019 |
restaurants | +0.018 |
ices | +0.018 |
site | +0.018 |
oving | +0.017 |
Neg logit contributions | |
bead | -0.011 |
aid | -0.011 |
can | -0.011 |
wand | -0.009 |
gently | -0.009 |
Token | You |
Token ID | 921 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
bead | +0.011 |
aid | +0.011 |
can | +0.011 |
wand | +0.010 |
gently | +0.009 |
Neg logit contributions | |
Fourth | -0.015 |
restaurants | -0.014 |
ices | -0.014 |
site | -0.013 |
burgers | -0.013 |
Token | are |
Token ID | 389 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
Fourth | +0.006 |
restaurants | +0.005 |
ices | +0.005 |
site | +0.005 |
burgers | +0.005 |
Neg logit contributions | |
bead | -0.003 |
aid | -0.003 |
can | -0.003 |
wand | -0.002 |
gently | -0.002 |
Token | my |
Token ID | 616 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
bead | +0.067 |
aid | +0.065 |
can | +0.062 |
wand | +0.055 |
och | +0.053 |
Neg logit contributions | |
Fourth | -0.108 |
restaurants | -0.101 |
burgers | -0.097 |
site | -0.096 |
outskirts | -0.093 |
Token | adventure |
Token ID | 8855 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
Fourth | +0.068 |
ices | +0.062 |
restaurants | +0.061 |
site | +0.059 |
dogs | +0.057 |
Neg logit contributions | |
bead | -0.085 |
can | -0.084 |
aid | -0.082 |
wand | -0.077 |
gently | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
Fourth | +0.088 |
restaurants | +0.083 |
ices | +0.082 |
urg | +0.080 |
dogs | +0.080 |
Neg logit contributions | |
can | -0.029 |
bead | -0.029 |
aid | -0.026 |
wand | -0.023 |
gently | -0.023 |
Token | found |
Token ID | 1043 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
can | +0.005 |
bead | +0.004 |
aid | +0.004 |
gently | +0.004 |
wand | +0.004 |
Neg logit contributions | |
Fourth | -0.008 |
ices | -0.008 |
restaurants | -0.007 |
site | -0.007 |
oving | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
Fourth | +0.077 |
restaurants | +0.070 |
oving | +0.069 |
ices | +0.069 |
urg | +0.068 |
Neg logit contributions | |
can | -0.045 |
aid | -0.042 |
bead | -0.042 |
gently | -0.038 |
wand | -0.037 |
Token | y |
Token ID | 331 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
Fourth | +0.015 |
restaurants | +0.014 |
ices | +0.013 |
site | +0.013 |
burgers | +0.013 |
Neg logit contributions | |
bead | -0.011 |
aid | -0.011 |
can | -0.011 |
wand | -0.010 |
gently | -0.009 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Fourth | +0.049 |
restaurants | +0.042 |
ices | +0.040 |
site | +0.039 |
ics | +0.038 |
Neg logit contributions | |
bead | -0.103 |
can | -0.101 |
aid | -0.098 |
wand | -0.094 |
bud | -0.092 |
Token | iest |
Token ID | 6386 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Fourth | +0.437 |
restaurants | +0.393 |
ices | +0.387 |
site | +0.378 |
outskirts | +0.361 |
Neg logit contributions | |
bead | -0.607 |
can | -0.595 |
aid | -0.592 |
wand | -0.546 |
gently | -0.526 |
Token | berries |
Token ID | 36322 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
Fourth | +0.213 |
restaurants | +0.197 |
ices | +0.195 |
site | +0.192 |
oving | +0.187 |
Neg logit contributions | |
bead | -0.168 |
can | -0.165 |
aid | -0.159 |
wand | -0.147 |
gently | -0.139 |
Token | they |
Token ID | 484 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
Fourth | +0.061 |
restaurants | +0.056 |
ices | +0.056 |
site | +0.056 |
burgers | +0.055 |
Neg logit contributions | |
bead | -0.044 |
aid | -0.043 |
can | -0.040 |
wand | -0.037 |
clip | -0.034 |
Token | had |
Token ID | 550 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
Fourth | +0.208 |
restaurants | +0.191 |
ices | +0.184 |
site | +0.184 |
burgers | +0.181 |
Neg logit contributions | |
bead | -0.108 |
aid | -0.105 |
can | -0.087 |
wand | -0.086 |
clip | -0.079 |
Token | ever |
Token ID | 1683 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
can | +0.068 |
bead | +0.067 |
aid | +0.061 |
wand | +0.054 |
gently | +0.050 |
Neg logit contributions | |
Fourth | -0.183 |
restaurants | -0.173 |
ices | -0.171 |
site | -0.169 |
burgers | -0.167 |
Token | ! |
Token ID | 0 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
Fourth | +0.033 |
ices | +0.032 |
restaurants | +0.031 |
site | +0.031 |
burgers | +0.030 |
Neg logit contributions | |
bead | -0.017 |
aid | -0.017 |
can | -0.016 |
wand | -0.014 |
gently | -0.013 |
Token | It |
Token ID | 632 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
oving | +0.177 |
Fourth | +0.177 |
site | +0.177 |
restaurants | +0.176 |
urg | +0.169 |
Neg logit contributions | |
can | -0.142 |
bead | -0.133 |
aid | -0.126 |
gently | -0.115 |
thread | -0.109 |
Token | was |
Token ID | 373 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
can | +0.036 |
bead | +0.031 |
gently | +0.029 |
aid | +0.027 |
will | +0.027 |
Neg logit contributions | |
Fourth | -0.075 |
restaurants | -0.071 |
ices | -0.068 |
site | -0.067 |
dogs | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Fourth | +0.125 |
ices | +0.120 |
restaurants | +0.119 |
site | +0.117 |
outskirts | +0.114 |
Neg logit contributions | |
can | -0.073 |
bead | -0.071 |
aid | -0.067 |
gently | -0.061 |
wand | -0.060 |
Token | y |
Token ID | 331 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
Fourth | +0.020 |
ices | +0.019 |
restaurants | +0.019 |
site | +0.018 |
oving | +0.018 |
Neg logit contributions | |
can | -0.020 |
bead | -0.020 |
aid | -0.020 |
wand | -0.019 |
gently | -0.018 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Fourth | +0.052 |
restaurants | +0.048 |
ics | +0.045 |
outskirts | +0.045 |
site | +0.045 |
Neg logit contributions | |
can | -0.104 |
bead | -0.104 |
aid | -0.100 |
wand | -0.093 |
bud | -0.093 |
Token | iest |
Token ID | 6386 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Fourth | +0.442 |
restaurants | +0.398 |
ices | +0.392 |
site | +0.385 |
outskirts | +0.367 |
Neg logit contributions | |
bead | -0.594 |
can | -0.583 |
aid | -0.579 |
wand | -0.534 |
gently | -0.514 |
Token | stew |
Token ID | 20798 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Fourth | +0.192 |
ics | +0.188 |
outskirts | +0.182 |
oving | +0.181 |
site | +0.175 |
Neg logit contributions | |
can | -0.192 |
bead | -0.182 |
wand | -0.174 |
aid | -0.167 |
fairy | -0.166 |
Token | ever |
Token ID | 1683 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
Fourth | +0.286 |
restaurants | +0.267 |
ices | +0.265 |
site | +0.260 |
oving | +0.252 |
Neg logit contributions | |
bead | -0.185 |
can | -0.182 |
aid | -0.177 |
wand | -0.159 |
gently | -0.150 |
Token | ! |
Token ID | 0 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
bead | +0.038 |
aid | +0.037 |
can | +0.035 |
wand | +0.032 |
gently | +0.029 |
Neg logit contributions | |
Fourth | -0.072 |
restaurants | -0.067 |
ices | -0.066 |
site | -0.065 |
burgers | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Fourth | +0.220 |
oving | +0.217 |
site | +0.216 |
restaurants | +0.214 |
ices | +0.210 |
Neg logit contributions | |
can | -0.105 |
bead | -0.098 |
aid | -0.092 |
gently | -0.076 |
hug | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Fourth | +0.218 |
ices | +0.207 |
restaurants | +0.204 |
burgers | +0.201 |
dogs | +0.199 |
Neg logit contributions | |
aid | -0.108 |
bead | -0.108 |
can | -0.100 |
wand | -0.084 |
gently | -0.080 |
Token | It |
Token ID | 632 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
bead | +0.015 |
aid | +0.015 |
can | +0.015 |
wand | +0.013 |
gently | +0.012 |
Neg logit contributions | |
Fourth | -0.024 |
restaurants | -0.022 |
ices | -0.022 |
site | -0.022 |
outskirts | -0.021 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
bead | +0.049 |
can | +0.048 |
aid | +0.047 |
wand | +0.042 |
gently | +0.041 |
Neg logit contributions | |
Fourth | -0.072 |
restaurants | -0.068 |
ices | -0.067 |
site | -0.066 |
oving | -0.064 |
Token | even |
Token ID | 772 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Fourth | +0.036 |
burgers | +0.033 |
restaurants | +0.033 |
site | +0.032 |
dogs | +0.032 |
Neg logit contributions | |
bead | -0.026 |
aid | -0.025 |
can | -0.022 |
wand | -0.021 |
och | -0.020 |
Token | y |
Token ID | 331 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
Fourth | +0.355 |
restaurants | +0.334 |
burgers | +0.327 |
site | +0.322 |
ices | +0.317 |
Neg logit contributions | |
bead | -0.198 |
aid | -0.188 |
can | -0.187 |
wand | -0.168 |
och | -0.161 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Fourth | +0.041 |
restaurants | +0.035 |
site | +0.033 |
ices | +0.033 |
outskirts | +0.030 |
Neg logit contributions | |
bead | -0.104 |
can | -0.102 |
aid | -0.101 |
wand | -0.095 |
gently | -0.093 |
Token | ier |
Token ID | 959 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
Fourth | +0.547 |
ices | +0.519 |
restaurants | +0.496 |
dogs | +0.482 |
urg | +0.477 |
Neg logit contributions | |
bead | -0.484 |
aid | -0.470 |
can | -0.456 |
wand | -0.425 |
gently | -0.414 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
Fourth | +0.017 |
restaurants | +0.016 |
ices | +0.016 |
site | +0.016 |
burgers | +0.015 |
Neg logit contributions | |
aid | -0.011 |
bead | -0.011 |
can | -0.010 |
wand | -0.009 |
thread | -0.008 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
bead | +0.015 |
aid | +0.015 |
can | +0.014 |
wand | +0.013 |
gently | +0.012 |
Neg logit contributions | |
Fourth | -0.026 |
restaurants | -0.024 |
ices | -0.024 |
site | -0.023 |
outskirts | -0.023 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
bead | +0.113 |
aid | +0.109 |
can | +0.109 |
wand | +0.098 |
gently | +0.092 |
Neg logit contributions | |
Fourth | -0.152 |
restaurants | -0.141 |
ices | -0.140 |
site | -0.138 |
oving | -0.133 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Fourth | +0.106 |
ices | +0.100 |
site | +0.098 |
restaurants | +0.098 |
oving | +0.098 |
Neg logit contributions | |
bead | -0.035 |
can | -0.035 |
aid | -0.033 |
gently | -0.026 |
wand | -0.026 |
Token | These |
Token ID | 4711 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Fourth | +0.008 |
restaurants | +0.007 |
ices | +0.007 |
site | +0.007 |
oving | +0.007 |
Neg logit contributions | |
bead | -0.006 |
aid | -0.005 |
can | -0.005 |
wand | -0.005 |
gently | -0.005 |
Token | oranges |
Token ID | 48389 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
Fourth | +0.395 |
ices | +0.368 |
restaurants | +0.365 |
site | +0.364 |
oving | +0.351 |
Neg logit contributions | |
can | -0.233 |
bead | -0.232 |
aid | -0.221 |
wand | -0.193 |
gently | -0.185 |
Token | are |
Token ID | 389 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
Fourth | +0.194 |
restaurants | +0.182 |
ices | +0.176 |
site | +0.175 |
burgers | +0.173 |
Neg logit contributions | |
bead | -0.109 |
aid | -0.107 |
can | -0.097 |
wand | -0.094 |
gently | -0.085 |
Token | even |
Token ID | 772 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
bead | +0.071 |
aid | +0.069 |
can | +0.068 |
wand | +0.061 |
gently | +0.057 |
Neg logit contributions | |
Fourth | -0.095 |
restaurants | -0.088 |
ices | -0.086 |
site | -0.086 |
burgers | -0.083 |
Token | y |
Token ID | 331 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
Fourth | +0.347 |
burgers | +0.332 |
restaurants | +0.329 |
dogs | +0.309 |
oving | +0.308 |
Neg logit contributions | |
bead | -0.203 |
wand | -0.187 |
aid | -0.184 |
can | -0.180 |
och | -0.166 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Fourth | +0.048 |
restaurants | +0.041 |
site | +0.040 |
ices | +0.039 |
outskirts | +0.037 |
Neg logit contributions | |
bead | -0.105 |
can | -0.103 |
aid | -0.101 |
wand | -0.093 |
gently | -0.092 |
Token | ier |
Token ID | 959 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
Fourth | +0.587 |
ices | +0.545 |
restaurants | +0.544 |
site | +0.527 |
dogs | +0.513 |
Neg logit contributions | |
bead | -0.443 |
can | -0.427 |
aid | -0.425 |
wand | -0.385 |
gently | -0.366 |
Token | than |
Token ID | 621 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
Fourth | +0.026 |
restaurants | +0.025 |
ices | +0.024 |
site | +0.024 |
burgers | +0.023 |
Neg logit contributions | |
bead | -0.015 |
aid | -0.014 |
can | -0.014 |
wand | -0.012 |
gently | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
Fourth | +0.068 |
restaurants | +0.063 |
ices | +0.061 |
site | +0.061 |
burgers | +0.059 |
Neg logit contributions | |
bead | -0.052 |
aid | -0.051 |
can | -0.050 |
wand | -0.045 |
gently | -0.043 |
Token | last |
Token ID | 938 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
Fourth | +0.017 |
restaurants | +0.016 |
ices | +0.015 |
site | +0.015 |
burgers | +0.014 |
Neg logit contributions | |
aid | -0.019 |
bead | -0.018 |
can | -0.018 |
wand | -0.016 |
gently | -0.016 |
Token | ," |
Token ID | 553 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
bead | +0.081 |
aid | +0.080 |
can | +0.079 |
wand | +0.073 |
gently | +0.070 |
Neg logit contributions | |
Fourth | -0.066 |
restaurants | -0.060 |
ices | -0.059 |
site | -0.058 |
burgers | -0.055 |
Token | make |
Token ID | 787 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
can | +0.320 |
bead | +0.284 |
aid | +0.265 |
gently | +0.254 |
will | +0.245 |
Neg logit contributions | |
Fourth | -0.487 |
ices | -0.473 |
site | -0.460 |
restaurants | -0.459 |
oving | -0.451 |
Token | the |
Token ID | 262 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
Fourth | +0.006 |
oving | +0.006 |
outskirts | +0.006 |
ices | +0.006 |
site | +0.006 |
Neg logit contributions | |
can | -0.004 |
bead | -0.004 |
better | -0.003 |
gently | -0.003 |
aid | -0.003 |
Token | food |
Token ID | 2057 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
oving | +0.009 |
rolled | +0.009 |
ics | +0.009 |
ices | +0.008 |
Fourth | +0.008 |
Neg logit contributions | |
can | -0.010 |
wand | -0.009 |
fairy | -0.008 |
bead | -0.008 |
will | -0.008 |
Token | even |
Token ID | 772 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Fourth | +0.133 |
restaurants | +0.124 |
ices | +0.121 |
site | +0.120 |
burgers | +0.118 |
Neg logit contributions | |
bead | -0.079 |
aid | -0.077 |
can | -0.073 |
wand | -0.066 |
gently | -0.061 |
Token | y |
Token ID | 331 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
Fourth | +0.409 |
restaurants | +0.390 |
burgers | +0.380 |
ices | +0.375 |
site | +0.372 |
Neg logit contributions | |
bead | -0.148 |
aid | -0.139 |
can | -0.132 |
wand | -0.118 |
och | -0.110 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Fourth | +0.056 |
site | +0.049 |
outskirts | +0.049 |
restaurants | +0.048 |
cinema | +0.045 |
Neg logit contributions | |
bead | -0.092 |
can | -0.092 |
aid | -0.089 |
arl | -0.081 |
wand | -0.081 |
Token | ier |
Token ID | 959 |
Feature activation | -8.60e-03 |
Pos logit contributions | |
Fourth | +0.514 |
restaurants | +0.468 |
ices | +0.464 |
site | +0.457 |
outskirts | +0.440 |
Neg logit contributions | |
bead | -0.520 |
can | -0.510 |
aid | -0.505 |
wand | -0.460 |
gently | -0.439 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
Fourth | +0.020 |
ices | +0.019 |
restaurants | +0.018 |
site | +0.018 |
outskirts | +0.018 |
Neg logit contributions | |
can | -0.010 |
bead | -0.010 |
aid | -0.009 |
wand | -0.009 |
gently | -0.008 |
Token | Let |
Token ID | 3914 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
can | +0.021 |
bead | +0.021 |
aid | +0.020 |
wand | +0.018 |
gently | +0.017 |
Neg logit contributions | |
Fourth | -0.025 |
restaurants | -0.023 |
ices | -0.023 |
site | -0.022 |
oving | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
can | +0.064 |
will | +0.052 |
gently | +0.051 |
better | +0.049 |
bead | +0.048 |
Neg logit contributions | |
Fourth | -0.124 |
ices | -0.121 |
site | -0.120 |
dogs | -0.119 |
restaurants | -0.118 |
Token | see |
Token ID | 766 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
Fourth | +0.274 |
ices | +0.255 |
restaurants | +0.255 |
site | +0.249 |
oving | +0.240 |
Neg logit contributions | |
bead | -0.201 |
can | -0.199 |
aid | -0.193 |
wand | -0.174 |
gently | -0.167 |
Token | store |
Token ID | 3650 |
Feature activation | +6.39e-03 |
Pos logit contributions | |
Fourth | +0.013 |
restaurants | +0.012 |
site | +0.011 |
ices | +0.011 |
burgers | +0.011 |
Neg logit contributions | |
bead | -0.013 |
aid | -0.013 |
can | -0.013 |
wand | -0.012 |
gently | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +4.01e-03 |
Pos logit contributions | |
can | +0.004 |
bead | +0.003 |
gently | +0.003 |
aid | +0.003 |
wand | +0.002 |
Neg logit contributions | |
Fourth | -0.019 |
ices | -0.018 |
restaurants | -0.018 |
urg | -0.017 |
oving | -0.017 |
Token | got |
Token ID | 1392 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
can | +0.006 |
bead | +0.005 |
aid | +0.005 |
gently | +0.005 |
c | +0.005 |
Neg logit contributions | |
Fourth | -0.009 |
ices | -0.008 |
restaurants | -0.008 |
urg | -0.008 |
site | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
Fourth | +0.044 |
ices | +0.042 |
site | +0.041 |
restaurants | +0.041 |
oving | +0.040 |
Neg logit contributions | |
can | -0.026 |
aid | -0.026 |
bead | -0.026 |
gently | -0.022 |
wand | -0.022 |
Token | y |
Token ID | 331 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
Fourth | +0.017 |
ices | +0.017 |
restaurants | +0.016 |
site | +0.016 |
oving | +0.016 |
Neg logit contributions | |
can | -0.013 |
bead | -0.013 |
aid | -0.012 |
wand | -0.011 |
gently | -0.011 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Fourth | +0.052 |
restaurants | +0.043 |
site | +0.043 |
ices | +0.042 |
outskirts | +0.042 |
Neg logit contributions | |
bead | -0.097 |
aid | -0.095 |
can | -0.094 |
bud | -0.088 |
gently | -0.087 |
Token | iest |
Token ID | 6386 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Fourth | +0.436 |
restaurants | +0.392 |
ices | +0.389 |
site | +0.378 |
burgers | +0.359 |
Neg logit contributions | |
bead | -0.598 |
can | -0.585 |
aid | -0.581 |
wand | -0.538 |
gently | -0.520 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
Fourth | +0.218 |
ices | +0.202 |
restaurants | +0.200 |
site | +0.196 |
oving | +0.194 |
Neg logit contributions | |
bead | -0.164 |
can | -0.161 |
aid | -0.156 |
wand | -0.141 |
gently | -0.137 |
Token | cream |
Token ID | 8566 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
Fourth | +0.040 |
restaurants | +0.037 |
ices | +0.037 |
site | +0.036 |
outskirts | +0.036 |
Neg logit contributions | |
bead | -0.024 |
can | -0.024 |
aid | -0.024 |
wand | -0.020 |
gently | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
bead | +0.062 |
can | +0.060 |
aid | +0.059 |
wand | +0.052 |
gently | +0.049 |
Neg logit contributions | |
Fourth | -0.112 |
restaurants | -0.104 |
ices | -0.103 |
site | -0.102 |
burgers | -0.099 |
Token | could |
Token ID | 714 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Fourth | +0.213 |
restaurants | +0.197 |
ices | +0.192 |
site | +0.190 |
burgers | +0.188 |
Neg logit contributions | |
bead | -0.105 |
aid | -0.102 |
can | -0.090 |
wand | -0.086 |
gently | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +4.22e-03 |
Pos logit contributions | |
Fourth | +0.021 |
ices | +0.020 |
burgers | +0.020 |
restaurants | +0.020 |
dogs | +0.019 |
Neg logit contributions | |
bead | -0.014 |
aid | -0.013 |
can | -0.012 |
wand | -0.012 |
arl | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +5.01e-03 |
Pos logit contributions | |
bead | +0.006 |
can | +0.006 |
aid | +0.006 |
wand | +0.005 |
gently | +0.005 |
Neg logit contributions | |
Fourth | -0.009 |
restaurants | -0.008 |
ices | -0.008 |
site | -0.008 |
oving | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
bead | +0.008 |
can | +0.007 |
aid | +0.007 |
wand | +0.006 |
gently | +0.006 |
Neg logit contributions | |
Fourth | -0.010 |
restaurants | -0.010 |
ices | -0.010 |
site | -0.009 |
dogs | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
Fourth | +0.106 |
restaurants | +0.097 |
ices | +0.095 |
site | +0.094 |
burgers | +0.093 |
Neg logit contributions | |
bead | -0.077 |
aid | -0.076 |
can | -0.074 |
wand | -0.066 |
och | -0.061 |
Token | y |
Token ID | 331 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
Fourth | +0.015 |
ices | +0.015 |
restaurants | +0.015 |
site | +0.015 |
oving | +0.014 |
Neg logit contributions | |
can | -0.014 |
bead | -0.014 |
aid | -0.013 |
wand | -0.012 |
gently | -0.011 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Fourth | +0.048 |
restaurants | +0.043 |
site | +0.041 |
outskirts | +0.041 |
ics | +0.040 |
Neg logit contributions | |
bead | -0.095 |
can | -0.093 |
aid | -0.091 |
bud | -0.083 |
gently | -0.083 |
Token | iest |
Token ID | 6386 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Fourth | +0.443 |
restaurants | +0.398 |
ices | +0.395 |
site | +0.385 |
burgers | +0.365 |
Neg logit contributions | |
bead | -0.589 |
can | -0.576 |
aid | -0.573 |
wand | -0.530 |
gently | -0.511 |
Token | steak |
Token ID | 26320 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
Fourth | +0.193 |
oving | +0.180 |
ics | +0.180 |
outskirts | +0.180 |
ices | +0.178 |
Neg logit contributions | |
bead | -0.187 |
can | -0.186 |
aid | -0.171 |
wand | -0.162 |
gently | -0.155 |
Token | she |
Token ID | 673 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
Fourth | +0.174 |
restaurants | +0.161 |
site | +0.158 |
ices | +0.158 |
burgers | +0.155 |
Neg logit contributions | |
aid | -0.095 |
bead | -0.094 |
can | -0.088 |
wand | -0.079 |
arl | -0.073 |
Token | ever |
Token ID | 1683 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
aid | +0.085 |
bead | +0.084 |
wand | +0.072 |
arl | +0.072 |
bud | +0.067 |
Neg logit contributions | |
Fourth | -0.123 |
restaurants | -0.113 |
burgers | -0.107 |
site | -0.105 |
dogs | -0.105 |
Token | tasted |
Token ID | 29187 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
bead | +0.051 |
aid | +0.049 |
wand | +0.046 |
can | +0.045 |
arl | +0.042 |
Neg logit contributions | |
Fourth | -0.064 |
restaurants | -0.060 |
ices | -0.058 |
burgers | -0.056 |
site | -0.055 |
Token | little |
Token ID | 1310 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
Fourth | +0.003 |
restaurants | +0.003 |
ices | +0.003 |
site | +0.003 |
oving | +0.003 |
Neg logit contributions | |
bead | -0.003 |
can | -0.002 |
aid | -0.002 |
wand | -0.002 |
gently | -0.002 |
Token | boy |
Token ID | 2933 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
Fourth | +0.036 |
restaurants | +0.033 |
ices | +0.033 |
site | +0.032 |
burgers | +0.031 |
Neg logit contributions | |
bead | -0.030 |
aid | -0.030 |
can | -0.029 |
wand | -0.027 |
gently | -0.025 |
Token | had |
Token ID | 550 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
Fourth | +0.008 |
restaurants | +0.008 |
ices | +0.008 |
site | +0.007 |
outskirts | +0.007 |
Neg logit contributions | |
can | -0.005 |
bead | -0.005 |
aid | -0.004 |
gently | -0.004 |
wand | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
can | +0.101 |
bead | +0.098 |
aid | +0.093 |
gently | +0.082 |
wand | +0.080 |
Neg logit contributions | |
Fourth | -0.185 |
ices | -0.175 |
restaurants | -0.169 |
site | -0.168 |
oving | -0.168 |
Token | y |
Token ID | 331 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Fourth | +0.003 |
ices | +0.003 |
restaurants | +0.003 |
oving | +0.003 |
urg | +0.003 |
Neg logit contributions | |
can | -0.003 |
bead | -0.002 |
aid | -0.002 |
wand | -0.002 |
gently | -0.002 |
Token | umm |
Token ID | 13929 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Fourth | +0.048 |
outskirts | +0.041 |
site | +0.040 |
restaurants | +0.039 |
ices | +0.038 |
Neg logit contributions | |
bead | -0.087 |
can | -0.085 |
aid | -0.084 |
bud | -0.077 |
gently | -0.075 |
Token | iest |
Token ID | 6386 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Fourth | +0.407 |
ices | +0.366 |
restaurants | +0.363 |
site | +0.347 |
dogs | +0.334 |
Neg logit contributions | |
bead | -0.619 |
can | -0.603 |
aid | -0.598 |
wand | -0.564 |
gently | -0.547 |
Token | treat |
Token ID | 2190 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
Fourth | +0.205 |
ices | +0.189 |
restaurants | +0.187 |
site | +0.185 |
outskirts | +0.182 |
Neg logit contributions | |
bead | -0.159 |
can | -0.159 |
aid | -0.153 |
wand | -0.137 |
gently | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
bead | +0.065 |
can | +0.063 |
aid | +0.062 |
wand | +0.055 |
gently | +0.052 |
Neg logit contributions | |
Fourth | -0.105 |
restaurants | -0.098 |
ices | -0.097 |
site | -0.095 |
outskirts | -0.092 |
Token | He |
Token ID | 679 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
can | +0.016 |
bead | +0.013 |
aid | +0.011 |
gently | +0.011 |
hug | +0.010 |
Neg logit contributions | |
Fourth | -0.026 |
ics | -0.026 |
oving | -0.025 |
restaurants | -0.024 |
site | -0.024 |
Token | asked |
Token ID | 1965 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
bead | +0.037 |
can | +0.037 |
aid | +0.035 |
wand | +0.032 |
gently | +0.031 |
Neg logit contributions | |
Fourth | -0.058 |
restaurants | -0.054 |
ices | -0.054 |
site | -0.053 |
outskirts | -0.051 |
Token | carry |
Token ID | 3283 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
bead | +0.328 |
can | +0.317 |
aid | +0.316 |
wand | +0.282 |
gently | +0.267 |
Neg logit contributions | |
Fourth | -0.466 |
restaurants | -0.432 |
ices | -0.428 |
site | -0.422 |
burgers | -0.406 |
Token | some |
Token ID | 617 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Fourth | +0.051 |
restaurants | +0.046 |
site | +0.046 |
ices | +0.045 |
burgers | +0.045 |
Neg logit contributions | |
bead | -0.048 |
aid | -0.047 |
can | -0.043 |
wand | -0.042 |
och | -0.040 |
Token | leaves |
Token ID | 5667 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
Fourth | +0.271 |
restaurants | +0.243 |
burgers | +0.243 |
site | +0.242 |
films | +0.232 |
Neg logit contributions | |
aid | -0.281 |
bead | -0.267 |
och | -0.251 |
tweet | -0.238 |
clip | -0.236 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
aid | +0.069 |
bead | +0.064 |
wand | +0.055 |
can | +0.055 |
diary | +0.055 |
Neg logit contributions | |
Fourth | -0.092 |
site | -0.083 |
ales | -0.083 |
ices | -0.081 |
restaurants | -0.080 |
Token | We |
Token ID | 775 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
bead | +0.019 |
aid | +0.019 |
can | +0.017 |
wand | +0.017 |
bud | +0.016 |
Neg logit contributions | |
Fourth | -0.021 |
restaurants | -0.018 |
ices | -0.018 |
Everyone | -0.017 |
dogs | -0.017 |
Token | can |
Token ID | 460 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Fourth | +0.163 |
restaurants | +0.148 |
ices | +0.148 |
outskirts | +0.144 |
banks | +0.143 |
Neg logit contributions | |
bead | -0.042 |
aid | -0.039 |
arl | -0.028 |
och | -0.027 |
wand | -0.026 |
Token | make |
Token ID | 787 |
Feature activation | -2.95e-03 |
Pos logit contributions | |
bead | +0.320 |
can | +0.312 |
aid | +0.308 |
wand | +0.275 |
gently | +0.261 |
Neg logit contributions | |
Fourth | -0.472 |
restaurants | -0.439 |
ices | -0.436 |
site | -0.429 |
burgers | -0.413 |
Token | it |
Token ID | 340 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
Fourth | +0.007 |
ices | +0.006 |
restaurants | +0.006 |
site | +0.006 |
oving | +0.006 |
Neg logit contributions | |
bead | -0.004 |
can | -0.004 |
aid | -0.004 |
wand | -0.003 |
gently | -0.003 |
Token | stronger |
Token ID | 7387 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
aid | +0.011 |
bead | +0.010 |
och | +0.010 |
can | +0.009 |
wand | +0.009 |
Neg logit contributions | |
Fourth | -0.015 |
restaurants | -0.013 |
ics | -0.013 |
site | -0.013 |
urg | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +3.52e-03 |
Pos logit contributions | |
aid | +0.061 |
bead | +0.058 |
can | +0.050 |
wand | +0.050 |
och | +0.050 |
Neg logit contributions | |
Fourth | -0.090 |
restaurants | -0.087 |
site | -0.086 |
ices | -0.086 |
burgers | -0.083 |
Token | bigger |
Token ID | 5749 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
bead | +0.005 |
och | +0.004 |
aid | +0.004 |
arl | +0.004 |
ig | +0.004 |
Neg logit contributions | |
Fourth | -0.007 |
restaurants | -0.007 |
burgers | -0.007 |
site | -0.007 |
outskirts | -0.006 |
Token | parents |
Token ID | 3397 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
can | +0.129 |
bead | +0.126 |
aid | +0.118 |
wand | +0.113 |
gently | +0.108 |
Neg logit contributions | |
Fourth | -0.165 |
ices | -0.158 |
restaurants | -0.155 |
oving | -0.151 |
site | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
Fourth | +0.132 |
restaurants | +0.124 |
ices | +0.123 |
site | +0.122 |
burgers | +0.119 |
Neg logit contributions | |
bead | -0.051 |
aid | -0.049 |
can | -0.048 |
wand | -0.041 |
gently | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
can | +0.018 |
bead | +0.014 |
gently | +0.014 |
aid | +0.013 |
hug | +0.012 |
Neg logit contributions | |
Fourth | -0.037 |
oving | -0.037 |
ices | -0.037 |
urg | -0.036 |
site | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
Fourth | +0.006 |
urg | +0.006 |
restaurants | +0.006 |
dogs | +0.006 |
burgers | +0.006 |
Neg logit contributions | |
can | -0.003 |
bead | -0.002 |
aid | -0.002 |
gently | -0.002 |
will | -0.002 |
Token | L |
Token ID | 43 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
Fourth | +0.003 |
restaurants | +0.003 |
ices | +0.003 |
site | +0.003 |
outskirts | +0.003 |
Neg logit contributions | |
bead | -0.002 |
aid | -0.002 |
can | -0.002 |
wand | -0.001 |
gently | -0.001 |
Token | ily |
Token ID | 813 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
bead | +0.073 |
can | +0.069 |
aid | +0.069 |
wand | +0.057 |
gently | +0.052 |
Neg logit contributions | |
Fourth | -0.200 |
restaurants | -0.188 |
ices | -0.186 |
site | -0.185 |
burgers | -0.180 |
Token | was |
Token ID | 373 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
can | +0.170 |
bead | +0.145 |
gently | +0.145 |
aid | +0.134 |
c | +0.134 |
Neg logit contributions | |
Fourth | -0.351 |
ices | -0.323 |
restaurants | -0.315 |
dogs | -0.311 |
urg | -0.309 |
Token | very |
Token ID | 845 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
Fourth | +0.115 |
ices | +0.113 |
site | +0.107 |
restaurants | +0.107 |
ales | +0.106 |
Neg logit contributions | |
can | -0.040 |
bead | -0.040 |
aid | -0.038 |
gently | -0.035 |
wand | -0.034 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
can | +0.067 |
bead | +0.065 |
aid | +0.064 |
gently | +0.059 |
wand | +0.055 |
Neg logit contributions | |
Fourth | -0.135 |
ices | -0.132 |
restaurants | -0.126 |
site | -0.125 |
dogs | -0.122 |
Token | to |
Token ID | 284 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
Fourth | +0.307 |
ices | +0.290 |
oving | +0.287 |
site | +0.286 |
restaurants | +0.286 |
Neg logit contributions | |
can | -0.063 |
bead | -0.051 |
aid | -0.043 |
too | -0.042 |
gently | -0.040 |
Token | see |
Token ID | 766 |
Feature activation | +6.31e-03 |
Pos logit contributions | |
can | +0.018 |
hug | +0.015 |
bead | +0.015 |
aid | +0.014 |
gently | +0.014 |
Neg logit contributions | |
ices | -0.038 |
Fourth | -0.037 |
oving | -0.036 |
umm | -0.036 |
site | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
Fourth | +0.052 |
ices | +0.050 |
site | +0.047 |
oving | +0.047 |
burgers | +0.047 |
Neg logit contributions | |
bead | -0.032 |
aid | -0.029 |
can | -0.028 |
wand | -0.024 |
thread | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
bead | +0.064 |
aid | +0.063 |
can | +0.060 |
wand | +0.059 |
necklace | +0.054 |
Neg logit contributions | |
Fourth | -0.058 |
ices | -0.052 |
restaurants | -0.052 |
Everyone | -0.051 |
site | -0.050 |
Token | takes |
Token ID | 2753 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
bead | +0.121 |
aid | +0.120 |
och | +0.103 |
can | +0.097 |
wand | +0.095 |
Neg logit contributions | |
Fourth | -0.167 |
restaurants | -0.160 |
site | -0.156 |
ices | -0.156 |
burgers | -0.153 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
bead | +0.065 |
can | +0.064 |
aid | +0.063 |
wand | +0.056 |
gently | +0.054 |
Neg logit contributions | |
Fourth | -0.097 |
restaurants | -0.090 |
ices | -0.090 |
site | -0.089 |
oving | -0.087 |
Token | cup |
Token ID | 6508 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
Fourth | +0.002 |
burgers | +0.002 |
restaurants | +0.002 |
dogs | +0.002 |
site | +0.002 |
Neg logit contributions | |
aid | -0.002 |
bead | -0.002 |
ig | -0.001 |
gently | -0.001 |
och | -0.001 |
Token | away |
Token ID | 1497 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Fourth | +0.120 |
ices | +0.111 |
site | +0.111 |
burgers | +0.111 |
restaurants | +0.108 |
Neg logit contributions | |
bead | -0.089 |
can | -0.081 |
aid | -0.080 |
wand | -0.076 |
ti | -0.069 |
Token | from |
Token ID | 422 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
bead | +0.187 |
aid | +0.181 |
can | +0.177 |
wand | +0.159 |
bracelet | +0.141 |
Neg logit contributions | |
Fourth | -0.292 |
ices | -0.272 |
restaurants | -0.269 |
site | -0.269 |
burgers | -0.260 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
Fourth | +0.121 |
ices | +0.115 |
restaurants | +0.111 |
site | +0.109 |
oving | +0.109 |
Neg logit contributions | |
bead | -0.081 |
can | -0.080 |
aid | -0.076 |
gently | -0.071 |
wand | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
Fourth | +0.031 |
ices | +0.030 |
restaurants | +0.030 |
site | +0.029 |
burgers | +0.029 |
Neg logit contributions | |
bead | -0.022 |
aid | -0.022 |
can | -0.019 |
wand | -0.018 |
bracelet | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
bead | +0.040 |
aid | +0.038 |
can | +0.038 |
wand | +0.035 |
gently | +0.032 |
Neg logit contributions | |
Fourth | -0.047 |
restaurants | -0.043 |
ices | -0.043 |
site | -0.042 |
burgers | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
bead | +0.017 |
can | +0.017 |
aid | +0.017 |
wand | +0.015 |
gently | +0.014 |
Neg logit contributions | |
Fourth | -0.026 |
restaurants | -0.024 |
ices | -0.024 |
site | -0.023 |
burgers | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
aid | +0.232 |
bead | +0.226 |
clip | +0.186 |
och | +0.181 |
wand | +0.179 |
Neg logit contributions | |
Fourth | -0.254 |
Joe | -0.231 |
Everyone | -0.228 |
restaurants | -0.228 |
John | -0.227 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
bead | +0.016 |
aid | +0.016 |
wand | +0.015 |
can | +0.014 |
och | +0.014 |
Neg logit contributions | |
Fourth | -0.012 |
restaurants | -0.011 |
burgers | -0.010 |
Andrew | -0.010 |
site | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
Fourth | +0.033 |
John | +0.031 |
Joe | +0.031 |
ices | +0.031 |
Andrew | +0.031 |
Neg logit contributions | |
aid | -0.034 |
bead | -0.033 |
wand | -0.028 |
och | -0.028 |
clip | -0.027 |
Token | I |
Token ID | 314 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
bead | +0.021 |
aid | +0.020 |
wand | +0.019 |
can | +0.018 |
gently | +0.017 |
Neg logit contributions | |
Fourth | -0.036 |
restaurants | -0.032 |
Everyone | -0.031 |
ices | -0.031 |
outskirts | -0.031 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
bead | +0.163 |
aid | +0.149 |
wand | +0.141 |
can | +0.138 |
och | +0.132 |
Neg logit contributions | |
Fourth | -0.209 |
ices | -0.194 |
restaurants | -0.188 |
oving | -0.188 |
burgers | -0.181 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
bead | +0.028 |
can | +0.026 |
aid | +0.026 |
wand | +0.022 |
gently | +0.020 |
Neg logit contributions | |
Fourth | -0.060 |
restaurants | -0.056 |
site | -0.054 |
ices | -0.054 |
burgers | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
aid | +0.230 |
bead | +0.222 |
clip | +0.187 |
och | +0.185 |
wand | +0.178 |
Neg logit contributions | |
Fourth | -0.250 |
Everyone | -0.228 |
Joe | -0.217 |
burgers | -0.216 |
restaurants | -0.214 |
Token | I |
Token ID | 314 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
bead | +0.020 |
aid | +0.019 |
wand | +0.018 |
bud | +0.017 |
can | +0.017 |
Neg logit contributions | |
Fourth | -0.032 |
Everyone | -0.029 |
restaurants | -0.029 |
Jon | -0.028 |
outskirts | -0.028 |
Token | should |
Token ID | 815 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
bead | +0.169 |
aid | +0.152 |
wand | +0.147 |
och | +0.140 |
can | +0.138 |
Neg logit contributions | |
Fourth | -0.198 |
ices | -0.182 |
oving | -0.180 |
restaurants | -0.176 |
burgers | -0.171 |
Token | have |
Token ID | 423 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
bead | +0.104 |
aid | +0.100 |
wand | +0.091 |
can | +0.090 |
och | +0.084 |
Neg logit contributions | |
Fourth | -0.142 |
restaurants | -0.132 |
site | -0.125 |
ics | -0.124 |
oving | -0.123 |
Token | told |
Token ID | 1297 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
bead | +0.149 |
aid | +0.145 |
can | +0.144 |
wand | +0.125 |
gently | +0.122 |
Neg logit contributions | |
Fourth | -0.236 |
restaurants | -0.220 |
ices | -0.219 |
site | -0.215 |
burgers | -0.207 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
aid | +0.016 |
bead | +0.016 |
can | +0.013 |
wand | +0.013 |
och | +0.012 |
Neg logit contributions | |
Fourth | -0.025 |
restaurants | -0.024 |
site | -0.022 |
ices | -0.022 |
burgers | -0.022 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
aid | +0.107 |
bead | +0.103 |
wand | +0.080 |
arl | +0.080 |
och | +0.077 |
Neg logit contributions | |
Fourth | -0.156 |
restaurants | -0.150 |
site | -0.146 |
ics | -0.145 |
ices | -0.143 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-03 |
Pos logit contributions | |
Fourth | +0.031 |
restaurants | +0.028 |
Everyone | +0.027 |
site | +0.027 |
ices | +0.027 |
Neg logit contributions | |
bead | -0.033 |
aid | -0.032 |
can | -0.031 |
wand | -0.031 |
bud | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
Fourth | +0.007 |
Everyone | +0.007 |
ices | +0.007 |
restaurants | +0.007 |
site | +0.006 |
Neg logit contributions | |
bead | -0.009 |
can | -0.009 |
wand | -0.009 |
aid | -0.009 |
clip | -0.008 |
Token | L |
Token ID | 43 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
Everyone | +0.006 |
Fourth | +0.006 |
ices | +0.006 |
oving | +0.006 |
outskirts | +0.006 |
Neg logit contributions | |
wand | -0.006 |
can | -0.006 |
bead | -0.005 |
endant | -0.005 |
aid | -0.005 |
Token | ily |
Token ID | 813 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
can | +0.122 |
bead | +0.116 |
wand | +0.112 |
aid | +0.109 |
gently | +0.106 |
Neg logit contributions | |
ices | -0.156 |
Fourth | -0.151 |
site | -0.140 |
restaurants | -0.140 |
urg | -0.137 |
Token | nodded |
Token ID | 14464 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
bead | +0.199 |
aid | +0.194 |
can | +0.171 |
wand | +0.160 |
och | +0.159 |
Neg logit contributions | |
Fourth | -0.288 |
restaurants | -0.274 |
site | -0.273 |
ices | -0.271 |
outskirts | -0.267 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
bead | +0.183 |
aid | +0.179 |
och | +0.165 |
can | +0.157 |
endant | +0.151 |
Neg logit contributions | |
Fourth | -0.180 |
ices | -0.163 |
urg | -0.160 |
films | -0.157 |
restaurants | -0.156 |
Token | She |
Token ID | 1375 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
aid | +0.032 |
bead | +0.030 |
wand | +0.028 |
can | +0.027 |
cape | +0.027 |
Neg logit contributions | |
Everyone | -0.026 |
Fourth | -0.025 |
People | -0.024 |
Everybody | -0.023 |
Joe | -0.023 |
Token | said |
Token ID | 531 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
bead | +0.102 |
aid | +0.095 |
can | +0.093 |
wand | +0.088 |
arl | +0.087 |
Neg logit contributions | |
Fourth | -0.118 |
ices | -0.108 |
restaurants | -0.107 |
site | -0.107 |
burgers | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
Everyone | +0.069 |
Fourth | +0.062 |
John | +0.061 |
People | +0.060 |
Joe | +0.059 |
Neg logit contributions | |
bead | -0.080 |
aid | -0.077 |
och | -0.071 |
clip | -0.070 |
thread | -0.069 |
Token | I |
Token ID | 40 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
bead | +0.003 |
can | +0.003 |
aid | +0.003 |
wand | +0.003 |
bud | +0.003 |
Neg logit contributions | |
Fourth | -0.005 |
ices | -0.005 |
restaurants | -0.004 |
site | -0.004 |
dogs | -0.004 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
bead | +0.085 |
aid | +0.077 |
wand | +0.067 |
och | +0.067 |
thread | +0.066 |
Neg logit contributions | |
Fourth | -0.102 |
ices | -0.089 |
restaurants | -0.088 |
Jon | -0.083 |
oving | -0.083 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
bead | +0.037 |
aid | +0.035 |
can | +0.034 |
wand | +0.031 |
gently | +0.029 |
Neg logit contributions | |
Fourth | -0.058 |
restaurants | -0.053 |
ices | -0.052 |
site | -0.052 |
outskirts | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | +8.06e-03 |
Pos logit contributions | |
aid | +0.056 |
bead | +0.055 |
clip | +0.049 |
och | +0.047 |
wand | +0.043 |
Neg logit contributions | |
Fourth | -0.072 |
Joe | -0.069 |
John | -0.066 |
Joey | -0.066 |
Everyone | -0.066 |
Token | help |
Token ID | 1037 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
bead | +0.013 |
aid | +0.013 |
wand | +0.011 |
can | +0.011 |
och | +0.011 |
Neg logit contributions | |
Fourth | -0.016 |
restaurants | -0.014 |
site | -0.014 |
Everyone | -0.013 |
outskirts | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
bead | +0.130 |
aid | +0.126 |
can | +0.122 |
wand | +0.106 |
gently | +0.097 |
Neg logit contributions | |
Fourth | -0.250 |
restaurants | -0.234 |
ices | -0.232 |
site | -0.229 |
oving | -0.222 |
Token | Friends |
Token ID | 14213 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
bead | +0.016 |
aid | +0.016 |
can | +0.014 |
wand | +0.014 |
clip | +0.013 |
Neg logit contributions | |
Fourth | -0.024 |
ices | -0.022 |
restaurants | -0.022 |
Everyone | -0.022 |
site | -0.021 |
Token | always |
Token ID | 1464 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
Fourth | +0.154 |
Everyone | +0.132 |
outskirts | +0.132 |
restaurants | +0.132 |
oving | +0.130 |
Neg logit contributions | |
bead | -0.099 |
aid | -0.096 |
endant | -0.076 |
och | -0.075 |
paste | -0.072 |
Token | help |
Token ID | 1037 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
bead | +0.082 |
aid | +0.078 |
och | +0.070 |
paste | +0.066 |
wand | +0.065 |
Neg logit contributions | |
Fourth | -0.090 |
restaurants | -0.083 |
oving | -0.078 |
outskirts | -0.076 |
ices | -0.075 |
Token | each |
Token ID | 1123 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
can | +0.179 |
bead | +0.166 |
aid | +0.160 |
gently | +0.159 |
wand | +0.153 |
Neg logit contributions | |
Fourth | -0.206 |
dogs | -0.189 |
restaurants | -0.188 |
ices | -0.186 |
site | -0.184 |
Token | other |
Token ID | 584 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
Fourth | +0.336 |
urg | +0.318 |
oving | +0.316 |
dogs | +0.316 |
site | +0.313 |
Neg logit contributions | |
can | -0.237 |
bead | -0.226 |
aid | -0.211 |
fairy | -0.208 |
gently | -0.201 |
Token | smiled |
Token ID | 13541 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
bead | +0.035 |
aid | +0.034 |
can | +0.032 |
wand | +0.030 |
arl | +0.029 |
Neg logit contributions | |
Fourth | -0.043 |
restaurants | -0.040 |
ices | -0.039 |
site | -0.039 |
outskirts | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
aid | +0.114 |
bead | +0.114 |
can | +0.104 |
wand | +0.089 |
och | +0.089 |
Neg logit contributions | |
Fourth | -0.188 |
ices | -0.172 |
urg | -0.167 |
restaurants | -0.167 |
site | -0.166 |
Token | himself |
Token ID | 2241 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
can | +0.017 |
bead | +0.016 |
aid | +0.016 |
gently | +0.014 |
wand | +0.014 |
Neg logit contributions | |
Fourth | -0.021 |
ices | -0.020 |
restaurants | -0.019 |
site | -0.019 |
oving | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -8.07e-04 |
Pos logit contributions | |
Fourth | +0.031 |
site | +0.029 |
ices | +0.029 |
restaurants | +0.028 |
outskirts | +0.027 |
Neg logit contributions | |
aid | -0.022 |
bead | -0.022 |
can | -0.019 |
arl | -0.017 |
och | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | -7.28e-03 |
Pos logit contributions | |
Fourth | +0.002 |
restaurants | +0.002 |
ices | +0.002 |
site | +0.001 |
burgers | +0.001 |
Neg logit contributions | |
bead | -0.001 |
can | -0.001 |
aid | -0.001 |
wand | -0.001 |
gently | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | +5.47e-03 |
Pos logit contributions | |
Fourth | +0.014 |
restaurants | +0.013 |
ices | +0.013 |
site | +0.013 |
outskirts | +0.013 |
Neg logit contributions | |
bead | -0.011 |
aid | -0.011 |
can | -0.010 |
wand | -0.010 |
arl | -0.009 |
Token | home |
Token ID | 1363 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
bead | +0.009 |
aid | +0.008 |
can | +0.008 |
thread | +0.007 |
wand | +0.006 |
Neg logit contributions | |
Fourth | -0.011 |
restaurants | -0.011 |
site | -0.010 |
outskirts | -0.010 |
ices | -0.010 |
Token | with |
Token ID | 351 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
Fourth | +0.074 |
restaurants | +0.070 |
site | +0.070 |
ices | +0.068 |
ics | +0.065 |
Neg logit contributions | |
bead | -0.055 |
can | -0.052 |
aid | -0.052 |
wand | -0.045 |
thread | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
Fourth | +0.184 |
restaurants | +0.171 |
ices | +0.169 |
site | +0.167 |
burgers | +0.160 |
Neg logit contributions | |
bead | -0.135 |
can | -0.131 |
aid | -0.130 |
wand | -0.116 |
gently | -0.110 |
Token | new |
Token ID | 649 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
bead | +0.024 |
aid | +0.022 |
can | +0.020 |
arl | +0.020 |
ppy | +0.019 |
Neg logit contributions | |
Fourth | -0.028 |
restaurants | -0.025 |
burgers | -0.024 |
Father | -0.024 |
cinema | -0.023 |
Token | found |
Token ID | 1043 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
aid | +0.041 |
bead | +0.039 |
can | +0.037 |
och | +0.036 |
arl | +0.034 |
Neg logit contributions | |
Fourth | -0.046 |
ices | -0.039 |
restaurants | -0.039 |
site | -0.038 |
youngest | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
can | +0.027 |
bead | +0.027 |
aid | +0.025 |
wand | +0.024 |
gently | +0.024 |
Neg logit contributions | |
Fourth | -0.019 |
restaurants | -0.018 |
ices | -0.018 |
site | -0.017 |
oving | -0.017 |
Token | are |
Token ID | 389 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
Fourth | +0.129 |
restaurants | +0.123 |
outskirts | +0.114 |
banks | +0.112 |
burgers | +0.112 |
Neg logit contributions | |
bead | -0.112 |
aid | -0.108 |
och | -0.098 |
wand | -0.095 |
arl | -0.092 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
bead | +0.080 |
can | +0.075 |
aid | +0.075 |
wand | +0.065 |
och | +0.064 |
Neg logit contributions | |
Fourth | -0.127 |
restaurants | -0.117 |
burgers | -0.115 |
site | -0.113 |
oving | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
aid | +0.047 |
bead | +0.047 |
can | +0.041 |
och | +0.041 |
wand | +0.039 |
Neg logit contributions | |
Fourth | -0.070 |
restaurants | -0.068 |
ices | -0.066 |
burgers | -0.065 |
site | -0.065 |
Token | They |
Token ID | 1119 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
can | +0.021 |
bead | +0.020 |
aid | +0.019 |
gently | +0.018 |
wand | +0.018 |
Neg logit contributions | |
Fourth | -0.019 |
restaurants | -0.018 |
ices | -0.018 |
site | -0.018 |
ics | -0.017 |
Token | are |
Token ID | 389 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
Fourth | +0.124 |
restaurants | +0.117 |
outskirts | +0.110 |
asted | +0.107 |
banks | +0.107 |
Neg logit contributions | |
bead | -0.109 |
aid | -0.103 |
och | -0.100 |
wand | -0.094 |
diary | -0.090 |
Token | friends |
Token ID | 2460 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
bead | +0.078 |
can | +0.075 |
aid | +0.074 |
wand | +0.065 |
och | +0.060 |
Neg logit contributions | |
Fourth | -0.128 |
restaurants | -0.118 |
ices | -0.114 |
site | -0.114 |
burgers | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
Fourth | +0.064 |
ices | +0.063 |
restaurants | +0.060 |
John | +0.060 |
burgers | +0.059 |
Neg logit contributions | |
aid | -0.072 |
bead | -0.069 |
arl | -0.066 |
thread | -0.065 |
wand | -0.063 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
can | +0.015 |
bead | +0.015 |
aid | +0.014 |
wand | +0.013 |
gently | +0.012 |
Neg logit contributions | |
Fourth | -0.019 |
restaurants | -0.018 |
ices | -0.017 |
site | -0.017 |
oving | -0.017 |
Token | Anna |
Token ID | 31160 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
aid | +0.139 |
bead | +0.134 |
wand | +0.126 |
clip | +0.125 |
can | +0.123 |
Neg logit contributions | |
Fourth | -0.084 |
restaurants | -0.083 |
ices | -0.082 |
site | -0.074 |
ics | -0.070 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
aid | +0.206 |
bead | +0.200 |
och | +0.167 |
wand | +0.167 |
bracelet | +0.159 |
Neg logit contributions | |
Fourth | -0.293 |
restaurants | -0.290 |
ices | -0.273 |
site | -0.265 |
dogs | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
Fourth | +0.068 |
ices | +0.065 |
site | +0.063 |
restaurants | +0.061 |
John | +0.061 |
Neg logit contributions | |
aid | -0.068 |
bead | -0.064 |
arl | -0.061 |
thread | -0.056 |
wand | -0.055 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
bead | +0.023 |
can | +0.022 |
aid | +0.022 |
wand | +0.020 |
gently | +0.019 |
Neg logit contributions | |
Fourth | -0.019 |
restaurants | -0.018 |
ices | -0.017 |
site | -0.017 |
burgers | -0.016 |
Token | L |
Token ID | 43 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
aid | +0.131 |
bead | +0.127 |
can | +0.117 |
wand | +0.117 |
clip | +0.114 |
Neg logit contributions | |
Fourth | -0.092 |
restaurants | -0.088 |
ices | -0.087 |
site | -0.082 |
ics | -0.077 |
Token | ily |
Token ID | 813 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
bead | +0.097 |
can | +0.094 |
aid | +0.092 |
wand | +0.079 |
gently | +0.075 |
Neg logit contributions | |
Fourth | -0.194 |
restaurants | -0.180 |
ices | -0.179 |
site | -0.177 |
oving | -0.174 |
Token | was |
Token ID | 373 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
bead | +0.203 |
aid | +0.199 |
can | +0.188 |
wand | +0.176 |
gently | +0.160 |
Neg logit contributions | |
Fourth | -0.291 |
restaurants | -0.273 |
ices | -0.268 |
site | -0.265 |
outskirts | -0.254 |
Token | very |
Token ID | 845 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
Fourth | +0.108 |
ices | +0.103 |
restaurants | +0.102 |
site | +0.101 |
oving | +0.096 |
Neg logit contributions | |
bead | -0.069 |
can | -0.067 |
aid | -0.065 |
wand | -0.060 |
gently | -0.057 |
Token | hungry |
Token ID | 14720 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
bead | +0.076 |
can | +0.074 |
aid | +0.073 |
wand | +0.065 |
gently | +0.063 |
Neg logit contributions | |
Fourth | -0.105 |
restaurants | -0.098 |
ices | -0.097 |
site | -0.095 |
burgers | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +5.06e-03 |
Pos logit contributions | |
Fourth | +0.191 |
restaurants | +0.180 |
ices | +0.179 |
site | +0.177 |
burgers | +0.172 |
Neg logit contributions | |
aid | -0.087 |
bead | -0.087 |
can | -0.080 |
wand | -0.070 |
gently | -0.063 |
Token | She |
Token ID | 1375 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
aid | +0.007 |
bead | +0.007 |
can | +0.007 |
wand | +0.007 |
gently | +0.006 |
Neg logit contributions | |
Fourth | -0.010 |
restaurants | -0.010 |
ices | -0.010 |
site | -0.009 |
outskirts | -0.009 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
bead | +0.078 |
can | +0.075 |
aid | +0.075 |
wand | +0.067 |
gently | +0.063 |
Neg logit contributions | |
Fourth | -0.115 |
restaurants | -0.107 |
ices | -0.106 |
site | -0.105 |
burgers | -0.101 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
oving | +0.105 |
Fourth | +0.104 |
ices | +0.100 |
ales | +0.098 |
urg | +0.098 |
Neg logit contributions | |
can | -0.028 |
bead | -0.028 |
aid | -0.023 |
gently | -0.022 |
c | -0.022 |
Token | merry |
Token ID | 44570 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
aid | +0.034 |
bead | +0.030 |
can | +0.029 |
och | +0.026 |
arl | +0.026 |
Neg logit contributions | |
Fourth | -0.034 |
site | -0.033 |
restaurants | -0.031 |
outskirts | -0.031 |
burgers | -0.030 |
Token | chase |
Token ID | 15505 |
Feature activation | +6.33e-04 |
Pos logit contributions | |
bead | +0.085 |
can | +0.081 |
aid | +0.080 |
wand | +0.074 |
gently | +0.071 |
Neg logit contributions | |
Fourth | -0.110 |
restaurants | -0.103 |
ices | -0.102 |
site | -0.098 |
burgers | -0.097 |
Token | around |
Token ID | 1088 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
aid | +0.001 |
bead | +0.001 |
can | +0.001 |
wand | +0.001 |
och | +0.001 |
Neg logit contributions | |
ices | -0.001 |
Fourth | -0.001 |
restaurants | -0.001 |
site | -0.001 |
burgers | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
Fourth | +0.100 |
restaurants | +0.094 |
ices | +0.094 |
site | +0.093 |
outskirts | +0.087 |
Neg logit contributions | |
aid | -0.083 |
bead | -0.079 |
can | -0.073 |
wand | -0.065 |
och | -0.065 |
Token | garden |
Token ID | 11376 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
aid | +0.003 |
bead | +0.003 |
can | +0.003 |
arl | +0.002 |
och | +0.002 |
Neg logit contributions | |
Fourth | -0.002 |
restaurants | -0.002 |
site | -0.002 |
outskirts | -0.002 |
youngest | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
aid | +0.010 |
bead | +0.010 |
can | +0.009 |
wand | +0.008 |
och | +0.007 |
Neg logit contributions | |
Fourth | -0.022 |
ices | -0.020 |
restaurants | -0.020 |
site | -0.020 |
burgers | -0.019 |
Token | all |
Token ID | 477 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
aid | +0.032 |
bead | +0.032 |
can | +0.028 |
och | +0.026 |
wand | +0.026 |
Neg logit contributions | |
Fourth | -0.036 |
restaurants | -0.034 |
site | -0.033 |
outskirts | -0.032 |
burgers | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
Fourth | +0.279 |
restaurants | +0.258 |
ices | +0.255 |
site | +0.247 |
ics | +0.240 |
Neg logit contributions | |
bead | -0.250 |
aid | -0.247 |
can | -0.235 |
wand | -0.221 |
clip | -0.209 |
Token | way |
Token ID | 835 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
Fourth | +0.002 |
restaurants | +0.002 |
ices | +0.002 |
site | +0.002 |
burgers | +0.002 |
Neg logit contributions | |
aid | -0.003 |
bead | -0.003 |
can | -0.003 |
och | -0.003 |
clip | -0.003 |
Token | around |
Token ID | 1088 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
Fourth | +0.186 |
ices | +0.168 |
restaurants | +0.165 |
ics | +0.164 |
site | +0.163 |
Neg logit contributions | |
aid | -0.122 |
bead | -0.117 |
can | -0.104 |
wand | -0.097 |
thread | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
Fourth | +0.110 |
restaurants | +0.104 |
ices | +0.104 |
site | +0.102 |
outskirts | +0.096 |
Neg logit contributions | |
aid | -0.079 |
bead | -0.074 |
can | -0.065 |
wand | -0.061 |
clip | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
Fourth | +0.002 |
restaurants | +0.002 |
ices | +0.002 |
site | +0.002 |
burgers | +0.002 |
Neg logit contributions | |
bead | -0.002 |
aid | -0.002 |
can | -0.002 |
wand | -0.002 |
och | -0.001 |
Token | garden |
Token ID | 11376 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
Fourth | +0.029 |
restaurants | +0.026 |
site | +0.026 |
burgers | +0.025 |
outskirts | +0.025 |
Neg logit contributions | |
aid | -0.036 |
bead | -0.033 |
can | -0.031 |
och | -0.030 |
arl | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
Fourth | +0.017 |
restaurants | +0.016 |
ices | +0.016 |
site | +0.016 |
burgers | +0.015 |
Neg logit contributions | |
aid | -0.009 |
bead | -0.009 |
can | -0.008 |
wand | -0.007 |
bud | -0.006 |
Token | find |
Token ID | 1064 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
bead | +0.008 |
aid | +0.008 |
can | +0.008 |
wand | +0.007 |
gently | +0.007 |
Neg logit contributions | |
Fourth | -0.011 |
restaurants | -0.010 |
ices | -0.010 |
site | -0.010 |
outskirts | -0.010 |
Token | some |
Token ID | 617 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Fourth | +0.079 |
restaurants | +0.074 |
ices | +0.073 |
site | +0.070 |
burgers | +0.069 |
Neg logit contributions | |
bead | -0.067 |
aid | -0.065 |
can | -0.064 |
wand | -0.058 |
clip | -0.056 |
Token | y |
Token ID | 331 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
Fourth | +0.259 |
restaurants | +0.245 |
burgers | +0.237 |
ices | +0.231 |
site | +0.219 |
Neg logit contributions | |
aid | -0.288 |
bead | -0.275 |
och | -0.269 |
arl | -0.253 |
clip | -0.253 |
Token | ummy |
Token ID | 13513 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Fourth | +0.043 |
site | +0.036 |
restaurants | +0.036 |
ices | +0.034 |
outskirts | +0.034 |
Neg logit contributions | |
bead | -0.098 |
can | -0.096 |
aid | -0.094 |
wand | -0.089 |
gently | -0.087 |
Token | carrots |
Token ID | 34397 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
Fourth | +0.357 |
restaurants | +0.342 |
ices | +0.325 |
burgers | +0.324 |
dogs | +0.314 |
Neg logit contributions | |
bead | -0.441 |
aid | -0.437 |
can | -0.408 |
wand | -0.387 |
clip | -0.382 |
Token | to |
Token ID | 284 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Fourth | +0.098 |
restaurants | +0.091 |
ices | +0.090 |
site | +0.088 |
burgers | +0.088 |
Neg logit contributions | |
aid | -0.053 |
bead | -0.052 |
can | -0.046 |
wand | -0.043 |
thread | -0.040 |
Token | m |
Token ID | 285 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
bead | +0.032 |
aid | +0.031 |
can | +0.031 |
wand | +0.028 |
gently | +0.027 |
Neg logit contributions | |
Fourth | -0.034 |
restaurants | -0.031 |
ices | -0.030 |
site | -0.030 |
burgers | -0.029 |
Token | unch |
Token ID | 3316 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Fourth | +0.084 |
restaurants | +0.072 |
site | +0.071 |
outskirts | +0.070 |
youngest | +0.067 |
Neg logit contributions | |
aid | -0.092 |
bead | -0.087 |
can | -0.083 |
och | -0.076 |
gently | -0.075 |
Token | So |
Token ID | 1406 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
can | +0.014 |
gently | +0.013 |
bead | +0.012 |
aid | +0.011 |
too | +0.011 |
Neg logit contributions | |
Fourth | -0.019 |
restaurants | -0.018 |
ices | -0.017 |
urg | -0.017 |
oving | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
Fourth | +0.173 |
restaurants | +0.162 |
ices | +0.161 |
site | +0.160 |
burgers | +0.155 |
Neg logit contributions | |
bead | -0.068 |
aid | -0.065 |
can | -0.064 |
wand | -0.054 |
gently | -0.049 |
Token | they |
Token ID | 484 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
can | +0.013 |
bead | +0.011 |
gently | +0.011 |
aid | +0.011 |
too | +0.010 |
Neg logit contributions | |
Fourth | -0.027 |
ices | -0.026 |
urg | -0.025 |
oving | -0.025 |
restaurants | -0.025 |
Token | played |
Token ID | 2826 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
Fourth | +0.183 |
restaurants | +0.169 |
ices | +0.168 |
site | +0.165 |
oving | +0.158 |
Neg logit contributions | |
bead | -0.147 |
can | -0.144 |
aid | -0.142 |
wand | -0.128 |
gently | -0.123 |
Token | without |
Token ID | 1231 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
bead | +0.074 |
aid | +0.072 |
can | +0.072 |
wand | +0.063 |
gently | +0.060 |
Neg logit contributions | |
Fourth | -0.103 |
restaurants | -0.096 |
ices | -0.095 |
site | -0.094 |
burgers | -0.090 |
Token | him |
Token ID | 683 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
Fourth | +0.233 |
ices | +0.213 |
restaurants | +0.212 |
site | +0.208 |
outskirts | +0.199 |
Neg logit contributions | |
bead | -0.202 |
can | -0.198 |
aid | -0.195 |
wand | -0.178 |
gently | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | +8.65e-03 |
Pos logit contributions | |
Fourth | +0.169 |
ices | +0.160 |
restaurants | +0.159 |
site | +0.155 |
burgers | +0.154 |
Neg logit contributions | |
bead | -0.096 |
aid | -0.096 |
can | -0.083 |
wand | -0.077 |
och | -0.069 |
Token | |
Token ID | 220 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
can | +0.011 |
gently | +0.009 |
too | +0.007 |
bead | +0.007 |
has | +0.007 |
Neg logit contributions | |
urg | -0.020 |
Fourth | -0.020 |
restaurants | -0.020 |
oving | -0.020 |
ics | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
Fourth | +0.053 |
restaurants | +0.052 |
urg | +0.050 |
dogs | +0.050 |
burgers | +0.050 |
Neg logit contributions | |
can | -0.020 |
aid | -0.016 |
bead | -0.016 |
gently | -0.015 |
forgive | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
Fourth | +0.015 |
urg | +0.015 |
umm | +0.015 |
restaurants | +0.015 |
dogs | +0.014 |
Neg logit contributions | |
can | -0.005 |
gently | -0.004 |
aid | -0.004 |
bead | -0.004 |
forgive | -0.003 |
Token | After |
Token ID | 3260 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
Fourth | +0.013 |
restaurants | +0.013 |
ices | +0.012 |
urg | +0.012 |
dogs | +0.012 |
Neg logit contributions | |
can | -0.008 |
aid | -0.008 |
bead | -0.007 |
gently | -0.007 |
wand | -0.006 |
Token | meant |
Token ID | 4001 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
Fourth | +0.003 |
restaurants | +0.003 |
site | +0.003 |
ices | +0.003 |
burgers | +0.003 |
Neg logit contributions | |
bead | -0.002 |
aid | -0.002 |
can | -0.002 |
wand | -0.002 |
gently | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
Fourth | +0.222 |
restaurants | +0.210 |
ices | +0.209 |
site | +0.205 |
oving | +0.201 |
Neg logit contributions | |
can | -0.080 |
bead | -0.080 |
aid | -0.074 |
wand | -0.064 |
gently | -0.059 |
Token | she |
Token ID | 673 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
bead | +0.012 |
can | +0.012 |
aid | +0.012 |
wand | +0.011 |
gently | +0.010 |
Neg logit contributions | |
Fourth | -0.017 |
ices | -0.016 |
restaurants | -0.016 |
site | -0.016 |
oving | -0.015 |
Token | told |
Token ID | 1297 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
can | +0.097 |
bead | +0.092 |
aid | +0.089 |
gently | +0.083 |
wand | +0.080 |
Neg logit contributions | |
Fourth | -0.156 |
restaurants | -0.147 |
ices | -0.146 |
site | -0.142 |
dogs | -0.140 |
Token | him |
Token ID | 683 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
Fourth | +0.123 |
ices | +0.115 |
restaurants | +0.111 |
site | +0.109 |
oving | +0.108 |
Neg logit contributions | |
can | -0.099 |
aid | -0.095 |
bead | -0.092 |
gently | -0.089 |
thread | -0.085 |
Token | that |
Token ID | 326 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
Fourth | +0.131 |
restaurants | +0.126 |
ices | +0.123 |
site | +0.121 |
burgers | +0.119 |
Neg logit contributions | |
bead | -0.111 |
aid | -0.107 |
can | -0.098 |
wand | -0.095 |
arl | -0.090 |
Token | it |
Token ID | 340 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
Fourth | +0.065 |
ices | +0.061 |
restaurants | +0.059 |
site | +0.059 |
oving | +0.058 |
Neg logit contributions | |
can | -0.044 |
bead | -0.043 |
aid | -0.041 |
wand | -0.037 |
gently | -0.035 |
Token | meant |
Token ID | 4001 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
can | +0.018 |
bead | +0.017 |
aid | +0.016 |
wand | +0.015 |
gently | +0.014 |
Neg logit contributions | |
Fourth | -0.027 |
restaurants | -0.026 |
ices | -0.025 |
site | -0.025 |
dogs | -0.024 |
Token | he |
Token ID | 339 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
Fourth | +0.173 |
restaurants | +0.160 |
site | +0.156 |
ices | +0.154 |
burgers | +0.154 |
Neg logit contributions | |
bead | -0.140 |
aid | -0.137 |
can | -0.121 |
wand | -0.117 |
och | -0.110 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
bead | +0.012 |
aid | +0.012 |
can | +0.011 |
wand | +0.011 |
gently | +0.010 |
Neg logit contributions | |
Fourth | -0.016 |
restaurants | -0.015 |
ices | -0.014 |
site | -0.014 |
oving | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
Fourth | +0.031 |
restaurants | +0.029 |
ices | +0.029 |
burgers | +0.027 |
site | +0.027 |
Neg logit contributions | |
can | -0.023 |
bead | -0.022 |
aid | -0.021 |
gently | -0.019 |
wand | -0.019 |
Token | little |
Token ID | 1310 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
bead | +0.033 |
aid | +0.032 |
can | +0.029 |
clip | +0.028 |
gently | +0.028 |
Neg logit contributions | |
Fourth | -0.031 |
restaurants | -0.027 |
site | -0.027 |
burgers | -0.026 |
Everyone | -0.025 |
Token | girl |
Token ID | 2576 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
Fourth | +0.027 |
restaurants | +0.025 |
burgers | +0.024 |
site | +0.023 |
dogs | +0.023 |
Neg logit contributions | |
aid | -0.023 |
bead | -0.022 |
can | -0.020 |
wand | -0.019 |
gently | -0.019 |
Token | came |
Token ID | 1625 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
bead | +0.176 |
aid | +0.172 |
wand | +0.155 |
can | +0.150 |
arl | +0.149 |
Neg logit contributions | |
Fourth | -0.166 |
restaurants | -0.156 |
ices | -0.151 |
site | -0.146 |
dogs | -0.140 |
Token | to |
Token ID | 284 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Fourth | +0.031 |
restaurants | +0.029 |
ices | +0.029 |
site | +0.027 |
ics | +0.027 |
Neg logit contributions | |
bead | -0.023 |
aid | -0.022 |
can | -0.021 |
wand | -0.019 |
clip | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
bead | +0.016 |
can | +0.016 |
aid | +0.016 |
wand | +0.014 |
gently | +0.013 |
Neg logit contributions | |
Fourth | -0.026 |
ices | -0.025 |
site | -0.024 |
restaurants | -0.024 |
oving | -0.024 |
Token | beach |
Token ID | 10481 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
Fourth | +0.003 |
restaurants | +0.002 |
ices | +0.002 |
site | +0.002 |
oving | +0.002 |
Neg logit contributions | |
bead | -0.007 |
can | -0.006 |
aid | -0.006 |
wand | -0.006 |
gently | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Fourth | +0.259 |
ices | +0.243 |
restaurants | +0.242 |
site | +0.238 |
oving | +0.234 |
Neg logit contributions | |
bead | -0.084 |
can | -0.083 |
aid | -0.077 |
wand | -0.064 |
gently | -0.061 |
Token | She |
Token ID | 1375 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
bead | +0.022 |
aid | +0.021 |
can | +0.021 |
wand | +0.019 |
gently | +0.018 |
Neg logit contributions | |
Fourth | -0.033 |
restaurants | -0.031 |
ices | -0.031 |
site | -0.030 |
outskirts | -0.029 |
Token | had |
Token ID | 550 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
bead | +0.096 |
aid | +0.093 |
can | +0.089 |
wand | +0.082 |
gently | +0.076 |
Neg logit contributions | |
Fourth | -0.131 |
restaurants | -0.122 |
ices | -0.120 |
site | -0.119 |
burgers | -0.115 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
bead | +0.111 |
aid | +0.107 |
can | +0.107 |
wand | +0.095 |
gently | +0.089 |
Neg logit contributions | |
Fourth | -0.163 |
restaurants | -0.152 |
ices | -0.149 |
site | -0.147 |
burgers | -0.143 |
Token | ball |
Token ID | 2613 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
aid | +0.030 |
bead | +0.028 |
can | +0.025 |
och | +0.025 |
smart | +0.023 |
Neg logit contributions | |
Fourth | -0.031 |
restaurants | -0.028 |
burgers | -0.027 |
site | -0.027 |
outskirts | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -7.21e-03 |
Pos logit contributions | |
Fourth | +0.017 |
restaurants | +0.015 |
ices | +0.015 |
site | +0.015 |
burgers | +0.015 |
Neg logit contributions | |
bead | -0.011 |
can | -0.011 |
aid | -0.011 |
wand | -0.009 |
gently | -0.009 |
Token | After |
Token ID | 3260 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
Fourth | +0.012 |
ices | +0.011 |
restaurants | +0.011 |
site | +0.011 |
outskirts | +0.011 |
Neg logit contributions | |
bead | -0.013 |
can | -0.013 |
aid | -0.013 |
wand | -0.012 |
gently | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
Fourth | +0.073 |
restaurants | +0.068 |
ices | +0.067 |
site | +0.066 |
burgers | +0.064 |
Neg logit contributions | |
bead | -0.059 |
aid | -0.057 |
can | -0.057 |
wand | -0.051 |
gently | -0.048 |
Token | while |
Token ID | 981 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
bead | +0.034 |
aid | +0.033 |
can | +0.032 |
wand | +0.029 |
clip | +0.027 |
Neg logit contributions | |
Fourth | -0.035 |
restaurants | -0.032 |
site | -0.031 |
ices | -0.030 |
burgers | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
Fourth | +0.131 |
restaurants | +0.123 |
ices | +0.121 |
site | +0.120 |
outskirts | +0.116 |
Neg logit contributions | |
bead | -0.058 |
aid | -0.056 |
can | -0.054 |
wand | -0.046 |
gently | -0.041 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
can | +0.029 |
bead | +0.028 |
aid | +0.027 |
gently | +0.025 |
wand | +0.025 |
Neg logit contributions | |
Fourth | -0.040 |
ices | -0.039 |
urg | -0.038 |
restaurants | -0.037 |
oving | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
Fourth | +0.082 |
restaurants | +0.076 |
ices | +0.075 |
site | +0.074 |
outskirts | +0.071 |
Neg logit contributions | |
bead | -0.063 |
aid | -0.061 |
can | -0.061 |
wand | -0.055 |
gently | -0.052 |
Token | carrying |
Token ID | 6872 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Fourth | +0.086 |
restaurants | +0.079 |
ices | +0.078 |
site | +0.077 |
outskirts | +0.073 |
Neg logit contributions | |
bead | -0.080 |
can | -0.077 |
aid | -0.077 |
wand | -0.070 |
gently | -0.066 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Fourth | +0.208 |
restaurants | +0.203 |
ices | +0.196 |
site | +0.191 |
burgers | +0.184 |
Neg logit contributions | |
bead | -0.193 |
aid | -0.191 |
can | -0.189 |
arl | -0.171 |
och | -0.166 |
Token | of |
Token ID | 286 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
ices | +0.166 |
restaurants | +0.163 |
Fourth | +0.157 |
dogs | +0.153 |
burgers | +0.153 |
Neg logit contributions | |
bead | -0.270 |
can | -0.254 |
aid | -0.253 |
wand | -0.243 |
arl | -0.242 |
Token | special |
Token ID | 2041 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
Fourth | +0.088 |
restaurants | +0.088 |
ices | +0.084 |
burgers | +0.081 |
site | +0.079 |
Neg logit contributions | |
bead | -0.088 |
aid | -0.083 |
can | -0.081 |
wand | -0.075 |
och | -0.074 |
Token | up |
Token ID | 510 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Fourth | +0.048 |
ices | +0.045 |
restaurants | +0.044 |
site | +0.044 |
oving | +0.042 |
Neg logit contributions | |
can | -0.032 |
bead | -0.032 |
aid | -0.031 |
wand | -0.027 |
gently | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +7.17e-03 |
Pos logit contributions | |
Fourth | +0.316 |
restaurants | +0.296 |
ices | +0.294 |
site | +0.290 |
oving | +0.281 |
Neg logit contributions | |
bead | -0.138 |
can | -0.132 |
aid | -0.131 |
wand | -0.112 |
gently | -0.104 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
bead | +0.010 |
can | +0.010 |
aid | +0.010 |
wand | +0.008 |
gently | +0.008 |
Neg logit contributions | |
Fourth | -0.015 |
restaurants | -0.014 |
ices | -0.014 |
site | -0.014 |
oving | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
bead | +0.045 |
aid | +0.040 |
can | +0.039 |
wand | +0.036 |
thread | +0.032 |
Neg logit contributions | |
Fourth | -0.078 |
restaurants | -0.074 |
site | -0.073 |
burgers | -0.072 |
ices | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
can | +0.010 |
gently | +0.009 |
hug | +0.009 |
bead | +0.008 |
aid | +0.008 |
Neg logit contributions | |
Fourth | -0.020 |
ices | -0.019 |
oving | -0.019 |
umm | -0.019 |
site | -0.018 |
Token | grill |
Token ID | 29901 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Fourth | +0.008 |
restaurants | +0.008 |
site | +0.007 |
burgers | +0.007 |
ices | +0.007 |
Neg logit contributions | |
bead | -0.011 |
aid | -0.011 |
can | -0.011 |
wand | -0.010 |
och | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
Fourth | +0.429 |
restaurants | +0.404 |
ices | +0.402 |
site | +0.401 |
burgers | +0.388 |
Neg logit contributions | |
bead | -0.186 |
aid | -0.179 |
can | -0.173 |
wand | -0.148 |
thread | -0.130 |
Token | They |
Token ID | 1119 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
can | +0.027 |
bead | +0.025 |
gently | +0.023 |
aid | +0.022 |
wand | +0.022 |
Neg logit contributions | |
Fourth | -0.027 |
oving | -0.026 |
ics | -0.025 |
ices | -0.025 |
ales | -0.024 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
Fourth | +0.163 |
ices | +0.152 |
restaurants | +0.151 |
site | +0.149 |
oving | +0.145 |
Neg logit contributions | |
can | -0.094 |
bead | -0.094 |
aid | -0.091 |
wand | -0.080 |
gently | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -5.66e-03 |
Pos logit contributions | |
Fourth | +0.133 |
oving | +0.128 |
ices | +0.128 |
site | +0.122 |
outskirts | +0.121 |
Neg logit contributions | |
can | -0.075 |
aid | -0.072 |
bead | -0.071 |
gently | -0.062 |
wand | -0.059 |
Token | burgers |
Token ID | 34623 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Fourth | +0.009 |
ices | +0.009 |
oving | +0.008 |
restaurants | +0.008 |
ics | +0.008 |
Neg logit contributions | |
can | -0.011 |
bead | -0.010 |
wand | -0.010 |
aid | -0.010 |
will | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
Fourth | +0.206 |
restaurants | +0.193 |
ices | +0.190 |
site | +0.188 |
burgers | +0.182 |
Neg logit contributions | |
bead | -0.106 |
can | -0.102 |
aid | -0.101 |
wand | -0.088 |
gently | -0.081 |
Token | toys |
Token ID | 14958 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
aid | +0.160 |
bead | +0.160 |
can | +0.149 |
wand | +0.141 |
och | +0.136 |
Neg logit contributions | |
Fourth | -0.139 |
restaurants | -0.124 |
site | -0.119 |
burgers | -0.117 |
ices | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
aid | +0.051 |
bead | +0.048 |
can | +0.045 |
arl | +0.044 |
tweet | +0.042 |
Neg logit contributions | |
Fourth | -0.064 |
site | -0.059 |
restaurants | -0.059 |
ices | -0.058 |
ics | -0.057 |
Token | m |
Token ID | 285 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
bead | +0.024 |
can | +0.023 |
aid | +0.023 |
wand | +0.021 |
gently | +0.019 |
Neg logit contributions | |
Fourth | -0.031 |
restaurants | -0.028 |
ices | -0.028 |
site | -0.027 |
burgers | -0.027 |
Token | unch |
Token ID | 3316 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Fourth | +0.069 |
restaurants | +0.064 |
ices | +0.059 |
site | +0.059 |
burgers | +0.058 |
Neg logit contributions | |
aid | -0.111 |
bead | -0.106 |
can | -0.105 |
gently | -0.096 |
clip | -0.095 |
Token | ing |
Token ID | 278 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Fourth | +0.226 |
ices | +0.219 |
icles | +0.210 |
burgers | +0.209 |
ics | +0.208 |
Neg logit contributions | |
bead | -0.305 |
aid | -0.291 |
wand | -0.267 |
can | -0.266 |
ti | -0.258 |
Token | on |
Token ID | 319 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
Fourth | +0.397 |
restaurants | +0.382 |
burgers | +0.379 |
dogs | +0.379 |
ices | +0.377 |
Neg logit contributions | |
bead | -0.239 |
can | -0.227 |
aid | -0.220 |
och | -0.194 |
wand | -0.186 |
Token | her |
Token ID | 607 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
bead | +0.043 |
aid | +0.042 |
can | +0.041 |
wand | +0.037 |
gently | +0.034 |
Neg logit contributions | |
Fourth | -0.057 |
restaurants | -0.053 |
ices | -0.052 |
site | -0.052 |
burgers | -0.050 |
Token | apple |
Token ID | 17180 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
bead | +0.145 |
aid | +0.143 |
can | +0.140 |
wand | +0.127 |
och | +0.121 |
Neg logit contributions | |
Fourth | -0.147 |
restaurants | -0.132 |
site | -0.126 |
ices | -0.126 |
burgers | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
Fourth | +0.012 |
site | +0.011 |
restaurants | +0.011 |
ices | +0.011 |
burgers | +0.011 |
Neg logit contributions | |
aid | -0.007 |
can | -0.007 |
bead | -0.007 |
arl | -0.006 |
wand | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
can | +0.020 |
bead | +0.019 |
aid | +0.018 |
gently | +0.017 |
c | +0.016 |
Neg logit contributions | |
Fourth | -0.031 |
site | -0.030 |
ices | -0.029 |
restaurants | -0.029 |
oving | -0.029 |
Token | ready |
Token ID | 3492 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
bead | +0.011 |
aid | +0.011 |
can | +0.011 |
wand | +0.010 |
gently | +0.009 |
Neg logit contributions | |
Fourth | -0.015 |
restaurants | -0.014 |
site | -0.013 |
ices | -0.013 |
burgers | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
Fourth | +0.053 |
restaurants | +0.049 |
site | +0.049 |
ices | +0.049 |
burgers | +0.047 |
Neg logit contributions | |
bead | -0.031 |
aid | -0.030 |
can | -0.027 |
wand | -0.024 |
och | -0.023 |
Token | Everyone |
Token ID | 11075 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
can | +0.015 |
bead | +0.014 |
aid | +0.014 |
gently | +0.013 |
wand | +0.012 |
Neg logit contributions | |
Fourth | -0.018 |
restaurants | -0.016 |
ics | -0.016 |
ices | -0.016 |
oving | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
Fourth | +0.348 |
restaurants | +0.323 |
ices | +0.320 |
site | +0.315 |
burgers | +0.304 |
Neg logit contributions | |
bead | -0.223 |
can | -0.218 |
aid | -0.214 |
wand | -0.190 |
gently | -0.181 |
Token | so |
Token ID | 523 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
Fourth | +0.109 |
ices | +0.103 |
restaurants | +0.100 |
ales | +0.097 |
site | +0.096 |
Neg logit contributions | |
can | -0.061 |
bead | -0.061 |
aid | -0.060 |
gently | -0.055 |
wand | -0.052 |
Token | amazed |
Token ID | 24562 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Fourth | +0.196 |
ices | +0.186 |
restaurants | +0.183 |
site | +0.179 |
ales | +0.175 |
Neg logit contributions | |
can | -0.095 |
bead | -0.093 |
aid | -0.093 |
gently | -0.078 |
wand | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
Fourth | +0.437 |
restaurants | +0.409 |
ices | +0.406 |
site | +0.399 |
outskirts | +0.389 |
Neg logit contributions | |
bead | -0.191 |
can | -0.189 |
aid | -0.181 |
wand | -0.156 |
gently | -0.148 |
Token | proud |
Token ID | 6613 |
Feature activation | -7.98e-03 |
Pos logit contributions | |
can | +0.016 |
bead | +0.016 |
aid | +0.015 |
wand | +0.014 |
gently | +0.013 |
Neg logit contributions | |
Fourth | -0.023 |
ices | -0.022 |
restaurants | -0.021 |
site | -0.021 |
oving | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
Fourth | +0.018 |
restaurants | +0.017 |
ices | +0.017 |
site | +0.017 |
burgers | +0.016 |
Neg logit contributions | |
bead | -0.010 |
aid | -0.010 |
can | -0.010 |
wand | -0.008 |
gently | -0.008 |
Token | see |
Token ID | 766 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
can | +0.017 |
bead | +0.016 |
aid | +0.015 |
gently | +0.014 |
wand | +0.013 |
Neg logit contributions | |
Fourth | -0.035 |
ices | -0.034 |
restaurants | -0.033 |
burgers | -0.032 |
site | -0.032 |
Token | it |
Token ID | 340 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
can | +0.014 |
bead | +0.014 |
aid | +0.013 |
wand | +0.012 |
gently | +0.012 |
Neg logit contributions | |
Fourth | -0.020 |
ices | -0.018 |
restaurants | -0.018 |
site | -0.018 |
oving | -0.018 |
Token | - |
Token ID | 12 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
Fourth | +0.063 |
site | +0.056 |
dogs | +0.053 |
restaurants | +0.053 |
burgers | +0.052 |
Neg logit contributions | |
aid | -0.058 |
bead | -0.052 |
can | -0.046 |
och | -0.045 |
gently | -0.044 |
Token | red |
Token ID | 445 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
Fourth | +0.028 |
dogs | +0.024 |
site | +0.024 |
ices | +0.024 |
restaurants | +0.023 |
Neg logit contributions | |
bead | -0.029 |
can | -0.028 |
wand | -0.027 |
bud | -0.026 |
aid | -0.026 |
Token | sc |
Token ID | 629 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
Fourth | +0.048 |
ices | +0.045 |
site | +0.044 |
restaurants | +0.044 |
burgers | +0.043 |
Neg logit contributions | |
aid | -0.040 |
bead | -0.039 |
can | -0.035 |
gently | -0.032 |
wand | -0.032 |
Token | ooter |
Token ID | 25141 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
bead | +0.090 |
can | +0.078 |
aid | +0.078 |
wand | +0.074 |
gently | +0.073 |
Neg logit contributions | |
Fourth | -0.092 |
site | -0.082 |
ices | -0.080 |
ales | -0.080 |
asts | -0.079 |
Token | ! |
Token ID | 0 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
bead | +0.115 |
aid | +0.115 |
can | +0.100 |
wand | +0.095 |
gently | +0.085 |
Neg logit contributions | |
Fourth | -0.195 |
site | -0.179 |
restaurants | -0.177 |
ices | -0.174 |
ics | -0.171 |
Token | All |
Token ID | 1439 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Fourth | +0.228 |
oving | +0.227 |
urg | +0.225 |
ices | +0.214 |
aded | +0.213 |
Neg logit contributions | |
can | -0.092 |
bead | -0.055 |
gently | -0.055 |
hug | -0.052 |
too | -0.052 |
Token | of |
Token ID | 286 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
Fourth | +0.370 |
ices | +0.347 |
restaurants | +0.343 |
site | +0.343 |
oving | +0.334 |
Neg logit contributions | |
can | -0.244 |
bead | -0.233 |
aid | -0.220 |
wand | -0.197 |
gently | -0.189 |
Token | his |
Token ID | 465 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
Fourth | +0.138 |
oving | +0.128 |
outskirts | +0.125 |
ices | +0.125 |
ics | +0.123 |
Neg logit contributions | |
can | -0.066 |
bead | -0.061 |
aid | -0.055 |
gently | -0.054 |
thread | -0.053 |
Token | friends |
Token ID | 2460 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
can | +0.018 |
bead | +0.018 |
aid | +0.017 |
wand | +0.016 |
gently | +0.015 |
Neg logit contributions | |
Fourth | -0.020 |
restaurants | -0.019 |
ices | -0.019 |
site | -0.018 |
outskirts | -0.018 |
Token | were |
Token ID | 547 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
Fourth | +0.067 |
ices | +0.062 |
restaurants | +0.062 |
site | +0.061 |
burgers | +0.059 |
Neg logit contributions | |
can | -0.046 |
bead | -0.045 |
aid | -0.043 |
wand | -0.039 |
gently | -0.038 |
Token | so |
Token ID | 523 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
ices | +0.193 |
Fourth | +0.192 |
ales | +0.182 |
restaurants | +0.178 |
site | +0.177 |
Neg logit contributions | |
can | -0.089 |
bead | -0.080 |
gently | -0.076 |
aid | -0.074 |
better | -0.072 |
Token | leave |
Token ID | 2666 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
bead | +0.016 |
aid | +0.016 |
can | +0.015 |
wand | +0.014 |
gently | +0.012 |
Neg logit contributions | |
Fourth | -0.025 |
restaurants | -0.024 |
ices | -0.023 |
site | -0.023 |
outskirts | -0.022 |
Token | him |
Token ID | 683 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
bead | +0.043 |
aid | +0.041 |
can | +0.039 |
wand | +0.035 |
clip | +0.031 |
Neg logit contributions | |
Fourth | -0.066 |
restaurants | -0.062 |
site | -0.061 |
ices | -0.060 |
burgers | -0.058 |
Token | alone |
Token ID | 3436 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
Fourth | +0.149 |
restaurants | +0.144 |
ices | +0.138 |
site | +0.137 |
ics | +0.134 |
Neg logit contributions | |
aid | -0.094 |
bead | -0.094 |
can | -0.082 |
wand | -0.074 |
och | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
aid | +0.116 |
bead | +0.111 |
can | +0.093 |
wand | +0.087 |
och | +0.083 |
Neg logit contributions | |
Fourth | -0.169 |
ices | -0.163 |
site | -0.161 |
restaurants | -0.159 |
oving | -0.151 |
Token | So |
Token ID | 1406 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
can | +0.048 |
bead | +0.045 |
gently | +0.044 |
aid | +0.042 |
wand | +0.041 |
Neg logit contributions | |
Fourth | -0.054 |
restaurants | -0.051 |
burgers | -0.051 |
dogs | -0.050 |
oving | -0.049 |
Token | Joe |
Token ID | 5689 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Fourth | +0.137 |
restaurants | +0.129 |
ices | +0.128 |
dogs | +0.125 |
oving | +0.125 |
Neg logit contributions | |
can | -0.073 |
bead | -0.071 |
aid | -0.065 |
gently | -0.063 |
wand | -0.062 |
Token | 's |
Token ID | 338 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Fourth | +0.325 |
ices | +0.314 |
site | +0.304 |
restaurants | +0.302 |
youngest | +0.295 |
Neg logit contributions | |
bead | -0.319 |
aid | -0.295 |
can | -0.277 |
wand | -0.263 |
arl | -0.263 |
Token | mother |
Token ID | 2802 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
Fourth | +0.184 |
ices | +0.162 |
restaurants | +0.161 |
site | +0.155 |
youngest | +0.154 |
Neg logit contributions | |
bead | -0.290 |
aid | -0.281 |
can | -0.271 |
och | -0.250 |
clip | -0.242 |
Token | suggested |
Token ID | 5220 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Fourth | +0.122 |
ices | +0.114 |
restaurants | +0.113 |
site | +0.113 |
burgers | +0.108 |
Neg logit contributions | |
bead | -0.096 |
aid | -0.090 |
can | -0.089 |
wand | -0.081 |
arl | -0.074 |
Token | that |
Token ID | 326 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
Fourth | +0.221 |
restaurants | +0.207 |
site | +0.205 |
ices | +0.205 |
burgers | +0.199 |
Neg logit contributions | |
bead | -0.157 |
aid | -0.146 |
can | -0.143 |
wand | -0.130 |
clip | -0.118 |
Token | Joe |
Token ID | 5689 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Fourth | +0.080 |
ices | +0.074 |
oving | +0.074 |
urg | +0.073 |
site | +0.072 |
Neg logit contributions | |
can | -0.045 |
bead | -0.041 |
aid | -0.037 |
gently | -0.037 |
fairy | -0.035 |