Token | . |
Token ID | 13 |
Feature activation | -2.90e-03 |
Pos logit contributions | |
rob | +0.191 |
ons | +0.180 |
rides | +0.176 |
opl | +0.174 |
cream | +0.164 |
Neg logit contributions | |
kin | -0.175 |
upon | -0.162 |
moment | -0.153 |
particular | -0.143 |
isel | -0.140 |
Token | There |
Token ID | 1318 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
kin | +0.005 |
isel | +0.005 |
upon | +0.005 |
rated | +0.004 |
moment | +0.004 |
Neg logit contributions | |
rob | -0.005 |
rides | -0.005 |
ons | -0.005 |
opl | -0.005 |
cand | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
kin | +0.113 |
isel | +0.104 |
rated | +0.099 |
loser | +0.096 |
upon | +0.096 |
Neg logit contributions | |
rides | -0.099 |
ons | -0.098 |
rob | -0.097 |
opl | -0.085 |
cand | -0.085 |
Token | many |
Token ID | 867 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
rob | +0.084 |
opl | +0.079 |
ons | +0.077 |
cream | +0.073 |
rides | +0.071 |
Neg logit contributions | |
kin | -0.068 |
upon | -0.067 |
moment | -0.060 |
loser | -0.057 |
particular | -0.056 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
rob | +0.238 |
opl | +0.217 |
rides | +0.212 |
ons | +0.211 |
cream | +0.205 |
Neg logit contributions | |
kin | -0.210 |
upon | -0.192 |
moment | -0.172 |
particular | -0.170 |
ac | -0.170 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
rob | +0.376 |
rides | +0.349 |
ons | +0.342 |
opl | +0.339 |
cream | +0.323 |
Neg logit contributions | |
kin | -0.295 |
upon | -0.260 |
moment | -0.246 |
isel | -0.240 |
rated | -0.226 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
rob | +0.973 |
rides | +0.924 |
ons | +0.919 |
opl | +0.886 |
cand | +0.840 |
Neg logit contributions | |
kin | -0.733 |
upon | -0.637 |
moment | -0.595 |
isel | -0.581 |
rated | -0.566 |
Token | games |
Token ID | 1830 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
rob | +0.017 |
opl | +0.016 |
ons | +0.015 |
rides | +0.015 |
cream | +0.014 |
Neg logit contributions | |
kin | -0.021 |
moment | -0.019 |
upon | -0.019 |
rated | -0.018 |
particular | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-03 |
Pos logit contributions | |
rob | +0.350 |
rides | +0.338 |
ons | +0.331 |
opl | +0.315 |
cand | +0.299 |
Neg logit contributions | |
kin | -0.296 |
upon | -0.257 |
isel | -0.250 |
moment | -0.243 |
rated | -0.238 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
kin | +0.005 |
isel | +0.004 |
upon | +0.004 |
rated | +0.004 |
moment | +0.004 |
Neg logit contributions | |
rob | -0.005 |
rides | -0.005 |
ons | -0.005 |
opl | -0.004 |
cand | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
kin | +0.040 |
upon | +0.039 |
moment | +0.034 |
don | +0.031 |
cca | +0.031 |
Neg logit contributions | |
rob | -0.064 |
ons | -0.060 |
opl | -0.060 |
rides | -0.058 |
cand | -0.055 |
Token | Mary |
Token ID | 5335 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
kin | +0.023 |
isel | +0.020 |
upon | +0.019 |
rated | +0.019 |
loser | +0.018 |
Neg logit contributions | |
rides | -0.022 |
rob | -0.022 |
ons | -0.021 |
opl | -0.020 |
kisses | -0.019 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
kin | +0.206 |
upon | +0.169 |
moment | +0.164 |
rated | +0.153 |
particular | +0.152 |
Neg logit contributions | |
rob | -0.313 |
rides | -0.285 |
opl | -0.285 |
ons | -0.276 |
pill | -0.261 |
Token | to |
Token ID | 284 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
rob | +0.139 |
handed | +0.129 |
opl | +0.128 |
odic | +0.120 |
course | +0.114 |
Neg logit contributions | |
upon | -0.057 |
thing | -0.048 |
moment | -0.048 |
particular | -0.044 |
time | -0.043 |
Token | go |
Token ID | 467 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
rob | +0.139 |
opl | +0.116 |
ons | +0.114 |
rides | +0.114 |
pill | +0.112 |
Neg logit contributions | |
kin | -0.123 |
particular | -0.108 |
isel | -0.104 |
moment | -0.103 |
upon | -0.102 |
Token | for |
Token ID | 329 |
Feature activation | -7.84e-03 |
Pos logit contributions | |
rob | +0.009 |
pill | +0.009 |
opl | +0.009 |
handed | +0.009 |
ons | +0.009 |
Neg logit contributions | |
upon | -0.005 |
moment | -0.004 |
particular | -0.004 |
kin | -0.003 |
halfway | -0.003 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
kin | +0.016 |
moment | +0.015 |
upon | +0.015 |
particular | +0.015 |
isel | +0.014 |
Neg logit contributions | |
rob | -0.011 |
ons | -0.010 |
opl | -0.010 |
cream | -0.009 |
handed | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
rob | +0.978 |
ons | +0.933 |
rides | +0.918 |
opl | +0.912 |
pill | +0.870 |
Neg logit contributions | |
kin | -0.706 |
upon | -0.609 |
moment | -0.570 |
particular | -0.546 |
inn | -0.535 |
Token | her |
Token ID | 607 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
kin | +0.026 |
upon | +0.026 |
particular | +0.024 |
moment | +0.024 |
halfway | +0.022 |
Neg logit contributions | |
rob | -0.029 |
ons | -0.027 |
cream | -0.026 |
opl | -0.026 |
handed | -0.025 |
Token | bike |
Token ID | 7161 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
ons | +0.095 |
rob | +0.093 |
pill | +0.085 |
course | +0.084 |
opl | +0.082 |
Neg logit contributions | |
kin | -0.076 |
upon | -0.072 |
moment | -0.069 |
particular | -0.068 |
footing | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
rob | +0.157 |
ons | +0.150 |
pill | +0.150 |
kisses | +0.147 |
cand | +0.145 |
Neg logit contributions | |
upon | -0.077 |
kin | -0.072 |
particular | -0.066 |
moment | -0.063 |
inn | -0.057 |
Token | She |
Token ID | 1375 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
kin | +0.024 |
upon | +0.021 |
isel | +0.021 |
moment | +0.020 |
rated | +0.020 |
Neg logit contributions | |
rob | -0.021 |
rides | -0.021 |
ons | -0.020 |
opl | -0.019 |
cand | -0.018 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
upon | +0.147 |
kin | +0.131 |
moment | +0.119 |
rated | +0.111 |
isel | +0.109 |
Neg logit contributions | |
rob | -0.261 |
opl | -0.252 |
ons | -0.247 |
cand | -0.234 |
cream | -0.230 |
Token | lots |
Token ID | 6041 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
kin | +0.078 |
upon | +0.072 |
moment | +0.063 |
isel | +0.063 |
disaster | +0.060 |
Neg logit contributions | |
rob | -0.135 |
opl | -0.129 |
ons | -0.126 |
rides | -0.126 |
grand | -0.116 |
Token | of |
Token ID | 286 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
rob | +0.309 |
opl | +0.276 |
rides | +0.272 |
ridge | +0.268 |
ons | +0.268 |
Neg logit contributions | |
kin | -0.194 |
upon | -0.174 |
thing | -0.155 |
particular | -0.154 |
isel | -0.151 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
rob | +0.127 |
ons | +0.121 |
rides | +0.119 |
opl | +0.118 |
cream | +0.108 |
Neg logit contributions | |
kin | -0.120 |
upon | -0.112 |
isel | -0.105 |
moment | -0.104 |
loser | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
rob | +0.269 |
opl | +0.242 |
ons | +0.242 |
rides | +0.233 |
cream | +0.231 |
Neg logit contributions | |
upon | -0.144 |
kin | -0.137 |
moment | -0.115 |
ges | -0.112 |
don | -0.112 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
rob | +0.004 |
ons | +0.004 |
opl | +0.004 |
rides | +0.004 |
course | +0.004 |
Neg logit contributions | |
kin | -0.004 |
upon | -0.004 |
isel | -0.003 |
moment | -0.003 |
rated | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
rides | +0.836 |
rob | +0.810 |
ons | +0.782 |
opl | +0.700 |
cand | +0.697 |
Neg logit contributions | |
kin | -0.854 |
isel | -0.786 |
upon | -0.719 |
loser | -0.709 |
rated | -0.709 |
Token | She |
Token ID | 1375 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
kin | +0.034 |
isel | +0.031 |
upon | +0.030 |
rated | +0.030 |
moment | +0.029 |
Neg logit contributions | |
rides | -0.022 |
rob | -0.021 |
ons | -0.020 |
cand | -0.018 |
opl | -0.018 |
Token | even |
Token ID | 772 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
rob | +0.233 |
rides | +0.231 |
ons | +0.224 |
opl | +0.209 |
cand | +0.201 |
Neg logit contributions | |
kin | -0.207 |
isel | -0.179 |
upon | -0.178 |
rated | -0.170 |
moment | -0.169 |
Token | got |
Token ID | 1392 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
kin | +0.117 |
isel | +0.104 |
upon | +0.102 |
rated | +0.098 |
moment | +0.098 |
Neg logit contributions | |
rob | -0.093 |
rides | -0.092 |
ons | -0.088 |
opl | -0.080 |
cand | -0.077 |
Token | to |
Token ID | 284 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
rob | +0.017 |
ons | +0.016 |
opl | +0.016 |
rides | +0.016 |
course | +0.014 |
Neg logit contributions | |
kin | -0.015 |
upon | -0.015 |
isel | -0.013 |
moment | -0.013 |
cca | -0.013 |
Token | would |
Token ID | 561 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
rob | +0.196 |
rides | +0.182 |
ons | +0.176 |
opl | +0.169 |
cand | +0.168 |
Neg logit contributions | |
kin | -0.142 |
upon | -0.127 |
moment | -0.125 |
ac | -0.119 |
isel | -0.112 |
Token | even |
Token ID | 772 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
kin | +0.151 |
upon | +0.137 |
particular | +0.133 |
moment | +0.133 |
isel | +0.129 |
Neg logit contributions | |
rob | -0.213 |
ons | -0.203 |
cream | -0.188 |
rides | -0.187 |
pill | -0.181 |
Token | give |
Token ID | 1577 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
kin | +0.105 |
upon | +0.092 |
isel | +0.092 |
moment | +0.088 |
rated | +0.087 |
Neg logit contributions | |
rob | -0.107 |
rides | -0.105 |
ons | -0.102 |
opl | -0.096 |
cand | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
rob | +0.056 |
rides | +0.053 |
ons | +0.051 |
opl | +0.051 |
cand | +0.046 |
Neg logit contributions | |
kin | -0.043 |
upon | -0.039 |
moment | -0.038 |
isel | -0.037 |
rated | -0.036 |
Token | frog |
Token ID | 21264 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
kin | +0.030 |
isel | +0.026 |
upon | +0.025 |
rated | +0.025 |
moment | +0.024 |
Neg logit contributions | |
rob | -0.030 |
rides | -0.030 |
ons | -0.029 |
opl | -0.027 |
cand | -0.026 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
kin | +0.134 |
upon | +0.125 |
moment | +0.118 |
ac | +0.108 |
thing | +0.106 |
Neg logit contributions | |
rob | -0.209 |
opl | -0.182 |
rides | -0.181 |
ons | -0.180 |
odic | -0.164 |
Token | on |
Token ID | 319 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
rob | +0.923 |
rides | +0.886 |
ons | +0.874 |
opl | +0.832 |
cand | +0.790 |
Neg logit contributions | |
kin | -0.763 |
upon | -0.659 |
isel | -0.631 |
moment | -0.631 |
rated | -0.612 |
Token | its |
Token ID | 663 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
kin | +0.022 |
upon | +0.019 |
isel | +0.019 |
moment | +0.018 |
rated | +0.018 |
Neg logit contributions | |
rob | -0.026 |
rides | -0.025 |
ons | -0.025 |
opl | -0.023 |
cand | -0.022 |
Token | back |
Token ID | 736 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
kin | +0.112 |
moment | +0.110 |
upon | +0.106 |
footing | +0.101 |
particular | +0.098 |
Neg logit contributions | |
rob | -0.185 |
ons | -0.179 |
pill | -0.159 |
cream | -0.157 |
rides | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
rob | +0.138 |
ons | +0.128 |
rides | +0.128 |
cand | +0.118 |
cream | +0.116 |
Neg logit contributions | |
kin | -0.094 |
upon | -0.086 |
moment | -0.082 |
isel | -0.078 |
particular | -0.075 |
Token | |
Token ID | 220 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
kin | +0.022 |
upon | +0.021 |
moment | +0.020 |
isel | +0.019 |
inn | +0.019 |
Neg logit contributions | |
rob | -0.029 |
rides | -0.029 |
ons | -0.028 |
cand | -0.026 |
odic | -0.026 |
Token | always |
Token ID | 1464 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
kin | +0.146 |
upon | +0.137 |
moment | +0.131 |
don | +0.130 |
particular | +0.125 |
Neg logit contributions | |
rob | -0.210 |
ons | -0.190 |
pill | -0.181 |
cream | -0.180 |
rides | -0.179 |
Token | take |
Token ID | 1011 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
rob | +0.154 |
ons | +0.137 |
pill | +0.134 |
rides | +0.128 |
opl | +0.128 |
Neg logit contributions | |
kin | -0.110 |
upon | -0.101 |
moment | -0.100 |
don | -0.099 |
isel | -0.094 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
kin | +0.031 |
upon | +0.027 |
isel | +0.027 |
moment | +0.026 |
loser | +0.025 |
Neg logit contributions | |
rob | -0.036 |
rides | -0.033 |
ons | -0.032 |
opl | -0.032 |
cream | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
kin | +0.332 |
upon | +0.306 |
moment | +0.293 |
ac | +0.283 |
rated | +0.281 |
Neg logit contributions | |
rob | -0.251 |
rides | -0.223 |
ons | -0.218 |
opl | -0.211 |
odic | -0.189 |
Token | special |
Token ID | 2041 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
kin | +0.012 |
upon | +0.010 |
moment | +0.010 |
isel | +0.010 |
loser | +0.010 |
Neg logit contributions | |
rob | -0.015 |
ons | -0.014 |
rides | -0.014 |
opl | -0.014 |
cream | -0.013 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
rob | +0.168 |
ons | +0.156 |
rides | +0.154 |
opl | +0.150 |
pill | +0.136 |
Neg logit contributions | |
kin | -0.203 |
moment | -0.180 |
isel | -0.175 |
upon | -0.174 |
loser | -0.169 |
Token | in |
Token ID | 287 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
rob | +0.900 |
rides | +0.886 |
ons | +0.861 |
opl | +0.810 |
cand | +0.776 |
Neg logit contributions | |
kin | -0.771 |
upon | -0.664 |
isel | -0.661 |
moment | -0.630 |
rated | -0.629 |
Token | his |
Token ID | 465 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
kin | +0.167 |
isel | +0.150 |
upon | +0.144 |
rated | +0.143 |
moment | +0.136 |
Neg logit contributions | |
rides | -0.169 |
rob | -0.166 |
ons | -0.163 |
opl | -0.151 |
cand | -0.144 |
Token | car |
Token ID | 1097 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
rob | +0.065 |
ons | +0.061 |
rides | +0.055 |
odic | +0.055 |
pill | +0.055 |
Neg logit contributions | |
kin | -0.052 |
moment | -0.044 |
upon | -0.044 |
loser | -0.042 |
particular | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
rob | +0.217 |
ons | +0.203 |
rides | +0.197 |
pill | +0.192 |
opl | +0.192 |
Neg logit contributions | |
kin | -0.129 |
upon | -0.106 |
moment | -0.101 |
loser | -0.096 |
rated | -0.096 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
upon | +0.023 |
kin | +0.022 |
moment | +0.021 |
particular | +0.020 |
rated | +0.019 |
Neg logit contributions | |
rob | -0.041 |
ons | -0.039 |
rides | -0.038 |
opl | -0.036 |
odic | -0.036 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
rob | +0.124 |
ons | +0.114 |
rides | +0.113 |
opl | +0.112 |
cream | +0.102 |
Neg logit contributions | |
kin | -0.111 |
upon | -0.107 |
moment | -0.099 |
isel | -0.099 |
rated | -0.095 |
Token | things |
Token ID | 1243 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
rob | +0.365 |
rides | +0.347 |
ons | +0.339 |
opl | +0.333 |
cream | +0.310 |
Neg logit contributions | |
kin | -0.264 |
upon | -0.234 |
isel | -0.224 |
moment | -0.222 |
rated | -0.210 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
kin | +0.060 |
upon | +0.056 |
moment | +0.052 |
isel | +0.047 |
rated | +0.046 |
Neg logit contributions | |
rob | -0.094 |
opl | -0.086 |
rides | -0.086 |
ons | -0.085 |
grand | -0.078 |
Token | There |
Token ID | 1318 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
kin | +0.034 |
isel | +0.030 |
upon | +0.030 |
rated | +0.029 |
moment | +0.029 |
Neg logit contributions | |
rides | -0.020 |
rob | -0.019 |
ons | -0.018 |
opl | -0.017 |
cand | -0.016 |
Token | were |
Token ID | 547 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
kin | +0.116 |
upon | +0.102 |
isel | +0.101 |
moment | +0.097 |
rated | +0.096 |
Neg logit contributions | |
rob | -0.118 |
rides | -0.116 |
ons | -0.112 |
opl | -0.106 |
cand | -0.101 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
rob | +0.065 |
ons | +0.060 |
opl | +0.059 |
rides | +0.056 |
cream | +0.054 |
Neg logit contributions | |
kin | -0.061 |
upon | -0.059 |
moment | -0.054 |
particular | -0.051 |
isel | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
rides | +0.874 |
rob | +0.874 |
ons | +0.843 |
opl | +0.786 |
cand | +0.758 |
Neg logit contributions | |
kin | -0.790 |
isel | -0.693 |
upon | -0.677 |
rated | -0.652 |
moment | -0.644 |
Token | games |
Token ID | 1830 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
rob | +0.004 |
opl | +0.003 |
ons | +0.003 |
cream | +0.003 |
assy | +0.003 |
Neg logit contributions | |
upon | -0.003 |
kin | -0.003 |
moment | -0.003 |
don | -0.003 |
isel | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +2.32e-03 |
Pos logit contributions | |
rob | +0.354 |
rides | +0.331 |
ons | +0.327 |
opl | +0.318 |
cream | +0.298 |
Neg logit contributions | |
kin | -0.280 |
upon | -0.247 |
moment | -0.232 |
isel | -0.229 |
rated | -0.216 |
Token | food |
Token ID | 2057 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
rob | +0.004 |
ons | +0.004 |
opl | +0.004 |
rides | +0.003 |
cream | +0.003 |
Neg logit contributions | |
kin | -0.004 |
upon | -0.004 |
moment | -0.004 |
rated | -0.004 |
isel | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
rob | +0.499 |
rides | +0.458 |
ons | +0.457 |
opl | +0.452 |
cream | +0.417 |
Neg logit contributions | |
kin | -0.337 |
upon | -0.291 |
moment | -0.266 |
isel | -0.247 |
rated | -0.237 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
rides | +0.195 |
rob | +0.192 |
ons | +0.187 |
opl | +0.173 |
cand | +0.167 |
Neg logit contributions | |
kin | -0.185 |
isel | -0.166 |
upon | -0.160 |
rated | -0.156 |
moment | -0.152 |
Token | They |
Token ID | 1119 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
kin | +0.029 |
upon | +0.026 |
isel | +0.025 |
moment | +0.025 |
rated | +0.024 |
Neg logit contributions | |
rob | -0.030 |
rides | -0.029 |
ons | -0.029 |
opl | -0.026 |
cand | -0.026 |
Token | would |
Token ID | 561 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
rob | +0.040 |
rides | +0.038 |
ons | +0.038 |
opl | +0.037 |
cand | +0.035 |
Neg logit contributions | |
kin | -0.031 |
upon | -0.027 |
isel | -0.026 |
moment | -0.025 |
rated | -0.024 |
Token | go |
Token ID | 467 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
kin | +0.162 |
upon | +0.146 |
isel | +0.143 |
particular | +0.141 |
moment | +0.139 |
Neg logit contributions | |
rob | -0.202 |
ons | -0.189 |
rides | -0.175 |
opl | -0.170 |
pill | -0.169 |
Token | for |
Token ID | 329 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
rob | +0.007 |
ons | +0.007 |
opl | +0.007 |
rides | +0.007 |
grand | +0.007 |
Neg logit contributions | |
upon | -0.005 |
kin | -0.005 |
moment | -0.005 |
isel | -0.004 |
inn | -0.004 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
kin | +0.012 |
moment | +0.011 |
upon | +0.010 |
isel | +0.010 |
particular | +0.010 |
Neg logit contributions | |
rob | -0.016 |
ons | -0.016 |
opl | -0.015 |
grand | -0.015 |
cream | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
rob | +0.868 |
rides | +0.862 |
ons | +0.831 |
opl | +0.776 |
cand | +0.745 |
Neg logit contributions | |
kin | -0.802 |
isel | -0.704 |
upon | -0.693 |
rated | -0.663 |
moment | -0.657 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
kin | +0.156 |
isel | +0.136 |
upon | +0.134 |
rated | +0.129 |
moment | +0.127 |
Neg logit contributions | |
rob | -0.180 |
rides | -0.179 |
ons | -0.174 |
opl | -0.163 |
cand | -0.156 |
Token | sunshine |
Token ID | 34488 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
moment | +0.025 |
upon | +0.025 |
particular | +0.024 |
time | +0.023 |
thing | +0.022 |
Neg logit contributions | |
ons | -0.031 |
rob | -0.029 |
grand | -0.027 |
cream | -0.026 |
cand | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +6.70e-04 |
Pos logit contributions | |
rob | +0.337 |
ons | +0.323 |
rides | +0.322 |
opl | +0.308 |
cream | +0.295 |
Neg logit contributions | |
kin | -0.230 |
upon | -0.198 |
moment | -0.193 |
particular | -0.170 |
isel | -0.170 |
Token | and |
Token ID | 290 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
rob | +0.001 |
ons | +0.001 |
opl | +0.001 |
rides | +0.001 |
cream | +0.001 |
Neg logit contributions | |
kin | -0.001 |
upon | -0.001 |
moment | -0.001 |
isel | -0.001 |
rated | -0.001 |
Token | eyes |
Token ID | 2951 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
rob | +0.124 |
ons | +0.113 |
rides | +0.112 |
opl | +0.110 |
course | +0.105 |
Neg logit contributions | |
kin | -0.064 |
upon | -0.058 |
moment | -0.050 |
isel | -0.050 |
particular | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
kin | +0.117 |
upon | +0.105 |
moment | +0.099 |
isel | +0.098 |
rated | +0.095 |
Neg logit contributions | |
rob | -0.167 |
rides | -0.155 |
ons | -0.155 |
opl | -0.147 |
cand | -0.139 |
Token | think |
Token ID | 892 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
rob | +0.008 |
ons | +0.008 |
rides | +0.008 |
opl | +0.007 |
pill | +0.007 |
Neg logit contributions | |
kin | -0.006 |
upon | -0.006 |
isel | -0.005 |
moment | -0.005 |
rated | -0.005 |
Token | about |
Token ID | 546 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
kin | +0.241 |
isel | +0.224 |
rated | +0.223 |
loser | +0.221 |
cca | +0.211 |
Neg logit contributions | |
rides | -0.141 |
ons | -0.135 |
kisses | -0.111 |
cand | -0.107 |
opl | -0.106 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
rob | +0.065 |
rides | +0.063 |
ons | +0.062 |
opl | +0.058 |
cand | +0.055 |
Neg logit contributions | |
kin | -0.056 |
upon | -0.049 |
isel | -0.049 |
moment | -0.047 |
rated | -0.046 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
kin | +0.022 |
upon | +0.020 |
isel | +0.019 |
moment | +0.019 |
rated | +0.018 |
Neg logit contributions | |
rob | -0.024 |
ons | -0.023 |
rides | -0.023 |
opl | -0.021 |
cand | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +4.02e-03 |
Pos logit contributions | |
rob | +0.892 |
rides | +0.865 |
ons | +0.843 |
opl | +0.800 |
cand | +0.764 |
Neg logit contributions | |
kin | -0.789 |
upon | -0.682 |
isel | -0.661 |
moment | -0.650 |
rated | -0.642 |
Token | games |
Token ID | 1830 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
rob | +0.008 |
ons | +0.007 |
rides | +0.007 |
opl | +0.007 |
cream | +0.007 |
Neg logit contributions | |
upon | -0.007 |
kin | -0.007 |
moment | -0.006 |
particular | -0.006 |
isel | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
rob | +0.340 |
rides | +0.327 |
ons | +0.321 |
opl | +0.306 |
cand | +0.290 |
Neg logit contributions | |
kin | -0.290 |
upon | -0.253 |
isel | -0.243 |
moment | -0.239 |
rated | -0.232 |
Token | would |
Token ID | 561 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
rob | +0.226 |
rides | +0.222 |
ons | +0.217 |
opl | +0.206 |
cand | +0.198 |
Neg logit contributions | |
kin | -0.158 |
upon | -0.135 |
isel | -0.133 |
moment | -0.127 |
rated | -0.126 |
Token | play |
Token ID | 711 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
kin | +0.162 |
upon | +0.147 |
isel | +0.141 |
moment | +0.140 |
rated | +0.134 |
Neg logit contributions | |
rob | -0.187 |
ons | -0.179 |
rides | -0.175 |
opl | -0.160 |
cand | -0.160 |
Token | in |
Token ID | 287 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
rob | +0.478 |
rides | +0.467 |
ons | +0.457 |
opl | +0.433 |
cand | +0.413 |
Neg logit contributions | |
kin | -0.408 |
upon | -0.356 |
isel | -0.347 |
moment | -0.337 |
rated | -0.333 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
kin | +0.155 |
isel | +0.135 |
upon | +0.134 |
rated | +0.128 |
moment | +0.127 |
Neg logit contributions | |
rob | -0.178 |
rides | -0.176 |
ons | -0.171 |
opl | -0.160 |
cand | -0.154 |
Token | park |
Token ID | 3952 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
particular | +0.028 |
upon | +0.027 |
moment | +0.027 |
thing | +0.025 |
time | +0.025 |
Neg logit contributions | |
ons | -0.034 |
rob | -0.033 |
odic | -0.028 |
cream | -0.027 |
grand | -0.027 |
Token | or |
Token ID | 393 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
rob | +0.460 |
rides | +0.443 |
ons | +0.436 |
opl | +0.413 |
cand | +0.393 |
Neg logit contributions | |
kin | -0.374 |
upon | -0.329 |
isel | -0.312 |
moment | -0.311 |
rated | -0.301 |
Token | for |
Token ID | 329 |
Feature activation | -6.69e-03 |
Pos logit contributions | |
kin | +0.275 |
upon | +0.247 |
moment | +0.235 |
isel | +0.232 |
rated | +0.224 |
Neg logit contributions | |
rob | -0.324 |
rides | -0.309 |
ons | -0.307 |
opl | -0.294 |
cand | -0.272 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
kin | +0.011 |
upon | +0.010 |
moment | +0.010 |
isel | +0.010 |
particular | +0.009 |
Neg logit contributions | |
rob | -0.013 |
ons | -0.012 |
rides | -0.012 |
opl | -0.012 |
cream | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
rob | +0.877 |
rides | +0.873 |
ons | +0.842 |
opl | +0.787 |
cand | +0.757 |
Neg logit contributions | |
kin | -0.790 |
isel | -0.694 |
upon | -0.683 |
rated | -0.652 |
moment | -0.647 |
Token | their |
Token ID | 511 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
kin | +0.164 |
isel | +0.147 |
rated | +0.141 |
upon | +0.140 |
moment | +0.132 |
Neg logit contributions | |
rides | -0.170 |
rob | -0.167 |
ons | -0.162 |
opl | -0.151 |
kisses | -0.144 |
Token | car |
Token ID | 1097 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
kin | +0.076 |
moment | +0.074 |
upon | +0.074 |
particular | +0.070 |
time | +0.065 |
Neg logit contributions | |
rob | -0.091 |
ons | -0.088 |
odic | -0.080 |
cream | -0.079 |
opl | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
rob | +0.229 |
ons | +0.214 |
opl | +0.205 |
pill | +0.204 |
odic | +0.199 |
Neg logit contributions | |
kin | -0.112 |
upon | -0.103 |
moment | -0.090 |
particular | -0.087 |
ac | -0.083 |
Token | |
Token ID | 220 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
kin | +0.026 |
isel | +0.023 |
upon | +0.023 |
rated | +0.022 |
moment | +0.022 |
Neg logit contributions | |
rob | -0.025 |
rides | -0.024 |
ons | -0.023 |
opl | -0.022 |
cand | -0.021 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
rob | +0.240 |
rides | +0.231 |
ons | +0.226 |
opl | +0.224 |
cand | +0.207 |
Neg logit contributions | |
kin | -0.210 |
upon | -0.178 |
moment | -0.174 |
rated | -0.168 |
isel | -0.164 |
Token | to |
Token ID | 284 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
rob | +0.146 |
opl | +0.143 |
handed | +0.140 |
odic | +0.129 |
course | +0.127 |
Neg logit contributions | |
upon | -0.055 |
moment | -0.046 |
thing | -0.044 |
time | -0.040 |
particular | -0.037 |
Token | go |
Token ID | 467 |
Feature activation | +6.37e-03 |
Pos logit contributions | |
rob | +0.154 |
opl | +0.133 |
pill | +0.128 |
ons | +0.128 |
handed | +0.127 |
Neg logit contributions | |
kin | -0.125 |
particular | -0.113 |
moment | -0.104 |
isel | -0.103 |
upon | -0.102 |
Token | on |
Token ID | 319 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
rob | +0.015 |
opl | +0.014 |
pill | +0.014 |
handed | +0.014 |
ons | +0.014 |
Neg logit contributions | |
upon | -0.008 |
moment | -0.007 |
particular | -0.006 |
kin | -0.006 |
inn | -0.005 |
Token | car |
Token ID | 1097 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
upon | +0.021 |
moment | +0.020 |
particular | +0.020 |
kin | +0.019 |
time | +0.018 |
Neg logit contributions | |
rob | -0.019 |
ons | -0.019 |
opl | -0.019 |
cream | -0.018 |
grand | -0.017 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
pill | +0.226 |
kisses | +0.212 |
ridge | +0.209 |
odic | +0.209 |
opl | +0.209 |
Neg logit contributions | |
upon | -0.083 |
particular | -0.075 |
thing | -0.075 |
if | -0.072 |
kin | -0.072 |
Token | with |
Token ID | 351 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
rob | +0.927 |
rides | +0.894 |
ons | +0.893 |
opl | +0.858 |
cand | +0.811 |
Neg logit contributions | |
kin | -0.739 |
upon | -0.646 |
moment | -0.609 |
isel | -0.596 |
rated | -0.587 |
Token | her |
Token ID | 607 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
rob | +0.078 |
opl | +0.070 |
rides | +0.068 |
ons | +0.066 |
cream | +0.066 |
Neg logit contributions | |
kin | -0.045 |
upon | -0.041 |
particular | -0.040 |
moment | -0.036 |
isel | -0.036 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
rob | +0.112 |
rides | +0.110 |
ons | +0.108 |
opl | +0.102 |
cand | +0.098 |
Neg logit contributions | |
kin | -0.076 |
upon | -0.065 |
isel | -0.064 |
moment | -0.061 |
rated | -0.059 |
Token | my |
Token ID | 1820 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
upon | +0.316 |
kin | +0.300 |
moment | +0.291 |
ac | +0.275 |
particular | +0.267 |
Neg logit contributions | |
rob | -0.326 |
rides | -0.311 |
opl | -0.294 |
ons | -0.290 |
pill | -0.287 |
Token | and |
Token ID | 290 |
Feature activation | +4.26e-03 |
Pos logit contributions | |
rob | +0.367 |
rides | +0.354 |
ons | +0.345 |
opl | +0.342 |
pill | +0.317 |
Neg logit contributions | |
kin | -0.241 |
upon | -0.223 |
moment | -0.204 |
inn | -0.190 |
ac | -0.187 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
rob | +0.104 |
ons | +0.104 |
opl | +0.097 |
rides | +0.092 |
ridge | +0.085 |
Neg logit contributions | |
kin | -0.137 |
upon | -0.129 |
moment | -0.124 |
isel | -0.119 |
rated | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
rob | +0.348 |
rides | +0.337 |
ons | +0.332 |
opl | +0.316 |
cand | +0.301 |
Neg logit contributions | |
kin | -0.290 |
upon | -0.254 |
isel | -0.248 |
moment | -0.241 |
rated | -0.236 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
kin | +0.020 |
upon | +0.017 |
isel | +0.017 |
moment | +0.016 |
rated | +0.016 |
Neg logit contributions | |
rob | -0.024 |
rides | -0.024 |
ons | -0.023 |
opl | -0.022 |
cand | -0.021 |
Token | went |
Token ID | 1816 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
kin | +0.046 |
upon | +0.046 |
moment | +0.039 |
isel | +0.038 |
cca | +0.037 |
Neg logit contributions | |
rob | -0.070 |
opl | -0.066 |
ons | -0.064 |
rides | -0.062 |
cand | -0.059 |
Token | on |
Token ID | 319 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
rob | +0.056 |
ons | +0.055 |
rides | +0.053 |
opl | +0.052 |
cand | +0.049 |
Neg logit contributions | |
kin | -0.049 |
upon | -0.047 |
moment | -0.044 |
isel | -0.042 |
inn | -0.041 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
kin | +0.026 |
upon | +0.023 |
isel | +0.022 |
moment | +0.021 |
rated | +0.020 |
Neg logit contributions | |
rob | -0.030 |
rides | -0.029 |
ons | -0.029 |
opl | -0.028 |
cand | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
rides | +0.822 |
rob | +0.794 |
ons | +0.757 |
opl | +0.691 |
cand | +0.673 |
Neg logit contributions | |
kin | -0.869 |
isel | -0.804 |
rated | -0.745 |
upon | -0.735 |
loser | -0.718 |
Token | met |
Token ID | 1138 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
opl | +0.003 |
rob | +0.003 |
ons | +0.002 |
rides | +0.002 |
cream | +0.002 |
Neg logit contributions | |
kin | -0.003 |
upon | -0.002 |
moment | -0.002 |
rated | -0.002 |
halfway | -0.002 |
Token | new |
Token ID | 649 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
rides | +0.238 |
rob | +0.224 |
ons | +0.218 |
kisses | +0.195 |
cand | +0.194 |
Neg logit contributions | |
kin | -0.351 |
isel | -0.326 |
rated | -0.310 |
upon | -0.301 |
loser | -0.297 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
rob | +0.118 |
rides | +0.116 |
ons | +0.111 |
opl | +0.101 |
cand | +0.095 |
Neg logit contributions | |
kin | -0.191 |
isel | -0.172 |
upon | -0.171 |
rated | -0.165 |
moment | -0.164 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
rob | +0.254 |
rides | +0.254 |
ons | +0.244 |
opl | +0.227 |
cand | +0.219 |
Neg logit contributions | |
kin | -0.234 |
isel | -0.205 |
upon | -0.200 |
rated | -0.194 |
moment | -0.191 |
Token | she |
Token ID | 673 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
kin | +0.102 |
isel | +0.090 |
upon | +0.088 |
rated | +0.086 |
moment | +0.084 |
Neg logit contributions | |
rides | -0.091 |
rob | -0.091 |
ons | -0.088 |
opl | -0.080 |
cand | -0.079 |
Token | would |
Token ID | 561 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
rob | +0.223 |
opl | +0.212 |
ons | +0.208 |
rides | +0.201 |
handed | +0.193 |
Neg logit contributions | |
kin | -0.144 |
upon | -0.131 |
isel | -0.123 |
moment | -0.118 |
rated | -0.115 |
Token | go |
Token ID | 467 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
kin | +0.167 |
upon | +0.153 |
isel | +0.150 |
particular | +0.147 |
moment | +0.145 |
Neg logit contributions | |
rob | -0.201 |
ons | -0.176 |
pill | -0.168 |
rides | -0.165 |
cream | -0.163 |
Token | on |
Token ID | 319 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
rob | +0.003 |
ons | +0.003 |
opl | +0.003 |
pill | +0.003 |
rides | +0.003 |
Neg logit contributions | |
upon | -0.003 |
kin | -0.002 |
moment | -0.002 |
particular | -0.002 |
inn | -0.002 |
Token | nice |
Token ID | 3621 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
kin | +0.028 |
upon | +0.026 |
moment | +0.025 |
isel | +0.024 |
particular | +0.023 |
Neg logit contributions | |
rob | -0.036 |
ons | -0.034 |
rides | -0.034 |
opl | -0.033 |
cream | -0.032 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
rob | +0.103 |
ons | +0.089 |
cream | +0.089 |
opl | +0.089 |
pill | +0.086 |
Neg logit contributions | |
kin | -0.124 |
moment | -0.118 |
upon | -0.117 |
isel | -0.113 |
particular | -0.108 |
Token | around |
Token ID | 1088 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
rob | +0.912 |
rides | +0.881 |
ons | +0.868 |
opl | +0.825 |
cand | +0.786 |
Neg logit contributions | |
kin | -0.762 |
upon | -0.662 |
isel | -0.632 |
moment | -0.630 |
rated | -0.606 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
kin | +0.093 |
isel | +0.085 |
rated | +0.081 |
upon | +0.079 |
loser | +0.076 |
Neg logit contributions | |
rides | -0.090 |
rob | -0.088 |
ons | -0.086 |
opl | -0.078 |
course | -0.076 |
Token | neighbourhood |
Token ID | 19495 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
kin | +0.036 |
upon | +0.033 |
moment | +0.032 |
isel | +0.031 |
loser | +0.030 |
Neg logit contributions | |
rob | -0.028 |
ons | -0.025 |
rides | -0.025 |
opl | -0.024 |
pill | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
rob | +0.232 |
ons | +0.214 |
opl | +0.210 |
rides | +0.202 |
kisses | +0.197 |
Neg logit contributions | |
kin | -0.123 |
upon | -0.115 |
moment | -0.110 |
particular | -0.092 |
runner | -0.091 |
Token | always |
Token ID | 1464 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
upon | +0.004 |
kin | +0.004 |
moment | +0.004 |
isel | +0.003 |
particular | +0.003 |
Neg logit contributions | |
rob | -0.005 |
ons | -0.005 |
rides | -0.004 |
opl | -0.004 |
cream | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
kin | +0.027 |
upon | +0.025 |
isel | +0.024 |
moment | +0.024 |
particular | +0.022 |
Neg logit contributions | |
rob | -0.033 |
rides | -0.032 |
ons | -0.031 |
opl | -0.029 |
cand | -0.029 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
kin | +0.167 |
upon | +0.142 |
moment | +0.138 |
rated | +0.135 |
isel | +0.134 |
Neg logit contributions | |
rob | -0.244 |
ons | -0.239 |
rides | -0.236 |
opl | -0.228 |
cand | -0.217 |
Token | taking |
Token ID | 2263 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
rob | +0.110 |
ons | +0.103 |
rides | +0.102 |
opl | +0.099 |
handed | +0.095 |
Neg logit contributions | |
kin | -0.085 |
upon | -0.079 |
moment | -0.078 |
isel | -0.074 |
particular | -0.070 |
Token | people |
Token ID | 661 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
rob | +0.142 |
ons | +0.129 |
rides | +0.127 |
opl | +0.124 |
odic | +0.116 |
Neg logit contributions | |
kin | -0.139 |
isel | -0.124 |
upon | -0.123 |
moment | -0.122 |
rated | -0.117 |
Token | for |
Token ID | 329 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
rob | +0.053 |
opl | +0.047 |
pill | +0.045 |
course | +0.044 |
ons | +0.044 |
Neg logit contributions | |
upon | -0.036 |
kin | -0.035 |
moment | -0.034 |
don | -0.031 |
art | -0.031 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
kin | +0.010 |
isel | +0.009 |
moment | +0.009 |
upon | +0.009 |
loser | +0.008 |
Neg logit contributions | |
rob | -0.012 |
ons | -0.012 |
rides | -0.011 |
opl | -0.011 |
pill | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
rob | +0.867 |
rides | +0.865 |
ons | +0.833 |
opl | +0.778 |
cand | +0.745 |
Neg logit contributions | |
kin | -0.797 |
isel | -0.701 |
upon | -0.689 |
rated | -0.659 |
moment | -0.653 |
Token | One |
Token ID | 1881 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
kin | +0.027 |
upon | +0.024 |
isel | +0.023 |
moment | +0.023 |
rated | +0.022 |
Neg logit contributions | |
rob | -0.030 |
rides | -0.030 |
ons | -0.029 |
opl | -0.027 |
cand | -0.026 |
Token | day |
Token ID | 1110 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
kin | +0.060 |
isel | +0.054 |
upon | +0.051 |
rated | +0.049 |
inn | +0.048 |
Neg logit contributions | |
rides | -0.067 |
rob | -0.066 |
ons | -0.064 |
opl | -0.061 |
cand | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
kin | +0.125 |
rated | +0.118 |
isel | +0.114 |
ac | +0.109 |
uzz | +0.108 |
Neg logit contributions | |
rides | -0.070 |
ons | -0.068 |
rob | -0.059 |
cand | -0.055 |
course | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
rides | +0.003 |
ons | +0.002 |
rob | +0.002 |
course | +0.002 |
cand | +0.002 |
Neg logit contributions | |
kin | -0.003 |
isel | -0.003 |
rated | -0.003 |
inn | -0.003 |
ac | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
rob | +0.174 |
opl | +0.164 |
odic | +0.149 |
ons | +0.148 |
rides | +0.147 |
Neg logit contributions | |
upon | -0.111 |
kin | -0.106 |
moment | -0.098 |
thing | -0.093 |
particular | -0.093 |
Token | sc |
Token ID | 629 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
rob | +0.083 |
rides | +0.081 |
ons | +0.080 |
opl | +0.076 |
cand | +0.071 |
Neg logit contributions | |
kin | -0.049 |
upon | -0.041 |
isel | -0.039 |
moment | -0.039 |
particular | -0.036 |
Token | ooter |
Token ID | 25141 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
rob | +0.660 |
rides | +0.572 |
ons | +0.551 |
course | +0.537 |
cand | +0.512 |
Neg logit contributions | |
kin | -0.578 |
upon | -0.572 |
uzz | -0.520 |
isel | -0.514 |
inn | -0.509 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
rob | +0.516 |
ons | +0.489 |
pill | +0.460 |
opl | +0.456 |
odic | +0.447 |
Neg logit contributions | |
kin | -0.207 |
upon | -0.169 |
moment | -0.154 |
thing | -0.153 |
particular | -0.148 |
Token | He |
Token ID | 679 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
kin | +0.025 |
upon | +0.022 |
rated | +0.022 |
isel | +0.021 |
footing | +0.021 |
Neg logit contributions | |
rides | -0.016 |
rob | -0.014 |
opl | -0.013 |
ons | -0.013 |
course | -0.012 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
rob | +0.070 |
ons | +0.068 |
rides | +0.067 |
opl | +0.064 |
cand | +0.062 |
Neg logit contributions | |
kin | -0.055 |
upon | -0.050 |
isel | -0.046 |
moment | -0.045 |
particular | -0.044 |
Token | it |
Token ID | 340 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
rides | +0.888 |
rob | +0.844 |
ons | +0.808 |
opl | +0.728 |
cand | +0.713 |
Neg logit contributions | |
kin | -0.836 |
isel | -0.754 |
rated | -0.713 |
upon | -0.689 |
loser | -0.670 |
Token | every |
Token ID | 790 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
kin | +0.329 |
isel | +0.291 |
upon | +0.277 |
rated | +0.270 |
moment | +0.264 |
Neg logit contributions | |
rides | -0.352 |
rob | -0.350 |
ons | -0.334 |
opl | -0.313 |
cand | -0.297 |
Token | day |
Token ID | 1110 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
rides | +0.052 |
rob | +0.051 |
ons | +0.048 |
opl | +0.046 |
course | +0.044 |
Neg logit contributions | |
kin | -0.050 |
isel | -0.046 |
upon | -0.044 |
rated | -0.041 |
loser | -0.040 |
Token | in |
Token ID | 287 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
kin | +0.069 |
upon | +0.063 |
moment | +0.057 |
isel | +0.056 |
inn | +0.055 |
Neg logit contributions | |
rob | -0.108 |
ons | -0.100 |
rides | -0.099 |
opl | -0.095 |
cand | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
kin | +0.163 |
isel | +0.147 |
rated | +0.146 |
upon | +0.139 |
inn | +0.132 |
Neg logit contributions | |
rides | -0.153 |
rob | -0.148 |
ons | -0.143 |
opl | -0.137 |
course | -0.129 |
Token | by |
Token ID | 1525 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
rob | +0.170 |
rides | +0.168 |
ons | +0.162 |
opl | +0.157 |
cand | +0.151 |
Neg logit contributions | |
kin | -0.076 |
upon | -0.062 |
isel | -0.059 |
moment | -0.056 |
rated | -0.055 |
Token | would |
Token ID | 561 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
kin | +0.252 |
upon | +0.218 |
ac | +0.203 |
isel | +0.202 |
moment | +0.200 |
Neg logit contributions | |
rob | -0.339 |
rides | -0.315 |
opl | -0.305 |
ons | -0.301 |
cand | -0.292 |
Token | go |
Token ID | 467 |
Feature activation | +3.74e-03 |
Pos logit contributions | |
kin | +0.152 |
upon | +0.134 |
isel | +0.133 |
particular | +0.133 |
moment | +0.128 |
Neg logit contributions | |
rob | -0.218 |
ons | -0.198 |
pill | -0.184 |
rides | -0.182 |
cream | -0.180 |
Token | for |
Token ID | 329 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
rob | +0.008 |
ons | +0.008 |
opl | +0.008 |
pill | +0.008 |
cand | +0.008 |
Neg logit contributions | |
upon | -0.005 |
moment | -0.005 |
kin | -0.004 |
inn | -0.004 |
particular | -0.004 |
Token | long |
Token ID | 890 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
kin | +0.013 |
moment | +0.012 |
isel | +0.011 |
upon | +0.011 |
disaster | +0.011 |
Neg logit contributions | |
ons | -0.017 |
rob | -0.017 |
opl | -0.016 |
grand | -0.015 |
rides | -0.015 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
kin | +0.116 |
moment | +0.112 |
upon | +0.111 |
isel | +0.106 |
rated | +0.105 |
Neg logit contributions | |
rob | -0.084 |
ons | -0.075 |
cream | -0.073 |
odic | -0.073 |
opl | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
rob | +0.904 |
rides | +0.871 |
ons | +0.867 |
opl | +0.822 |
cand | +0.786 |
Neg logit contributions | |
kin | -0.758 |
upon | -0.659 |
isel | -0.634 |
moment | -0.627 |
rated | -0.608 |
Token | Even |
Token ID | 3412 |
Feature activation | -8.47e-03 |
Pos logit contributions | |
kin | +0.024 |
isel | +0.022 |
upon | +0.022 |
moment | +0.021 |
inn | +0.020 |
Neg logit contributions | |
rob | -0.031 |
ons | -0.030 |
rides | -0.029 |
opl | -0.027 |
cand | -0.026 |
Token | though |
Token ID | 996 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
kin | +0.013 |
isel | +0.011 |
rated | +0.010 |
upon | +0.010 |
OO | +0.010 |
Neg logit contributions | |
rides | -0.019 |
rob | -0.018 |
ons | -0.017 |
opl | -0.016 |
cand | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
kin | +0.471 |
isel | +0.418 |
rated | +0.409 |
upon | +0.398 |
inn | +0.386 |
Neg logit contributions | |
rides | -0.411 |
rob | -0.394 |
ons | -0.377 |
opl | -0.344 |
cand | -0.343 |
Token | man |
Token ID | 582 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
kin | +0.025 |
upon | +0.023 |
moment | +0.023 |
rated | +0.022 |
isel | +0.022 |
Neg logit contributions | |
rob | -0.020 |
ons | -0.020 |
rides | -0.018 |
opl | -0.017 |
cream | -0.016 |
Token | now |
Token ID | 783 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
rob | +0.240 |
rides | +0.220 |
ons | +0.216 |
opl | +0.215 |
cand | +0.196 |
Neg logit contributions | |
kin | -0.190 |
upon | -0.162 |
moment | -0.155 |
isel | -0.152 |
ac | -0.145 |
Token | invites |
Token ID | 27671 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
rob | +0.009 |
rides | +0.008 |
ons | +0.008 |
opl | +0.008 |
cand | +0.008 |
Neg logit contributions | |
kin | -0.008 |
upon | -0.007 |
isel | -0.007 |
moment | -0.007 |
rated | -0.007 |
Token | everyone |
Token ID | 2506 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
rob | +0.281 |
rides | +0.260 |
ons | +0.252 |
opl | +0.250 |
cream | +0.233 |
Neg logit contributions | |
kin | -0.210 |
upon | -0.193 |
moment | -0.180 |
isel | -0.175 |
rated | -0.167 |
Token | to |
Token ID | 284 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
kin | +0.092 |
upon | +0.086 |
moment | +0.080 |
isel | +0.076 |
ac | +0.074 |
Neg logit contributions | |
rob | -0.108 |
rides | -0.100 |
ons | -0.097 |
opl | -0.096 |
cand | -0.089 |
Token | hey |
Token ID | 17207 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
rob | +0.131 |
rides | +0.114 |
ons | +0.112 |
opl | +0.109 |
cream | +0.108 |
Neg logit contributions | |
kin | -0.110 |
upon | -0.101 |
moment | -0.096 |
isel | -0.093 |
particular | -0.091 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
kin | +0.243 |
isel | +0.215 |
upon | +0.208 |
rated | +0.202 |
moment | +0.200 |
Neg logit contributions | |
rides | -0.247 |
rob | -0.246 |
ons | -0.241 |
opl | -0.221 |
cand | -0.213 |
Token | and |
Token ID | 290 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
rob | +0.891 |
rides | +0.879 |
ons | +0.853 |
opl | +0.802 |
cand | +0.768 |
Neg logit contributions | |
kin | -0.773 |
upon | -0.667 |
isel | -0.667 |
moment | -0.633 |
rated | -0.632 |
Token | even |
Token ID | 772 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
kin | +0.009 |
upon | +0.009 |
moment | +0.009 |
isel | +0.008 |
don | +0.008 |
Neg logit contributions | |
rob | -0.012 |
opl | -0.010 |
rides | -0.010 |
ons | -0.010 |
cream | -0.010 |
Token | gives |
Token ID | 3607 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
kin | +0.111 |
upon | +0.098 |
isel | +0.096 |
moment | +0.093 |
rated | +0.091 |
Neg logit contributions | |
rob | -0.123 |
rides | -0.119 |
ons | -0.116 |
opl | -0.111 |
cand | -0.104 |
Token | them |
Token ID | 606 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
rob | +0.316 |
rides | +0.308 |
ons | +0.296 |
opl | +0.287 |
cand | +0.270 |
Neg logit contributions | |
kin | -0.240 |
upon | -0.208 |
isel | -0.204 |
moment | -0.197 |
rated | -0.193 |
Token | a |
Token ID | 257 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
kin | +0.207 |
upon | +0.204 |
moment | +0.181 |
ac | +0.171 |
particular | +0.160 |
Neg logit contributions | |
rob | -0.332 |
opl | -0.299 |
ons | -0.278 |
rides | -0.277 |
odic | -0.258 |
Token | fair |
Token ID | 3148 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
kin | +0.088 |
moment | +0.078 |
upon | +0.076 |
rated | +0.073 |
particular | +0.070 |
Neg logit contributions | |
rob | -0.117 |
ons | -0.112 |
rides | -0.111 |
opl | -0.105 |
cand | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
rides | +0.163 |
rob | +0.160 |
ons | +0.156 |
opl | +0.145 |
cand | +0.141 |
Neg logit contributions | |
kin | -0.156 |
isel | -0.138 |
upon | -0.132 |
rated | -0.129 |
moment | -0.126 |
Token | She |
Token ID | 1375 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
kin | +0.035 |
isel | +0.031 |
upon | +0.030 |
rated | +0.030 |
moment | +0.029 |
Neg logit contributions | |
rides | -0.028 |
rob | -0.028 |
ons | -0.027 |
opl | -0.025 |
cand | -0.024 |
Token | went |
Token ID | 1816 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
rob | +0.227 |
rides | +0.216 |
ons | +0.215 |
opl | +0.204 |
cand | +0.194 |
Neg logit contributions | |
kin | -0.191 |
upon | -0.169 |
isel | -0.164 |
moment | -0.159 |
rated | -0.157 |
Token | on |
Token ID | 319 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
rob | +0.046 |
ons | +0.044 |
rides | +0.043 |
opl | +0.042 |
cand | +0.040 |
Neg logit contributions | |
kin | -0.038 |
upon | -0.035 |
moment | -0.033 |
isel | -0.032 |
inn | -0.031 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
kin | +0.034 |
upon | +0.032 |
moment | +0.030 |
isel | +0.029 |
particular | +0.028 |
Neg logit contributions | |
rob | -0.039 |
ons | -0.036 |
rides | -0.036 |
opl | -0.035 |
cream | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
rides | +0.830 |
rob | +0.802 |
ons | +0.767 |
opl | +0.702 |
cand | +0.682 |
Neg logit contributions | |
kin | -0.850 |
isel | -0.787 |
rated | -0.724 |
upon | -0.717 |
loser | -0.703 |
Token | ate |
Token ID | 15063 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
kin | +0.008 |
upon | +0.008 |
moment | +0.008 |
isel | +0.007 |
rated | +0.007 |
Neg logit contributions | |
rob | -0.009 |
ons | -0.009 |
opl | -0.009 |
rides | -0.009 |
cand | -0.008 |
Token | tasty |
Token ID | 25103 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
rob | +0.463 |
rides | +0.442 |
ons | +0.434 |
opl | +0.415 |
grand | +0.378 |
Neg logit contributions | |
kin | -0.521 |
upon | -0.463 |
moment | -0.446 |
isel | -0.445 |
rated | -0.425 |
Token | food |
Token ID | 2057 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
rob | +0.223 |
opl | +0.212 |
grand | +0.205 |
yard | +0.200 |
handed | +0.199 |
Neg logit contributions | |
kin | -0.372 |
moment | -0.359 |
thing | -0.344 |
upon | -0.343 |
isel | -0.330 |
Token | and |
Token ID | 290 |
Feature activation | -8.30e-04 |
Pos logit contributions | |
rob | +0.523 |
ons | +0.483 |
rides | +0.479 |
opl | +0.476 |
grand | +0.445 |
Neg logit contributions | |
kin | -0.315 |
upon | -0.248 |
moment | -0.242 |
particular | -0.218 |
inn | -0.206 |
Token | day |
Token ID | 1110 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
rides | +0.112 |
rob | +0.108 |
ons | +0.100 |
opl | +0.095 |
cand | +0.095 |
Neg logit contributions | |
kin | -0.144 |
isel | -0.136 |
upon | -0.127 |
rated | -0.127 |
loser | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
kin | +0.089 |
upon | +0.078 |
isel | +0.075 |
moment | +0.074 |
rated | +0.071 |
Neg logit contributions | |
rob | -0.109 |
rides | -0.104 |
ons | -0.102 |
opl | -0.097 |
cand | -0.093 |
Token | they |
Token ID | 484 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
kin | +0.002 |
isel | +0.002 |
loser | +0.002 |
inn | +0.002 |
rated | +0.002 |
Neg logit contributions | |
rides | -0.003 |
ons | -0.003 |
rob | -0.003 |
opl | -0.003 |
course | -0.003 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
kin | +0.014 |
isel | +0.013 |
loser | +0.012 |
rated | +0.012 |
moment | +0.012 |
Neg logit contributions | |
rides | -0.013 |
rob | -0.013 |
ons | -0.013 |
opl | -0.011 |
cand | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
rob | +0.159 |
rides | +0.157 |
ons | +0.151 |
opl | +0.139 |
cand | +0.133 |
Neg logit contributions | |
kin | -0.196 |
isel | -0.174 |
upon | -0.173 |
rated | -0.168 |
moment | -0.165 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
kin | +0.035 |
upon | +0.031 |
moment | +0.031 |
isel | +0.029 |
rated | +0.029 |
Neg logit contributions | |
rob | -0.035 |
ons | -0.034 |
rides | -0.033 |
opl | -0.032 |
pill | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
rob | +0.927 |
rides | +0.894 |
ons | +0.884 |
opl | +0.842 |
cand | +0.801 |
Neg logit contributions | |
kin | -0.747 |
upon | -0.641 |
isel | -0.613 |
moment | -0.611 |
rated | -0.596 |
Token | They |
Token ID | 1119 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
kin | +0.043 |
loser | +0.037 |
isel | +0.036 |
rated | +0.035 |
ac | +0.034 |
Neg logit contributions | |
rides | -0.025 |
ons | -0.023 |
rob | -0.022 |
opl | -0.020 |
kisses | -0.020 |
Token | brought |
Token ID | 3181 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
rides | +0.029 |
rob | +0.029 |
ons | +0.028 |
opl | +0.026 |
cand | +0.025 |
Neg logit contributions | |
kin | -0.031 |
isel | -0.027 |
upon | -0.027 |
rated | -0.026 |
moment | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
rob | +0.201 |
rides | +0.187 |
ons | +0.187 |
opl | +0.186 |
pill | +0.169 |
Neg logit contributions | |
kin | -0.161 |
upon | -0.144 |
isel | -0.138 |
moment | -0.137 |
rated | -0.128 |
Token | huge |
Token ID | 3236 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
kin | +0.024 |
upon | +0.022 |
moment | +0.021 |
isel | +0.020 |
particular | +0.019 |
Neg logit contributions | |
rob | -0.027 |
ons | -0.025 |
rides | -0.025 |
opl | -0.025 |
pill | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -8.25e-04 |
Pos logit contributions | |
kin | +0.004 |
upon | +0.003 |
moment | +0.003 |
rated | +0.003 |
isel | +0.003 |
Neg logit contributions | |
rob | -0.006 |
rides | -0.006 |
kisses | -0.006 |
ons | -0.006 |
opl | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
kin | +0.001 |
isel | +0.001 |
upon | +0.001 |
rated | +0.001 |
moment | +0.001 |
Neg logit contributions | |
rob | -0.002 |
rides | -0.002 |
ons | -0.001 |
opl | -0.001 |
cand | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
rob | +0.182 |
rides | +0.176 |
ons | +0.169 |
opl | +0.162 |
cand | +0.155 |
Neg logit contributions | |
kin | -0.152 |
upon | -0.136 |
isel | -0.132 |
moment | -0.130 |
rated | -0.128 |
Token | other |
Token ID | 584 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
kin | +0.038 |
isel | +0.034 |
upon | +0.033 |
rated | +0.032 |
moment | +0.032 |
Neg logit contributions | |
rob | -0.031 |
rides | -0.031 |
ons | -0.029 |
opl | -0.027 |
cand | -0.026 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
rob | +0.187 |
rides | +0.186 |
ons | +0.179 |
opl | +0.165 |
cand | +0.159 |
Neg logit contributions | |
kin | -0.211 |
isel | -0.186 |
upon | -0.184 |
rated | -0.178 |
moment | -0.176 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
rob | +0.318 |
rides | +0.312 |
ons | +0.302 |
opl | +0.285 |
cand | +0.270 |
Neg logit contributions | |
kin | -0.311 |
upon | -0.272 |
isel | -0.271 |
moment | -0.259 |
rated | -0.258 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
rides | +0.853 |
rob | +0.836 |
ons | +0.811 |
opl | +0.742 |
cand | +0.719 |
Neg logit contributions | |
kin | -0.815 |
isel | -0.739 |
upon | -0.698 |
rated | -0.677 |
moment | -0.662 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
kin | +0.040 |
isel | +0.035 |
rated | +0.034 |
upon | +0.034 |
moment | +0.034 |
Neg logit contributions | |
rides | -0.022 |
ons | -0.021 |
rob | -0.021 |
opl | -0.019 |
kisses | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
rides | +0.361 |
ons | +0.329 |
rob | +0.327 |
cand | +0.317 |
opl | +0.312 |
Neg logit contributions | |
kin | -0.233 |
rated | -0.216 |
isel | -0.211 |
inn | -0.195 |
upon | -0.194 |
Token | said |
Token ID | 531 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
upon | +0.328 |
kin | +0.314 |
moment | +0.283 |
cca | +0.274 |
ac | +0.271 |
Neg logit contributions | |
rob | -0.349 |
opl | -0.327 |
rides | -0.314 |
pill | -0.284 |
ons | -0.283 |
Token | , |
Token ID | 11 |
Feature activation | -7.73e-04 |
Pos logit contributions | |
rides | +0.349 |
ons | +0.347 |
rob | +0.325 |
cand | +0.318 |
kisses | +0.300 |
Neg logit contributions | |
kin | -0.423 |
isel | -0.394 |
rated | -0.390 |
upon | -0.373 |
inn | -0.368 |
Token | excited |
Token ID | 6568 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
kin | +0.002 |
upon | +0.002 |
moment | +0.002 |
rated | +0.002 |
don | +0.002 |
Neg logit contributions | |
rob | -0.003 |
opl | -0.003 |
ons | -0.003 |
pill | -0.002 |
course | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
kin | +0.124 |
upon | +0.115 |
moment | +0.108 |
isel | +0.105 |
rated | +0.105 |
Neg logit contributions | |
rob | -0.155 |
rides | -0.145 |
ons | -0.142 |
opl | -0.139 |
cand | -0.126 |
Token | pay |
Token ID | 1414 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
rob | +0.139 |
ons | +0.127 |
rides | +0.124 |
pill | +0.122 |
cand | +0.118 |
Neg logit contributions | |
kin | -0.115 |
isel | -0.100 |
particular | -0.097 |
moment | -0.097 |
upon | -0.095 |
Token | for |
Token ID | 329 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
rob | +0.334 |
rides | +0.331 |
ons | +0.320 |
opl | +0.299 |
cand | +0.287 |
Neg logit contributions | |
kin | -0.312 |
isel | -0.272 |
upon | -0.270 |
rated | -0.258 |
moment | -0.257 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
kin | +0.015 |
upon | +0.013 |
isel | +0.013 |
moment | +0.013 |
particular | +0.012 |
Neg logit contributions | |
rob | -0.019 |
ons | -0.018 |
rides | -0.018 |
opl | -0.017 |
cream | -0.016 |
Token | rides |
Token ID | 17445 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
kin | +0.033 |
moment | +0.031 |
upon | +0.031 |
isel | +0.029 |
loser | +0.029 |
Neg logit contributions | |
rob | -0.025 |
ons | -0.025 |
rides | -0.022 |
opl | -0.021 |
cream | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e-03 |
Pos logit contributions | |
rob | +0.959 |
rides | +0.899 |
ons | +0.893 |
opl | +0.859 |
cand | +0.814 |
Neg logit contributions | |
kin | -0.731 |
upon | -0.624 |
moment | -0.600 |
rated | -0.570 |
isel | -0.566 |
Token | she |
Token ID | 673 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
kin | +0.003 |
upon | +0.003 |
moment | +0.003 |
don | +0.003 |
halfway | +0.003 |
Neg logit contributions | |
rob | -0.004 |
ons | -0.003 |
opl | -0.003 |
pill | -0.003 |
odic | -0.003 |
Token | played |
Token ID | 2826 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
rob | +0.205 |
ons | +0.192 |
opl | +0.189 |
rides | +0.178 |
cand | +0.172 |
Neg logit contributions | |
kin | -0.170 |
upon | -0.148 |
isel | -0.137 |
moment | -0.135 |
rated | -0.133 |
Token | for |
Token ID | 329 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
rides | +0.414 |
rob | +0.408 |
ons | +0.386 |
opl | +0.357 |
cand | +0.343 |
Neg logit contributions | |
kin | -0.430 |
isel | -0.392 |
upon | -0.379 |
rated | -0.374 |
moment | -0.360 |
Token | a |
Token ID | 257 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
kin | +0.015 |
upon | +0.012 |
isel | +0.012 |
moment | +0.012 |
rated | +0.012 |
Neg logit contributions | |
rob | -0.018 |
rides | -0.017 |
ons | -0.017 |
opl | -0.016 |
cand | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
kin | +0.062 |
upon | +0.056 |
isel | +0.054 |
moment | +0.053 |
rated | +0.052 |
Neg logit contributions | |
rob | -0.062 |
rides | -0.060 |
ons | -0.058 |
opl | -0.054 |
cand | -0.052 |
Token | packed |
Token ID | 11856 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
rob | +0.199 |
rides | +0.184 |
ons | +0.184 |
opl | +0.177 |
cand | +0.168 |
Neg logit contributions | |
kin | -0.161 |
upon | -0.147 |
isel | -0.138 |
moment | -0.134 |
rated | -0.133 |
Token | up |
Token ID | 510 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
rob | +0.106 |
rides | +0.100 |
ons | +0.097 |
opl | +0.097 |
pill | +0.089 |
Neg logit contributions | |
kin | -0.096 |
upon | -0.086 |
isel | -0.081 |
moment | -0.081 |
rated | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
kin | +0.121 |
upon | +0.113 |
moment | +0.104 |
isel | +0.100 |
particular | +0.098 |
Neg logit contributions | |
rob | -0.134 |
opl | -0.124 |
ons | -0.123 |
rides | -0.122 |
odic | -0.112 |
Token | nap |
Token ID | 25422 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
kin | +0.061 |
upon | +0.056 |
moment | +0.054 |
isel | +0.051 |
rated | +0.050 |
Neg logit contributions | |
rob | -0.054 |
ons | -0.051 |
rides | -0.050 |
opl | -0.049 |
odic | -0.043 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
rob | +0.163 |
rides | +0.162 |
ons | +0.159 |
opl | +0.152 |
cand | +0.149 |
Neg logit contributions | |
kin | -0.034 |
isel | -0.022 |
upon | -0.022 |
rated | -0.018 |
moment | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
kin | +0.825 |
upon | +0.700 |
moment | +0.619 |
inn | +0.567 |
ac | +0.555 |
Neg logit contributions | |
rob | -1.210 |
rides | -1.125 |
opl | -1.119 |
ons | -1.063 |
pill | -1.025 |
Token | they |
Token ID | 484 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
kin | +0.017 |
upon | +0.015 |
moment | +0.014 |
rated | +0.013 |
isel | +0.013 |
Neg logit contributions | |
opl | -0.019 |
rob | -0.019 |
ons | -0.018 |
rides | -0.017 |
pill | -0.017 |
Token | both |
Token ID | 1111 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
kin | +0.027 |
upon | +0.024 |
isel | +0.022 |
moment | +0.022 |
rated | +0.021 |
Neg logit contributions | |
rob | -0.028 |
opl | -0.026 |
ons | -0.026 |
rides | -0.026 |
pill | -0.024 |
Token | marched |
Token ID | 23558 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
rob | +0.148 |
rides | +0.138 |
ons | +0.138 |
opl | +0.135 |
cand | +0.122 |
Neg logit contributions | |
kin | -0.148 |
upon | -0.128 |
isel | -0.123 |
moment | -0.121 |
rated | -0.121 |
Token | back |
Token ID | 736 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
kin | +0.155 |
isel | +0.139 |
upon | +0.131 |
rated | +0.131 |
loser | +0.126 |
Neg logit contributions | |
rides | -0.148 |
rob | -0.144 |
ons | -0.137 |
opl | -0.125 |
cand | -0.123 |
Token | so |
Token ID | 523 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
kin | +0.025 |
upon | +0.025 |
isel | +0.023 |
moment | +0.023 |
particular | +0.021 |
Neg logit contributions | |
rob | -0.032 |
rides | -0.028 |
opl | -0.028 |
ons | -0.028 |
handed | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
rides | +0.231 |
ons | +0.227 |
rob | +0.222 |
cand | +0.192 |
opl | +0.188 |
Neg logit contributions | |
kin | -0.431 |
isel | -0.400 |
rated | -0.393 |
upon | -0.382 |
moment | -0.373 |
Token | took |
Token ID | 1718 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
rob | +0.170 |
rides | +0.166 |
ons | +0.160 |
opl | +0.154 |
cand | +0.143 |
Neg logit contributions | |
kin | -0.171 |
isel | -0.149 |
upon | -0.149 |
rated | -0.141 |
moment | -0.141 |
Token | a |
Token ID | 257 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
rides | +0.041 |
ons | +0.039 |
rob | +0.039 |
cand | +0.035 |
kisses | +0.035 |
Neg logit contributions | |
kin | -0.042 |
rated | -0.037 |
upon | -0.037 |
isel | -0.037 |
moment | -0.035 |
Token | nap |
Token ID | 25422 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
kin | +0.045 |
rated | +0.039 |
isel | +0.039 |
loser | +0.038 |
ac | +0.037 |
Neg logit contributions | |
ons | -0.046 |
rides | -0.045 |
rob | -0.044 |
cand | -0.040 |
kisses | -0.039 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
rob | +0.114 |
ons | +0.114 |
rides | +0.113 |
cand | +0.103 |
course | +0.100 |
Neg logit contributions | |
isel | -0.090 |
kin | -0.084 |
rated | -0.084 |
upon | -0.083 |
loser | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
kin | +0.801 |
upon | +0.679 |
moment | +0.608 |
inn | +0.592 |
isel | +0.560 |
Neg logit contributions | |
rob | -1.187 |
rides | -1.111 |
opl | -1.086 |
ons | -1.063 |
pill | -1.016 |
Token | tried |
Token ID | 3088 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
kin | +0.031 |
upon | +0.027 |
isel | +0.026 |
moment | +0.025 |
rated | +0.025 |
Neg logit contributions | |
rob | -0.032 |
rides | -0.031 |
ons | -0.030 |
opl | -0.029 |
cand | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
kin | +0.112 |
isel | +0.100 |
rated | +0.097 |
upon | +0.097 |
loser | +0.094 |
Neg logit contributions | |
rides | -0.079 |
rob | -0.077 |
ons | -0.076 |
opl | -0.067 |
cand | -0.067 |
Token | polish |
Token ID | 25245 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
rides | +0.101 |
rob | +0.098 |
ons | +0.096 |
opl | +0.088 |
cand | +0.086 |
Neg logit contributions | |
kin | -0.106 |
isel | -0.094 |
upon | -0.094 |
rated | -0.091 |
moment | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
kin | +0.132 |
isel | +0.131 |
rated | +0.125 |
upon | +0.117 |
loser | +0.117 |
Neg logit contributions | |
rob | -0.121 |
ons | -0.121 |
rides | -0.120 |
cand | -0.108 |
kisses | -0.104 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
rob | +0.172 |
opl | +0.168 |
rides | +0.160 |
ons | +0.153 |
rell | +0.136 |
Neg logit contributions | |
kin | -0.229 |
upon | -0.212 |
moment | -0.192 |
cca | -0.192 |
isel | -0.190 |
Token | her |
Token ID | 607 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
rides | +0.290 |
ons | +0.285 |
rob | +0.282 |
cand | +0.260 |
kisses | +0.255 |
Neg logit contributions | |
kin | -0.331 |
isel | -0.295 |
rated | -0.282 |
upon | -0.274 |
loser | -0.270 |
Token | a |
Token ID | 257 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
rides | +0.065 |
rob | +0.064 |
ons | +0.063 |
kisses | +0.058 |
cand | +0.057 |
Neg logit contributions | |
kin | -0.067 |
isel | -0.061 |
rated | -0.058 |
upon | -0.057 |
loser | -0.056 |
Token | new |
Token ID | 649 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
kin | +0.046 |
upon | +0.042 |
moment | +0.040 |
isel | +0.039 |
particular | +0.037 |
Neg logit contributions | |
rob | -0.042 |
rides | -0.041 |
ons | -0.039 |
opl | -0.038 |
cream | -0.034 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
rides | +0.116 |
rob | +0.113 |
ons | +0.111 |
kisses | +0.103 |
cand | +0.101 |
Neg logit contributions | |
kin | -0.135 |
isel | -0.127 |
rated | -0.124 |
upon | -0.116 |
loser | -0.113 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
rob | +0.203 |
ons | +0.203 |
rides | +0.202 |
cand | +0.192 |
kisses | +0.189 |
Neg logit contributions | |
isel | -0.012 |
upon | -0.005 |
kin | -0.004 |
rated | -0.004 |
moment | +0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
kin | +0.833 |
upon | +0.680 |
moment | +0.624 |
inn | +0.574 |
ac | +0.566 |
Neg logit contributions | |
rob | -1.173 |
rides | -1.094 |
opl | -1.049 |
ons | -1.036 |
pill | -0.973 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
kin | +0.056 |
rated | +0.051 |
isel | +0.050 |
upon | +0.048 |
ac | +0.048 |
Neg logit contributions | |
rides | -0.034 |
ons | -0.031 |
rob | -0.031 |
kisses | -0.030 |
opl | -0.028 |
Token | she |
Token ID | 673 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
kin | +0.039 |
isel | +0.037 |
rated | +0.036 |
upon | +0.035 |
inn | +0.035 |
Neg logit contributions | |
rides | -0.026 |
ons | -0.025 |
rob | -0.024 |
cand | -0.022 |
kisses | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
rob | +0.157 |
rides | +0.148 |
opl | +0.147 |
ons | +0.145 |
course | +0.127 |
Neg logit contributions | |
kin | -0.197 |
upon | -0.174 |
isel | -0.165 |
moment | -0.161 |
rated | -0.160 |
Token | : |
Token ID | 25 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
rides | +0.340 |
ons | +0.334 |
rob | +0.321 |
cand | +0.309 |
kisses | +0.304 |
Neg logit contributions | |
kin | -0.399 |
rated | -0.376 |
isel | -0.370 |
upon | -0.356 |
particular | -0.342 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
rides | +0.318 |
ons | +0.313 |
rob | +0.300 |
kisses | +0.283 |
opl | +0.273 |
Neg logit contributions | |
kin | -0.378 |
isel | -0.349 |
upon | -0.338 |
rated | -0.338 |
loser | -0.321 |
Token | He |
Token ID | 679 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
kin | +0.056 |
rated | +0.053 |
isel | +0.051 |
footing | +0.048 |
upon | +0.048 |
Neg logit contributions | |
rides | -0.039 |
rob | -0.038 |
ons | -0.036 |
opl | -0.034 |
kisses | -0.034 |
Token | used |
Token ID | 973 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
rob | +0.035 |
rides | +0.034 |
ons | +0.033 |
opl | +0.032 |
cand | +0.029 |
Neg logit contributions | |
kin | -0.035 |
upon | -0.030 |
isel | -0.030 |
moment | -0.029 |
rated | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
rides | +0.044 |
rob | +0.044 |
ons | +0.043 |
opl | +0.039 |
cand | +0.038 |
Neg logit contributions | |
kin | -0.046 |
isel | -0.040 |
upon | -0.040 |
rated | -0.039 |
moment | -0.038 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
kin | +0.037 |
isel | +0.033 |
upon | +0.033 |
moment | +0.031 |
rated | +0.031 |
Neg logit contributions | |
rob | -0.033 |
rides | -0.033 |
ons | -0.031 |
opl | -0.029 |
cand | -0.028 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
rob | +0.180 |
ons | +0.180 |
rides | +0.180 |
cand | +0.168 |
opl | +0.166 |
Neg logit contributions | |
kin | -0.034 |
isel | -0.032 |
rated | -0.028 |
upon | -0.028 |
moment | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
kin | +0.901 |
upon | +0.794 |
moment | +0.731 |
isel | +0.710 |
ac | +0.684 |
Neg logit contributions | |
rob | -1.050 |
rides | -0.965 |
opl | -0.930 |
ons | -0.928 |
pill | -0.840 |
Token | wiped |
Token ID | 21122 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
kin | +0.017 |
upon | +0.014 |
isel | +0.014 |
moment | +0.014 |
rated | +0.013 |
Neg logit contributions | |
rob | -0.017 |
rides | -0.016 |
ons | -0.016 |
opl | -0.015 |
cand | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
rides | +0.003 |
rob | +0.003 |
ons | +0.003 |
kisses | +0.003 |
hugs | +0.003 |
Neg logit contributions | |
kin | -0.004 |
upon | -0.003 |
isel | -0.003 |
rated | -0.003 |
loser | -0.003 |
Token | mouth |
Token ID | 5422 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
rob | +0.042 |
rides | +0.040 |
ons | +0.039 |
opl | +0.037 |
cand | +0.035 |
Neg logit contributions | |
kin | -0.034 |
upon | -0.029 |
isel | -0.029 |
moment | -0.028 |
rated | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
rob | +0.036 |
rides | +0.036 |
ons | +0.035 |
opl | +0.033 |
cand | +0.031 |
Neg logit contributions | |
kin | -0.032 |
isel | -0.028 |
upon | -0.028 |
rated | -0.027 |
moment | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
rob | +0.024 |
opl | +0.021 |
rides | +0.021 |
ons | +0.021 |
grand | +0.020 |
Neg logit contributions | |
kin | -0.016 |
upon | -0.015 |
moment | -0.015 |
isel | -0.014 |
disaster | -0.013 |
Token | give |
Token ID | 1577 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
rob | +0.111 |
rides | +0.104 |
ons | +0.103 |
opl | +0.097 |
cand | +0.092 |
Neg logit contributions | |
kin | -0.097 |
isel | -0.083 |
upon | -0.082 |
moment | -0.079 |
rated | -0.077 |
Token | back |
Token ID | 736 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
rob | +0.027 |
rides | +0.027 |
ons | +0.026 |
opl | +0.025 |
cand | +0.023 |
Neg logit contributions | |
kin | -0.025 |
upon | -0.021 |
isel | -0.021 |
moment | -0.020 |
rated | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
rob | +0.093 |
rides | +0.091 |
ons | +0.089 |
opl | +0.084 |
cand | +0.080 |
Neg logit contributions | |
kin | -0.081 |
upon | -0.071 |
isel | -0.071 |
moment | -0.067 |
rated | -0.067 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
rob | +0.032 |
rides | +0.031 |
ons | +0.029 |
opl | +0.027 |
cand | +0.026 |
Neg logit contributions | |
kin | -0.044 |
upon | -0.040 |
isel | -0.039 |
moment | -0.038 |
rated | -0.038 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
rob | +0.205 |
rides | +0.205 |
ons | +0.202 |
opl | +0.192 |
cand | +0.190 |
Neg logit contributions | |
kin | -0.018 |
isel | -0.012 |
upon | -0.009 |
rated | -0.005 |
moment | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
kin | +0.846 |
upon | +0.710 |
moment | +0.662 |
rated | +0.621 |
isel | +0.609 |
Neg logit contributions | |
rob | -1.132 |
rides | -1.042 |
ons | -1.006 |
opl | -0.998 |
pill | -0.935 |
Token | The |
Token ID | 383 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
kin | +0.038 |
upon | +0.034 |
isel | +0.034 |
moment | +0.032 |
rated | +0.032 |
Neg logit contributions | |
rob | -0.040 |
rides | -0.039 |
ons | -0.038 |
opl | -0.035 |
cand | -0.034 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
rob | +0.085 |
rides | +0.085 |
ons | +0.081 |
opl | +0.076 |
cand | +0.074 |
Neg logit contributions | |
kin | -0.090 |
isel | -0.081 |
upon | -0.079 |
rated | -0.077 |
moment | -0.075 |
Token | bunny |
Token ID | 44915 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
rob | +0.094 |
rides | +0.094 |
ons | +0.091 |
opl | +0.082 |
cand | +0.079 |
Neg logit contributions | |
kin | -0.132 |
isel | -0.121 |
upon | -0.118 |
rated | -0.114 |
loser | -0.112 |
Token | agreed |
Token ID | 4987 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
rob | +0.025 |
rides | +0.023 |
opl | +0.023 |
ons | +0.023 |
grand | +0.021 |
Neg logit contributions | |
kin | -0.018 |
upon | -0.015 |
moment | -0.015 |
rated | -0.014 |
isel | -0.014 |
Token | So |
Token ID | 1406 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
kin | +0.046 |
upon | +0.042 |
isel | +0.041 |
moment | +0.040 |
rated | +0.039 |
Neg logit contributions | |
rob | -0.042 |
rides | -0.041 |
ons | -0.040 |
opl | -0.037 |
cand | -0.035 |
Token | she |
Token ID | 673 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
rides | +0.267 |
ons | +0.259 |
rob | +0.259 |
opl | +0.229 |
cand | +0.229 |
Neg logit contributions | |
kin | -0.326 |
isel | -0.295 |
rated | -0.283 |
upon | -0.281 |
loser | -0.271 |
Token | took |
Token ID | 1718 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
rob | +0.167 |
rides | +0.161 |
ons | +0.157 |
opl | +0.152 |
cand | +0.140 |
Neg logit contributions | |
kin | -0.167 |
upon | -0.146 |
isel | -0.145 |
rated | -0.138 |
moment | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
rides | +0.033 |
ons | +0.032 |
rob | +0.032 |
kisses | +0.028 |
opl | +0.028 |
Neg logit contributions | |
kin | -0.032 |
upon | -0.028 |
rated | -0.027 |
isel | -0.027 |
moment | -0.026 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
kin | +0.061 |
isel | +0.055 |
upon | +0.054 |
rated | +0.052 |
inn | +0.051 |
Neg logit contributions | |
rob | -0.057 |
rides | -0.057 |
ons | -0.055 |
opl | -0.050 |
cand | -0.049 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
rob | +0.186 |
rides | +0.184 |
ons | +0.181 |
opl | +0.173 |
cand | +0.170 |
Neg logit contributions | |
kin | -0.039 |
isel | -0.027 |
upon | -0.026 |
rated | -0.022 |
moment | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -7.23e-03 |
Pos logit contributions | |
kin | +0.830 |
upon | +0.733 |
moment | +0.664 |
inn | +0.618 |
isel | +0.614 |
Neg logit contributions | |
rob | -1.143 |
rides | -1.055 |
opl | -1.020 |
ons | -1.011 |
pill | -0.953 |
Token | dipped |
Token ID | 35300 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
kin | +0.012 |
upon | +0.011 |
isel | +0.010 |
moment | +0.010 |
rated | +0.009 |
Neg logit contributions | |
rob | -0.015 |
rides | -0.014 |
opl | -0.014 |
ons | -0.014 |
cand | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
kin | +0.210 |
rated | +0.208 |
isel | +0.204 |
loser | +0.200 |
OO | +0.193 |
Neg logit contributions | |
ons | -0.163 |
rides | -0.142 |
kisses | -0.141 |
cand | -0.139 |
course | -0.138 |
Token | into |
Token ID | 656 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
kin | +0.300 |
upon | +0.254 |
isel | +0.247 |
moment | +0.239 |
rated | +0.236 |
Neg logit contributions | |
rob | -0.445 |
rides | -0.433 |
ons | -0.421 |
opl | -0.404 |
cand | -0.382 |
Token | her |
Token ID | 607 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
kin | +0.117 |
rated | +0.108 |
isel | +0.108 |
upon | +0.103 |
loser | +0.100 |
Neg logit contributions | |
rides | -0.106 |
ons | -0.104 |
rob | -0.103 |
cand | -0.095 |
kisses | -0.093 |
Token | eyes |
Token ID | 2951 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
rob | +0.059 |
rides | +0.054 |
ons | +0.053 |
opl | +0.052 |
cand | +0.048 |
Neg logit contributions | |
kin | -0.041 |
upon | -0.037 |
isel | -0.035 |
moment | -0.034 |
particular | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
kin | +0.135 |
upon | +0.120 |
moment | +0.113 |
isel | +0.111 |
rated | +0.107 |
Neg logit contributions | |
rob | -0.198 |
rides | -0.187 |
ons | -0.183 |
opl | -0.180 |
pill | -0.166 |
Token | took |
Token ID | 1718 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
kin | +0.009 |
upon | +0.008 |
isel | +0.008 |
moment | +0.007 |
rated | +0.007 |
Neg logit contributions | |
rob | -0.011 |
rides | -0.010 |
ons | -0.010 |
opl | -0.010 |
cand | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
rob | +0.025 |
rides | +0.025 |
ons | +0.024 |
opl | +0.023 |
cand | +0.022 |
Neg logit contributions | |
kin | -0.021 |
isel | -0.018 |
upon | -0.018 |
moment | -0.017 |
rated | -0.017 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
kin | +0.047 |
isel | +0.042 |
upon | +0.041 |
rated | +0.040 |
moment | +0.039 |
Neg logit contributions | |
rob | -0.046 |
rides | -0.046 |
ons | -0.045 |
opl | -0.041 |
cand | -0.040 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
rob | +0.158 |
rides | +0.157 |
ons | +0.154 |
opl | +0.146 |
cand | +0.142 |
Neg logit contributions | |
kin | -0.072 |
isel | -0.059 |
upon | -0.058 |
rated | -0.054 |
moment | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -5.03e-03 |
Pos logit contributions | |
kin | +0.807 |
upon | +0.713 |
moment | +0.633 |
ac | +0.567 |
inn | +0.566 |
Neg logit contributions | |
rob | -1.193 |
rides | -1.090 |
opl | -1.067 |
ons | -1.027 |
pill | -0.993 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
kin | +0.009 |
upon | +0.008 |
moment | +0.008 |
isel | +0.008 |
rated | +0.007 |
Neg logit contributions | |
rob | -0.010 |
opl | -0.009 |
rides | -0.009 |
ons | -0.009 |
pill | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
rides | +0.043 |
rob | +0.041 |
ons | +0.040 |
kisses | +0.038 |
cand | +0.038 |
Neg logit contributions | |
kin | -0.044 |
isel | -0.041 |
rated | -0.037 |
loser | -0.037 |
upon | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
kin | +0.037 |
isel | +0.032 |
upon | +0.032 |
rated | +0.031 |
moment | +0.031 |
Neg logit contributions | |
rob | -0.032 |
rides | -0.032 |
ons | -0.031 |
opl | -0.029 |
cand | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
rob | +0.216 |
rides | +0.203 |
opl | +0.202 |
ons | +0.199 |
cand | +0.178 |
Neg logit contributions | |
kin | -0.203 |
upon | -0.178 |
moment | -0.164 |
isel | -0.164 |
cca | -0.159 |
Token | it |
Token ID | 340 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
kin | +0.171 |
isel | +0.137 |
loser | +0.136 |
rated | +0.134 |
iding | +0.130 |
Neg logit contributions | |
rides | -0.143 |
ons | -0.132 |
hugs | -0.125 |
kisses | -0.123 |
bars | -0.121 |
Token | up |
Token ID | 510 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
kin | +0.336 |
isel | +0.293 |
upon | +0.287 |
rated | +0.273 |
moment | +0.272 |
Neg logit contributions | |
rides | -0.371 |
rob | -0.369 |
ons | -0.359 |
opl | -0.335 |
cand | -0.324 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
kin | +0.110 |
isel | +0.099 |
loser | +0.093 |
upon | +0.093 |
rated | +0.092 |
Neg logit contributions | |
rides | -0.096 |
rob | -0.092 |
ons | -0.092 |
opl | -0.082 |
cand | -0.082 |
Token | The |
Token ID | 383 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
kin | +0.021 |
upon | +0.018 |
isel | +0.018 |
moment | +0.017 |
rated | +0.017 |
Neg logit contributions | |
rob | -0.021 |
rides | -0.020 |
ons | -0.020 |
opl | -0.018 |
cand | -0.018 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
rob | +0.091 |
rides | +0.090 |
ons | +0.087 |
opl | +0.080 |
cand | +0.077 |
Neg logit contributions | |
kin | -0.118 |
isel | -0.106 |
upon | -0.105 |
rated | -0.101 |
moment | -0.100 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ons | +0.215 |
rob | +0.207 |
rides | +0.202 |
cand | +0.197 |
cookies | +0.188 |
Neg logit contributions | |
isel | -0.031 |
rated | -0.022 |
particular | -0.016 |
upon | -0.016 |
halfway | -0.014 |
Token | had |
Token ID | 550 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
kin | +0.846 |
upon | +0.709 |
moment | +0.662 |
rated | +0.643 |
isel | +0.638 |
Neg logit contributions | |
rob | -1.107 |
rides | -1.037 |
opl | -1.024 |
ons | -0.989 |
course | -0.908 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
upon | +0.003 |
kin | +0.003 |
disaster | +0.003 |
moment | +0.003 |
time | +0.002 |
Neg logit contributions | |
rob | -0.005 |
opl | -0.005 |
ons | -0.005 |
grand | -0.004 |
rides | -0.004 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
kin | +0.023 |
upon | +0.020 |
isel | +0.019 |
moment | +0.019 |
loser | +0.018 |
Neg logit contributions | |
rob | -0.027 |
rides | -0.026 |
ons | -0.026 |
opl | -0.024 |
cream | -0.023 |
Token | inside |
Token ID | 2641 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
rob | +0.468 |
rides | +0.442 |
ons | +0.425 |
opl | +0.419 |
pill | +0.397 |
Neg logit contributions | |
kin | -0.366 |
upon | -0.291 |
moment | -0.265 |
inn | -0.260 |
loser | -0.258 |
Token | ! |
Token ID | 0 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
kin | +0.161 |
isel | +0.141 |
upon | +0.138 |
rated | +0.133 |
moment | +0.132 |
Neg logit contributions | |
rob | -0.178 |
rides | -0.177 |
ons | -0.173 |
opl | -0.161 |
cand | -0.154 |
Token | it |
Token ID | 340 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
rides | +0.100 |
ons | +0.099 |
rob | +0.098 |
course | +0.089 |
cand | +0.088 |
Neg logit contributions | |
kin | -0.089 |
isel | -0.082 |
rated | -0.080 |
upon | -0.077 |
loser | -0.077 |
Token | up |
Token ID | 510 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
kin | +0.346 |
isel | +0.309 |
upon | +0.297 |
rated | +0.286 |
loser | +0.284 |
Neg logit contributions | |
rides | -0.371 |
rob | -0.362 |
ons | -0.358 |
opl | -0.326 |
cand | -0.321 |
Token | in |
Token ID | 287 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
kin | +0.105 |
isel | +0.100 |
rated | +0.092 |
upon | +0.091 |
loser | +0.091 |
Neg logit contributions | |
rides | -0.102 |
ons | -0.096 |
rob | -0.096 |
cand | -0.087 |
course | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
kin | +0.184 |
isel | +0.162 |
upon | +0.160 |
rated | +0.156 |
moment | +0.151 |
Neg logit contributions | |
rides | -0.181 |
rob | -0.181 |
ons | -0.175 |
opl | -0.163 |
cand | -0.158 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
kin | +0.038 |
upon | +0.033 |
moment | +0.033 |
isel | +0.030 |
particular | +0.030 |
Neg logit contributions | |
rob | -0.039 |
rides | -0.036 |
ons | -0.034 |
opl | -0.033 |
cream | -0.031 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ons | +0.203 |
rob | +0.202 |
rides | +0.201 |
cand | +0.192 |
course | +0.189 |
Neg logit contributions | |
isel | -0.028 |
upon | -0.020 |
rated | -0.020 |
kin | -0.014 |
moment | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
kin | +0.813 |
upon | +0.673 |
moment | +0.621 |
isel | +0.612 |
inn | +0.600 |
Neg logit contributions | |
rob | -1.100 |
rides | -1.054 |
ons | -1.033 |
opl | -1.001 |
kisses | -0.933 |
Token | This |
Token ID | 770 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
kin | +0.034 |
upon | +0.030 |
isel | +0.030 |
moment | +0.028 |
rated | +0.028 |
Neg logit contributions | |
rob | -0.041 |
rides | -0.040 |
ons | -0.039 |
opl | -0.037 |
cand | -0.035 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
rob | +0.446 |
rides | +0.439 |
ons | +0.430 |
opl | +0.414 |
cand | +0.399 |
Neg logit contributions | |
kin | -0.149 |
upon | -0.109 |
isel | -0.107 |
moment | -0.099 |
rated | -0.096 |
Token | was |
Token ID | 373 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
rob | +0.492 |
rides | +0.474 |
opl | +0.457 |
ons | +0.449 |
kisses | +0.412 |
Neg logit contributions | |
kin | -0.327 |
upon | -0.249 |
moment | -0.245 |
rated | -0.233 |
isel | -0.231 |
Token | so |
Token ID | 523 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
kin | +0.106 |
upon | +0.094 |
isel | +0.093 |
moment | +0.090 |
rated | +0.090 |
Neg logit contributions | |
rob | -0.075 |
rides | -0.073 |
ons | -0.070 |
opl | -0.065 |
cand | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
kin | +0.232 |
upon | +0.201 |
moment | +0.191 |
isel | +0.190 |
rated | +0.181 |
Neg logit contributions | |
rob | -0.300 |
rides | -0.285 |
ons | -0.277 |
opl | -0.268 |
pill | -0.250 |
Token | he |
Token ID | 339 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
kin | +0.024 |
isel | +0.021 |
upon | +0.021 |
rated | +0.020 |
moment | +0.020 |
Neg logit contributions | |
rides | -0.023 |
rob | -0.023 |
ons | -0.022 |
opl | -0.020 |
cand | -0.020 |
Token | saw |
Token ID | 2497 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
rob | +0.184 |
rides | +0.175 |
ons | +0.171 |
opl | +0.166 |
cand | +0.155 |
Neg logit contributions | |
kin | -0.164 |
upon | -0.145 |
isel | -0.141 |
moment | -0.136 |
rated | -0.135 |
Token | a |
Token ID | 257 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
kin | +0.140 |
upon | +0.123 |
isel | +0.122 |
moment | +0.117 |
rated | +0.115 |
Neg logit contributions | |
rob | -0.140 |
rides | -0.136 |
ons | -0.132 |
opl | -0.125 |
cand | -0.118 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
kin | +0.048 |
isel | +0.043 |
upon | +0.042 |
rated | +0.041 |
inn | +0.039 |
Neg logit contributions | |
rides | -0.045 |
rob | -0.045 |
ons | -0.044 |
opl | -0.040 |
cand | -0.039 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ons | +0.190 |
rob | +0.189 |
rides | +0.188 |
course | +0.175 |
opl | +0.173 |
Neg logit contributions | |
isel | -0.040 |
rated | -0.030 |
kin | -0.028 |
upon | -0.027 |
loser | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
kin | +0.886 |
upon | +0.759 |
moment | +0.698 |
isel | +0.677 |
rated | +0.658 |
Neg logit contributions | |
rob | -1.046 |
rides | -0.991 |
ons | -0.951 |
opl | -0.932 |
pill | -0.870 |
Token | the |
Token ID | 262 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
kin | +0.043 |
isel | +0.040 |
rated | +0.039 |
upon | +0.039 |
ac | +0.037 |
Neg logit contributions | |
rides | -0.038 |
rob | -0.036 |
ons | -0.035 |
course | -0.032 |
opl | -0.032 |
Token | floor |
Token ID | 4314 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
kin | +0.045 |
moment | +0.038 |
upon | +0.035 |
footing | +0.035 |
loser | +0.034 |
Neg logit contributions | |
rob | -0.054 |
ons | -0.054 |
opl | -0.048 |
rides | -0.048 |
pill | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
rob | +0.109 |
rides | +0.106 |
ons | +0.103 |
opl | +0.097 |
cand | +0.093 |
Neg logit contributions | |
kin | -0.089 |
upon | -0.077 |
isel | -0.075 |
moment | -0.072 |
rated | -0.071 |
Token | The |
Token ID | 383 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
kin | +0.041 |
isel | +0.036 |
upon | +0.036 |
rated | +0.035 |
moment | +0.034 |
Neg logit contributions | |
rides | -0.038 |
rob | -0.038 |
ons | -0.036 |
opl | -0.034 |
cand | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
rides | +0.124 |
rob | +0.116 |
ons | +0.115 |
kisses | +0.109 |
cand | +0.109 |
Neg logit contributions | |
kin | -0.135 |
isel | -0.126 |
rated | -0.118 |
upon | -0.117 |
loser | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
kin | +0.031 |
isel | +0.028 |
upon | +0.027 |
moment | +0.026 |
rated | +0.026 |
Neg logit contributions | |
rob | -0.027 |
rides | -0.026 |
ons | -0.026 |
opl | -0.024 |
cand | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
rob | +0.023 |
rides | +0.023 |
ons | +0.022 |
opl | +0.021 |
kisses | +0.019 |
Neg logit contributions | |
kin | -0.026 |
isel | -0.023 |
upon | -0.023 |
rated | -0.022 |
moment | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
rob | +0.026 |
rides | +0.025 |
ons | +0.024 |
opl | +0.023 |
cand | +0.022 |
Neg logit contributions | |
kin | -0.027 |
isel | -0.024 |
upon | -0.023 |
rated | -0.022 |
moment | -0.022 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
rides | +0.135 |
rob | +0.133 |
ons | +0.129 |
opl | +0.119 |
cand | +0.118 |
Neg logit contributions | |
kin | -0.138 |
isel | -0.126 |
upon | -0.121 |
rated | -0.119 |
moment | -0.115 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ons | +0.207 |
rob | +0.203 |
rides | +0.203 |
cand | +0.192 |
kisses | +0.188 |
Neg logit contributions | |
isel | -0.026 |
rated | -0.020 |
upon | -0.020 |
kin | -0.020 |
inn | -0.013 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
kin | +0.843 |
upon | +0.669 |
moment | +0.640 |
isel | +0.604 |
rated | +0.603 |
Neg logit contributions | |
rob | -1.150 |
opl | -1.069 |
rides | -1.055 |
ons | -1.007 |
pill | -0.941 |
Token | nice |
Token ID | 3621 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
rides | +0.039 |
ons | +0.035 |
rob | +0.034 |
cand | +0.032 |
kisses | +0.032 |
Neg logit contributions | |
kin | -0.066 |
isel | -0.060 |
loser | -0.058 |
moment | -0.056 |
upon | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-04 |
Pos logit contributions | |
rob | +0.131 |
rides | +0.125 |
ons | +0.122 |
opl | +0.119 |
grand | +0.108 |
Neg logit contributions | |
kin | -0.103 |
upon | -0.088 |
moment | -0.084 |
isel | -0.083 |
rated | -0.080 |
Token | tidy |
Token ID | 43044 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
rob | +0.000 |
rides | +0.000 |
ons | +0.000 |
opl | +0.000 |
cand | +0.000 |
Neg logit contributions | |
kin | -0.000 |
upon | -0.000 |
isel | -0.000 |
moment | -0.000 |
rated | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
rides | +0.141 |
rob | +0.140 |
ons | +0.135 |
opl | +0.125 |
cand | +0.123 |
Neg logit contributions | |
kin | -0.131 |
isel | -0.119 |
upon | -0.115 |
rated | -0.109 |
moment | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
kin | +0.260 |
upon | +0.223 |
moment | +0.200 |
isel | +0.195 |
rated | +0.191 |
Neg logit contributions | |
rob | -0.375 |
rides | -0.348 |
ons | -0.335 |
opl | -0.327 |
pill | -0.305 |
Token | They |
Token ID | 1119 |
Feature activation | +9.04e-03 |
Pos logit contributions | |
kin | +0.051 |
isel | +0.044 |
upon | +0.044 |
rated | +0.043 |
moment | +0.042 |
Neg logit contributions | |
rob | -0.046 |
rides | -0.046 |
ons | -0.044 |
opl | -0.041 |
cand | -0.039 |
Token | use |
Token ID | 779 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
rob | +0.018 |
ons | +0.017 |
rides | +0.016 |
opl | +0.016 |
cand | +0.015 |
Neg logit contributions | |
kin | -0.015 |
upon | -0.014 |
isel | -0.013 |
rated | -0.013 |
moment | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
kin | +0.181 |
isel | +0.156 |
upon | +0.156 |
moment | +0.148 |
rated | +0.148 |
Neg logit contributions | |
rob | -0.208 |
rides | -0.205 |
ons | -0.199 |
opl | -0.187 |
cand | -0.179 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
kin | +0.049 |
isel | +0.045 |
rated | +0.043 |
upon | +0.043 |
inn | +0.042 |
Neg logit contributions | |
rides | -0.047 |
rob | -0.046 |
ons | -0.045 |
cand | -0.041 |
opl | -0.041 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
rob | +0.201 |
rides | +0.199 |
ons | +0.198 |
opl | +0.186 |
cand | +0.186 |
Neg logit contributions | |
kin | -0.024 |
isel | -0.017 |
upon | -0.014 |
rated | -0.012 |
moment | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
kin | +0.870 |
upon | +0.738 |
moment | +0.672 |
ac | +0.624 |
rated | +0.624 |
Neg logit contributions | |
rob | -1.106 |
rides | -1.015 |
opl | -1.001 |
ons | -0.965 |
pill | -0.903 |
Token | keep |
Token ID | 1394 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
rob | +0.114 |
rides | +0.110 |
ons | +0.108 |
opl | +0.101 |
pill | +0.095 |
Neg logit contributions | |
kin | -0.125 |
isel | -0.107 |
upon | -0.106 |
moment | -0.103 |
rated | -0.101 |
Token | their |
Token ID | 511 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
kin | +0.115 |
upon | +0.097 |
isel | +0.096 |
moment | +0.094 |
rated | +0.091 |
Neg logit contributions | |
rob | -0.133 |
rides | -0.129 |
ons | -0.123 |
opl | -0.120 |
pill | -0.111 |
Token | hands |
Token ID | 2832 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
kin | +0.106 |
upon | +0.093 |
isel | +0.091 |
moment | +0.088 |
rated | +0.087 |
Neg logit contributions | |
rob | -0.102 |
rides | -0.098 |
ons | -0.096 |
opl | -0.090 |
cand | -0.083 |
Token | clean |
Token ID | 3424 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
kin | +0.134 |
upon | +0.110 |
moment | +0.101 |
rated | +0.095 |
ac | +0.093 |
Neg logit contributions | |
rob | -0.185 |
rides | -0.170 |
opl | -0.164 |
ons | -0.162 |
pill | -0.159 |
Token | You |
Token ID | 921 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
kin | +0.038 |
isel | +0.033 |
upon | +0.033 |
rated | +0.032 |
moment | +0.032 |
Neg logit contributions | |
rob | -0.043 |
rides | -0.043 |
ons | -0.042 |
opl | -0.039 |
cand | -0.038 |
Token | need |
Token ID | 761 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
rob | +0.051 |
rides | +0.047 |
opl | +0.046 |
ons | +0.046 |
cand | +0.042 |
Neg logit contributions | |
kin | -0.031 |
upon | -0.026 |
isel | -0.025 |
don | -0.023 |
loser | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
kin | +0.107 |
upon | +0.100 |
moment | +0.093 |
isel | +0.092 |
disaster | +0.084 |
Neg logit contributions | |
rob | -0.144 |
opl | -0.130 |
rides | -0.126 |
ons | -0.122 |
odic | -0.113 |
Token | clean |
Token ID | 3424 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
kin | +0.030 |
isel | +0.027 |
upon | +0.027 |
rated | +0.026 |
moment | +0.025 |
Neg logit contributions | |
rides | -0.025 |
rob | -0.024 |
ons | -0.023 |
opl | -0.022 |
cand | -0.021 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
rob | +0.144 |
rides | +0.144 |
ons | +0.138 |
opl | +0.126 |
cand | +0.125 |
Neg logit contributions | |
kin | -0.178 |
isel | -0.165 |
upon | -0.156 |
rated | -0.155 |
inn | -0.150 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
rob | +0.152 |
rides | +0.151 |
ons | +0.150 |
cand | +0.138 |
opl | +0.138 |
Neg logit contributions | |
isel | -0.077 |
kin | -0.077 |
upon | -0.070 |
rated | -0.067 |
moment | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
kin | +0.839 |
upon | +0.706 |
moment | +0.648 |
rated | +0.625 |
ac | +0.619 |
Neg logit contributions | |
rob | -1.095 |
rides | -1.036 |
ons | -1.001 |
opl | -0.980 |
pill | -0.924 |
Token | And |
Token ID | 843 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
kin | +0.044 |
upon | +0.039 |
isel | +0.039 |
rated | +0.037 |
moment | +0.037 |
Neg logit contributions | |
rob | -0.042 |
rides | -0.042 |
ons | -0.041 |
opl | -0.038 |
cand | -0.036 |
Token | you |
Token ID | 345 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
rides | +0.165 |
rob | +0.161 |
ons | +0.156 |
opl | +0.139 |
cand | +0.137 |
Neg logit contributions | |
kin | -0.276 |
isel | -0.251 |
upon | -0.248 |
rated | -0.243 |
moment | -0.239 |
Token | need |
Token ID | 761 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
rob | +0.580 |
rides | +0.541 |
ons | +0.534 |
opl | +0.526 |
cand | +0.480 |
Neg logit contributions | |
kin | -0.376 |
upon | -0.322 |
isel | -0.309 |
moment | -0.294 |
rated | -0.291 |
Token | to |
Token ID | 284 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
kin | +0.103 |
upon | +0.096 |
moment | +0.089 |
isel | +0.087 |
disaster | +0.082 |
Neg logit contributions | |
rob | -0.138 |
opl | -0.126 |
rides | -0.122 |
ons | -0.118 |
pill | -0.110 |
Token | grateful |
Token ID | 14066 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
rob | +0.378 |
rides | +0.365 |
ons | +0.354 |
opl | +0.334 |
cand | +0.318 |
Neg logit contributions | |
kin | -0.323 |
upon | -0.278 |
isel | -0.275 |
moment | -0.260 |
rated | -0.259 |
Token | for |
Token ID | 329 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
rob | +0.311 |
rides | +0.295 |
ons | +0.288 |
opl | +0.276 |
cand | +0.256 |
Neg logit contributions | |
kin | -0.294 |
upon | -0.268 |
moment | -0.252 |
isel | -0.249 |
rated | -0.239 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
kin | +0.028 |
isel | +0.024 |
upon | +0.024 |
moment | +0.023 |
rated | +0.023 |
Neg logit contributions | |
rob | -0.030 |
rides | -0.030 |
ons | -0.029 |
opl | -0.027 |
cand | -0.026 |
Token | special |
Token ID | 2041 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
kin | +0.046 |
upon | +0.041 |
moment | +0.041 |
isel | +0.039 |
loser | +0.038 |
Neg logit contributions | |
rob | -0.037 |
rides | -0.034 |
ons | -0.034 |
opl | -0.032 |
cream | -0.029 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
rides | +0.123 |
ons | +0.117 |
rob | +0.117 |
cand | +0.109 |
kisses | +0.102 |
Neg logit contributions | |
kin | -0.216 |
isel | -0.207 |
upon | -0.197 |
rated | -0.197 |
inn | -0.189 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
rob | +0.197 |
rides | +0.196 |
ons | +0.194 |
opl | +0.184 |
cand | +0.181 |
Neg logit contributions | |
kin | -0.043 |
isel | -0.033 |
upon | -0.031 |
rated | -0.027 |
moment | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
kin | +0.870 |
upon | +0.738 |
moment | +0.705 |
rated | +0.609 |
footing | +0.596 |
Neg logit contributions | |
rob | -1.110 |
rides | -1.002 |
opl | -0.989 |
ons | -0.961 |
pill | -0.903 |
Token | |
Token ID | 220 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
kin | +0.046 |
upon | +0.042 |
isel | +0.041 |
moment | +0.040 |
inn | +0.039 |
Neg logit contributions | |
rob | -0.043 |
ons | -0.041 |
rides | -0.041 |
opl | -0.037 |
cand | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
rides | +0.157 |
rob | +0.157 |
ons | +0.154 |
opl | +0.142 |
kisses | +0.132 |
Neg logit contributions | |
kin | -0.187 |
isel | -0.166 |
rated | -0.161 |
upon | -0.160 |
moment | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +7.95e-03 |
Pos logit contributions | |
rob | +0.013 |
rides | +0.013 |
ons | +0.013 |
opl | +0.012 |
cand | +0.011 |
Neg logit contributions | |
kin | -0.013 |
upon | -0.012 |
isel | -0.011 |
moment | -0.011 |
rated | -0.011 |
Token | Tom |
Token ID | 13787 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
rob | +0.015 |
rides | +0.015 |
ons | +0.015 |
opl | +0.014 |
cand | +0.013 |
Neg logit contributions | |
kin | -0.014 |
upon | -0.012 |
isel | -0.012 |
moment | -0.011 |
inn | -0.011 |
Token | The |
Token ID | 383 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
kin | +0.025 |
isel | +0.022 |
upon | +0.022 |
rated | +0.021 |
moment | +0.021 |
Neg logit contributions | |
rob | -0.022 |
rides | -0.022 |
ons | -0.021 |
opl | -0.020 |
cand | -0.019 |
Token | bear |
Token ID | 6842 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
rob | +0.094 |
rides | +0.092 |
ons | +0.089 |
opl | +0.083 |
cand | +0.078 |
Neg logit contributions | |
kin | -0.112 |
upon | -0.100 |
isel | -0.098 |
moment | -0.096 |
rated | -0.094 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
rob | +0.125 |
opl | +0.120 |
rides | +0.114 |
ons | +0.110 |
odic | +0.103 |
Neg logit contributions | |
kin | -0.081 |
upon | -0.075 |
moment | -0.068 |
rated | -0.066 |
cca | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
upon | +0.074 |
kin | +0.073 |
isel | +0.061 |
moment | +0.060 |
disaster | +0.059 |
Neg logit contributions | |
rob | -0.156 |
opl | -0.151 |
rides | -0.150 |
ons | -0.139 |
grand | -0.139 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
kin | +0.027 |
isel | +0.024 |
upon | +0.023 |
rated | +0.022 |
moment | +0.022 |
Neg logit contributions | |
rob | -0.026 |
rides | -0.026 |
ons | -0.025 |
opl | -0.023 |
cand | -0.022 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
rob | +0.214 |
ons | +0.213 |
rides | +0.207 |
course | +0.196 |
cand | +0.195 |
Neg logit contributions | |
isel | -0.029 |
rated | -0.015 |
upon | -0.011 |
moment | -0.007 |
uzz | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
kin | +0.824 |
upon | +0.685 |
moment | +0.627 |
isel | +0.604 |
rated | +0.592 |
Neg logit contributions | |
rob | -1.103 |
rides | -1.067 |
ons | -1.020 |
opl | -1.003 |
pill | -0.941 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
kin | +0.029 |
upon | +0.025 |
isel | +0.025 |
moment | +0.024 |
rated | +0.024 |
Neg logit contributions | |
rob | -0.034 |
rides | -0.034 |
ons | -0.033 |
opl | -0.031 |
cand | -0.030 |
Token | ground |
Token ID | 2323 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
kin | +0.028 |
foot | +0.022 |
moment | +0.021 |
footing | +0.021 |
upon | +0.021 |
Neg logit contributions | |
rob | -0.039 |
ons | -0.038 |
pill | -0.035 |
opl | -0.035 |
rides | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
rob | +0.191 |
rides | +0.182 |
ons | +0.177 |
opl | +0.168 |
cand | +0.163 |
Neg logit contributions | |
kin | -0.136 |
upon | -0.119 |
moment | -0.110 |
isel | -0.109 |
rated | -0.106 |
Token | lifted |
Token ID | 13663 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
rob | +0.002 |
opl | +0.002 |
rides | +0.002 |
ons | +0.002 |
pill | +0.002 |
Neg logit contributions | |
kin | -0.002 |
upon | -0.002 |
isel | -0.001 |
moment | -0.001 |
rated | -0.001 |
Token | wanted |
Token ID | 2227 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
kin | +0.251 |
upon | +0.221 |
isel | +0.208 |
rated | +0.206 |
moment | +0.204 |
Neg logit contributions | |
rob | -0.322 |
rides | -0.308 |
ons | -0.298 |
opl | -0.291 |
cand | -0.276 |
Token | to |
Token ID | 284 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
kin | +0.142 |
upon | +0.134 |
moment | +0.131 |
isel | +0.123 |
particular | +0.119 |
Neg logit contributions | |
rob | -0.208 |
opl | -0.188 |
rides | -0.181 |
ons | -0.179 |
pill | -0.168 |
Token | get |
Token ID | 651 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
rob | +0.116 |
ons | +0.107 |
rides | +0.106 |
opl | +0.101 |
cand | +0.097 |
Neg logit contributions | |
kin | -0.094 |
isel | -0.083 |
upon | -0.081 |
moment | -0.078 |
particular | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
kin | +0.138 |
upon | +0.121 |
isel | +0.119 |
moment | +0.114 |
rated | +0.111 |
Neg logit contributions | |
rob | -0.184 |
rides | -0.178 |
ons | -0.174 |
opl | -0.167 |
cand | -0.158 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
kin | +0.062 |
upon | +0.054 |
isel | +0.054 |
moment | +0.052 |
rated | +0.051 |
Neg logit contributions | |
rob | -0.054 |
rides | -0.053 |
ons | -0.052 |
opl | -0.048 |
cand | -0.045 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
rob | +0.171 |
rides | +0.171 |
ons | +0.168 |
opl | +0.157 |
cand | +0.156 |
Neg logit contributions | |
kin | -0.061 |
isel | -0.055 |
upon | -0.052 |
rated | -0.047 |
moment | -0.045 |
Token | so |
Token ID | 523 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
kin | +0.875 |
upon | +0.757 |
moment | +0.715 |
isel | +0.695 |
rated | +0.691 |
Neg logit contributions | |
rob | -1.026 |
rides | -0.984 |
ons | -0.955 |
opl | -0.922 |
pill | -0.853 |
Token | she |
Token ID | 673 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
rides | +0.287 |
ons | +0.267 |
rob | +0.259 |
kisses | +0.239 |
cand | +0.236 |
Neg logit contributions | |
kin | -0.382 |
isel | -0.351 |
upon | -0.337 |
rated | -0.331 |
moment | -0.331 |
Token | jumped |
Token ID | 11687 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
rob | +0.174 |
rides | +0.172 |
ons | +0.167 |
opl | +0.155 |
cand | +0.150 |
Neg logit contributions | |
kin | -0.160 |
isel | -0.139 |
upon | -0.139 |
moment | -0.132 |
rated | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
kin | +0.052 |
isel | +0.050 |
rated | +0.046 |
loser | +0.044 |
upon | +0.044 |
Neg logit contributions | |
rides | -0.044 |
rob | -0.040 |
ons | -0.040 |
cand | -0.036 |
kisses | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
kin | +0.041 |
isel | +0.036 |
rated | +0.035 |
upon | +0.035 |
loser | +0.034 |
Neg logit contributions | |
rides | -0.029 |
rob | -0.028 |
ons | -0.028 |
opl | -0.025 |
kisses | -0.024 |
Token | ished |
Token ID | 1348 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
kin | +0.031 |
moment | +0.026 |
upon | +0.026 |
particular | +0.025 |
isel | +0.025 |
Neg logit contributions | |
rides | -0.032 |
rob | -0.031 |
ons | -0.031 |
kisses | -0.028 |
cand | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
kin | +0.099 |
isel | +0.088 |
rated | +0.088 |
loser | +0.084 |
particular | +0.084 |
Neg logit contributions | |
ons | -0.086 |
rides | -0.083 |
rob | -0.077 |
course | -0.075 |
cand | -0.074 |
Token | with |
Token ID | 351 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
kin | +0.324 |
isel | +0.281 |
upon | +0.278 |
rated | +0.264 |
moment | +0.263 |
Neg logit contributions | |
rides | -0.380 |
rob | -0.380 |
ons | -0.368 |
opl | -0.344 |
cand | -0.332 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
rides | +0.037 |
ons | +0.036 |
rob | +0.035 |
kisses | +0.032 |
opl | +0.032 |
Neg logit contributions | |
kin | -0.048 |
rated | -0.043 |
upon | -0.042 |
isel | -0.041 |
moment | -0.040 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
kin | +0.030 |
rated | +0.027 |
isel | +0.027 |
upon | +0.026 |
uzz | +0.025 |
Neg logit contributions | |
ons | -0.026 |
rides | -0.026 |
rob | -0.025 |
kisses | -0.024 |
cand | -0.024 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ons | +0.206 |
rob | +0.203 |
rides | +0.198 |
cand | +0.195 |
course | +0.188 |
Neg logit contributions | |
isel | -0.026 |
upon | -0.019 |
rated | -0.018 |
particular | -0.011 |
moment | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
kin | +0.814 |
upon | +0.681 |
isel | +0.637 |
moment | +0.626 |
inn | +0.617 |
Neg logit contributions | |
rob | -1.096 |
rides | -1.044 |
ons | -1.020 |
opl | -0.988 |
pill | -0.920 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
kin | +0.032 |
upon | +0.029 |
isel | +0.028 |
moment | +0.027 |
rated | +0.026 |
Neg logit contributions | |
rob | -0.048 |
rides | -0.046 |
ons | -0.046 |
opl | -0.043 |
cand | -0.041 |
Token | my |
Token ID | 1820 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
kin | +0.031 |
upon | +0.029 |
isel | +0.028 |
rated | +0.027 |
moment | +0.027 |
Neg logit contributions | |
rob | -0.018 |
rides | -0.018 |
ons | -0.017 |
opl | -0.016 |
cand | -0.015 |
Token | felt |
Token ID | 2936 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
rob | +0.344 |
opl | +0.321 |
rides | +0.319 |
ons | +0.308 |
grand | +0.280 |
Neg logit contributions | |
kin | -0.234 |
upon | -0.200 |
isel | -0.192 |
rated | -0.186 |
moment | -0.186 |
Token | bad |
Token ID | 2089 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
kin | +0.090 |
isel | +0.079 |
upon | +0.079 |
moment | +0.075 |
rated | +0.075 |
Neg logit contributions | |
rob | -0.095 |
rides | -0.094 |
ons | -0.091 |
opl | -0.085 |
cand | -0.082 |
Token | it |
Token ID | 340 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
kin | +0.061 |
isel | +0.057 |
upon | +0.053 |
rated | +0.053 |
moment | +0.051 |
Neg logit contributions | |
rob | -0.073 |
ons | -0.072 |
rides | -0.071 |
cand | -0.064 |
opl | -0.064 |
Token | off |
Token ID | 572 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
kin | +0.353 |
upon | +0.306 |
isel | +0.300 |
moment | +0.292 |
rated | +0.291 |
Neg logit contributions | |
rob | -0.376 |
rides | -0.368 |
ons | -0.357 |
opl | -0.337 |
cand | -0.318 |
Token | with |
Token ID | 351 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
rob | +0.047 |
rides | +0.046 |
ons | +0.044 |
opl | +0.042 |
cand | +0.039 |
Neg logit contributions | |
kin | -0.051 |
upon | -0.045 |
isel | -0.045 |
moment | -0.043 |
rated | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
rob | +0.044 |
rides | +0.040 |
ons | +0.037 |
opl | +0.037 |
cream | +0.034 |
Neg logit contributions | |
kin | -0.054 |
upon | -0.047 |
isel | -0.046 |
moment | -0.044 |
loser | -0.044 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
kin | +0.040 |
isel | +0.036 |
upon | +0.035 |
rated | +0.034 |
inn | +0.033 |
Neg logit contributions | |
rides | -0.033 |
rob | -0.033 |
ons | -0.032 |
opl | -0.029 |
cand | -0.029 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
rob | +0.162 |
ons | +0.160 |
rides | +0.159 |
cand | +0.150 |
opl | +0.146 |
Neg logit contributions | |
isel | -0.064 |
upon | -0.056 |
kin | -0.055 |
rated | -0.051 |
inn | -0.048 |
Token | ," |
Token ID | 553 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
kin | +0.848 |
upon | +0.703 |
moment | +0.655 |
loser | +0.640 |
rated | +0.629 |
Neg logit contributions | |
rob | -1.069 |
rides | -1.028 |
ons | -0.996 |
opl | -0.964 |
pill | -0.906 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
rob | +0.108 |
rides | +0.107 |
ons | +0.104 |
opl | +0.095 |
cand | +0.093 |
Neg logit contributions | |
kin | -0.110 |
isel | -0.097 |
upon | -0.096 |
rated | -0.093 |
moment | -0.091 |
Token | said |
Token ID | 531 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
upon | +0.387 |
kin | +0.367 |
moment | +0.349 |
rated | +0.335 |
inn | +0.333 |
Neg logit contributions | |
rob | -0.314 |
rides | -0.296 |
opl | -0.292 |
ons | -0.256 |
cand | -0.252 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
rides | +0.368 |
ons | +0.364 |
rob | +0.360 |
kisses | +0.325 |
cand | +0.323 |
Neg logit contributions | |
kin | -0.390 |
isel | -0.349 |
upon | -0.342 |
rated | -0.334 |
moment | -0.322 |
Token |
|
Token ID | 198 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
kin | +0.044 |
rated | +0.040 |
isel | +0.039 |
ac | +0.036 |
footing | +0.036 |
Neg logit contributions | |
rides | -0.029 |
ons | -0.028 |
rob | -0.028 |
kisses | -0.026 |
opl | -0.025 |
Token | covers |
Token ID | 8698 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
rob | +0.047 |
ons | +0.043 |
opl | +0.043 |
rides | +0.040 |
handed | +0.040 |
Neg logit contributions | |
kin | -0.044 |
upon | -0.041 |
isel | -0.038 |
don | -0.036 |
moment | -0.035 |
Token | them |
Token ID | 606 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ons | +0.267 |
rides | +0.253 |
kisses | +0.232 |
hugs | +0.228 |
rob | +0.227 |
Neg logit contributions | |
kin | -0.392 |
rated | -0.376 |
isel | -0.372 |
loser | -0.370 |
runner | -0.354 |
Token | with |
Token ID | 351 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
kin | +0.231 |
upon | +0.199 |
moment | +0.188 |
rated | +0.183 |
isel | +0.181 |
Neg logit contributions | |
rob | -0.323 |
ons | -0.291 |
rides | -0.291 |
opl | -0.284 |
pill | -0.265 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
rob | +0.045 |
rides | +0.045 |
ons | +0.044 |
opl | +0.040 |
cand | +0.039 |
Neg logit contributions | |
kin | -0.048 |
isel | -0.042 |
upon | -0.042 |
rated | -0.041 |
moment | -0.040 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
kin | +0.048 |
isel | +0.044 |
upon | +0.043 |
rated | +0.042 |
inn | +0.042 |
Neg logit contributions | |
rides | -0.040 |
rob | -0.039 |
ons | -0.039 |
cand | -0.035 |
kisses | -0.035 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ons | +0.203 |
rides | +0.202 |
rob | +0.201 |
cand | +0.190 |
opl | +0.187 |
Neg logit contributions | |
isel | -0.030 |
kin | -0.028 |
upon | -0.026 |
rated | -0.024 |
moment | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
kin | +0.756 |
upon | +0.583 |
moment | +0.534 |
isel | +0.483 |
rated | +0.478 |
Neg logit contributions | |
rob | -1.243 |
rides | -1.117 |
opl | -1.104 |
ons | -1.089 |
pill | -1.044 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
kin | +0.065 |
rated | +0.059 |
isel | +0.057 |
upon | +0.055 |
moment | +0.054 |
Neg logit contributions | |
rides | -0.045 |
rob | -0.043 |
ons | -0.041 |
kisses | -0.038 |
opl | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
rides | +0.026 |
ons | +0.025 |
rob | +0.025 |
opl | +0.022 |
kisses | +0.021 |
Neg logit contributions | |
kin | -0.041 |
rated | -0.037 |
isel | -0.037 |
loser | -0.035 |
footing | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
rides | +0.036 |
rob | +0.036 |
ons | +0.035 |
opl | +0.032 |
course | +0.031 |
Neg logit contributions | |
kin | -0.032 |
isel | -0.028 |
rated | -0.028 |
upon | -0.027 |
moment | -0.026 |
Token | Here |
Token ID | 4342 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
kin | +0.121 |
isel | +0.117 |
upon | +0.113 |
rated | +0.109 |
footing | +0.106 |
Neg logit contributions | |
rob | -0.142 |
rides | -0.132 |
ons | -0.125 |
cand | -0.120 |
course | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | -3.41e-03 |
Pos logit contributions | |
kin | +0.011 |
isel | +0.010 |
rated | +0.010 |
upon | +0.009 |
loser | +0.009 |
Neg logit contributions | |
rides | -0.009 |
rob | -0.009 |
ons | -0.009 |
opl | -0.008 |
course | -0.007 |
Token | Tom |
Token ID | 13787 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
kin | +0.006 |
isel | +0.005 |
upon | +0.005 |
rated | +0.005 |
moment | +0.005 |
Neg logit contributions | |
rob | -0.006 |
rides | -0.006 |
ons | -0.006 |
opl | -0.006 |
cand | -0.005 |
Token | used |
Token ID | 973 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
kin | +0.029 |
upon | +0.029 |
rated | +0.027 |
moment | +0.026 |
isel | +0.026 |
Neg logit contributions | |
rob | -0.027 |
rides | -0.024 |
ons | -0.024 |
opl | -0.023 |
cand | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
rides | +0.047 |
rob | +0.047 |
ons | +0.046 |
opl | +0.042 |
cand | +0.041 |
Neg logit contributions | |
kin | -0.052 |
isel | -0.045 |
upon | -0.045 |
rated | -0.045 |
moment | -0.043 |
Token | nap |
Token ID | 25422 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
kin | +0.048 |
isel | +0.042 |
upon | +0.042 |
rated | +0.040 |
moment | +0.040 |
Neg logit contributions | |
rob | -0.049 |
rides | -0.049 |
ons | -0.047 |
opl | -0.044 |
cand | -0.043 |
Token | kin |
Token ID | 5116 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
rob | +0.169 |
rides | +0.169 |
ons | +0.167 |
opl | +0.156 |
cand | +0.154 |
Neg logit contributions | |
kin | -0.058 |
isel | -0.050 |
upon | -0.047 |
rated | -0.045 |
moment | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
kin | +0.866 |
upon | +0.764 |
moment | +0.701 |
isel | +0.669 |
rated | +0.641 |
Neg logit contributions | |
rob | -1.082 |
rides | -0.989 |
opl | -0.958 |
ons | -0.938 |
pill | -0.871 |
Token | clean |
Token ID | 3424 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
rob | +0.103 |
rides | +0.100 |
ons | +0.098 |
opl | +0.091 |
cand | +0.087 |
Neg logit contributions | |
kin | -0.109 |
isel | -0.094 |
upon | -0.094 |
moment | -0.091 |
rated | -0.090 |
Token | up |
Token ID | 510 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
rides | +0.165 |
rob | +0.165 |
ons | +0.159 |
opl | +0.148 |
cand | +0.144 |
Neg logit contributions | |
kin | -0.149 |
isel | -0.131 |
upon | -0.129 |
rated | -0.124 |
moment | -0.122 |
Token | the |
Token ID | 262 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
kin | +0.096 |
upon | +0.083 |
isel | +0.083 |
moment | +0.079 |
rated | +0.078 |
Neg logit contributions | |
rob | -0.110 |
rides | -0.108 |
ons | -0.105 |
opl | -0.099 |
cand | -0.094 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
kin | +0.047 |
upon | +0.041 |
isel | +0.040 |
moment | +0.040 |
rated | +0.038 |
Neg logit contributions | |
rob | -0.043 |
rides | -0.041 |
ons | -0.040 |
opl | -0.038 |
cream | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
rides | +0.052 |
kisses | +0.048 |
hugs | +0.047 |
ons | +0.045 |
rob | +0.044 |
Neg logit contributions | |
kin | -0.094 |
isel | -0.087 |
loser | -0.083 |
rated | -0.080 |
footing | -0.078 |
Token | said |
Token ID | 531 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
rob | +0.003 |
rides | +0.003 |
ons | +0.003 |
opl | +0.003 |
cand | +0.002 |
Neg logit contributions | |
kin | -0.006 |
upon | -0.005 |
isel | -0.005 |
moment | -0.005 |
rated | -0.005 |
Token | : |
Token ID | 25 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ons | +0.329 |
rides | +0.324 |
rob | +0.306 |
cand | +0.293 |
kisses | +0.286 |
Neg logit contributions | |
kin | -0.449 |
rated | -0.413 |
isel | -0.409 |
loser | -0.394 |
upon | -0.390 |
Token | " |
Token ID | 366 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
rides | +0.022 |
ons | +0.022 |
rob | +0.021 |
opl | +0.019 |
kisses | +0.019 |
Neg logit contributions | |
kin | -0.026 |
rated | -0.024 |
isel | -0.024 |
ac | -0.022 |
footing | -0.022 |
Token | It |
Token ID | 1026 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
kin | +0.222 |
upon | +0.194 |
isel | +0.190 |
moment | +0.184 |
rated | +0.180 |
Neg logit contributions | |
rob | -0.288 |
rides | -0.286 |
ons | -0.276 |
opl | -0.263 |
cand | -0.253 |
Token | 's |
Token ID | 338 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
kin | +0.217 |
upon | +0.211 |
moment | +0.205 |
rated | +0.204 |
isel | +0.203 |
Neg logit contributions | |
rob | -0.124 |
rides | -0.111 |
opl | -0.105 |
ons | -0.103 |
cand | -0.091 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
rides | +0.496 |
ons | +0.462 |
rob | +0.435 |
opl | +0.434 |
kisses | +0.423 |
Neg logit contributions | |
kin | -0.711 |
isel | -0.664 |
loser | -0.621 |
rated | -0.610 |
ges | -0.599 |
Token | net |
Token ID | 2010 |
Feature activation | -7.19e-03 |
Pos logit contributions | |
kin | +0.020 |
isel | +0.018 |
upon | +0.018 |
rated | +0.018 |
inn | +0.017 |
Neg logit contributions | |
rides | -0.017 |
rob | -0.016 |
ons | -0.016 |
opl | -0.014 |
cand | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
kin | +0.011 |
upon | +0.009 |
moment | +0.009 |
don | +0.008 |
rated | +0.008 |
Neg logit contributions | |
rob | -0.017 |
rides | -0.015 |
ons | -0.015 |
opl | -0.014 |
cream | -0.014 |
Token | It |
Token ID | 632 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
kin | +0.025 |
upon | +0.021 |
isel | +0.021 |
rated | +0.021 |
moment | +0.020 |
Neg logit contributions | |
rides | -0.026 |
rob | -0.026 |
ons | -0.025 |
opl | -0.024 |
kisses | -0.023 |
Token | 's |
Token ID | 338 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
kin | +0.231 |
upon | +0.217 |
isel | +0.213 |
rated | +0.209 |
moment | +0.208 |
Neg logit contributions | |
rob | -0.173 |
rides | -0.158 |
ons | -0.153 |
opl | -0.152 |
cand | -0.135 |
Token | their |
Token ID | 511 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
rob | +0.009 |
opl | +0.008 |
ons | +0.008 |
rides | +0.008 |
odic | +0.007 |
Neg logit contributions | |
kin | -0.005 |
upon | -0.004 |
isel | -0.004 |
moment | -0.004 |
halfway | -0.004 |
Token | ball |
Token ID | 2613 |
Feature activation | -3.77e-03 |
Pos logit contributions | |
kin | +0.094 |
isel | +0.084 |
upon | +0.083 |
rated | +0.081 |
moment | +0.079 |
Neg logit contributions | |
rides | -0.083 |
rob | -0.081 |
ons | -0.079 |
opl | -0.073 |
cand | -0.070 |
Token | back |
Token ID | 736 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
kin | +0.005 |
upon | +0.004 |
moment | +0.004 |
loser | +0.004 |
inn | +0.004 |
Neg logit contributions | |
rob | -0.009 |
ons | -0.008 |
rides | -0.008 |
opl | -0.008 |
grand | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
rob | +0.114 |
rides | +0.112 |
ons | +0.109 |
opl | +0.103 |
cand | +0.098 |
Neg logit contributions | |
kin | -0.099 |
upon | -0.087 |
isel | -0.085 |
moment | -0.082 |
rated | -0.081 |
Token | They |
Token ID | 1119 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
kin | +0.032 |
isel | +0.028 |
rated | +0.028 |
upon | +0.028 |
moment | +0.027 |
Neg logit contributions | |
rides | -0.026 |
rob | -0.025 |
ons | -0.023 |
opl | -0.022 |
kisses | -0.022 |
Token | thanked |
Token ID | 26280 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
rob | +0.025 |
opl | +0.024 |
ons | +0.023 |
rides | +0.022 |
pill | +0.020 |
Neg logit contributions | |
kin | -0.024 |
upon | -0.021 |
isel | -0.020 |
don | -0.019 |
cca | -0.019 |
Token | Leo |
Token ID | 19632 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
rides | +0.614 |
rob | +0.601 |
ons | +0.579 |
kisses | +0.546 |
cand | +0.545 |
Neg logit contributions | |
kin | -0.472 |
isel | -0.424 |
rated | -0.418 |
upon | -0.405 |
moment | -0.376 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
kin | +0.082 |
upon | +0.075 |
moment | +0.069 |
isel | +0.065 |
rated | +0.065 |
Neg logit contributions | |
rob | -0.115 |
rides | -0.108 |
ons | -0.108 |
opl | -0.104 |
cream | -0.095 |
Token | They |
Token ID | 1119 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
kin | +0.029 |
upon | +0.025 |
isel | +0.025 |
moment | +0.024 |
rated | +0.024 |
Neg logit contributions | |
rob | -0.031 |
rides | -0.030 |
ons | -0.030 |
opl | -0.028 |
cand | -0.026 |
Token | said |
Token ID | 531 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
rob | +0.023 |
opl | +0.022 |
ons | +0.022 |
rides | +0.020 |
pill | +0.019 |
Neg logit contributions | |
kin | -0.024 |
upon | -0.020 |
isel | -0.018 |
don | -0.018 |
cca | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-03 |
Pos logit contributions | |
rob | +0.420 |
rides | +0.412 |
ons | +0.400 |
opl | +0.377 |
cand | +0.357 |
Neg logit contributions | |
kin | -0.387 |
upon | -0.335 |
isel | -0.335 |
moment | -0.319 |
rated | -0.315 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
rob | +0.148 |
ons | +0.130 |
pill | +0.126 |
opl | +0.124 |
rides | +0.123 |
Neg logit contributions | |
kin | -0.112 |
upon | -0.102 |
loser | -0.098 |
isel | -0.097 |
moment | -0.097 |
Token | Sam |
Token ID | 3409 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
kin | +0.056 |
upon | +0.056 |
moment | +0.052 |
isel | +0.050 |
particular | +0.050 |
Neg logit contributions | |
rob | -0.076 |
ons | -0.071 |
rides | -0.070 |
opl | -0.069 |
cand | -0.064 |
Token | nodded |
Token ID | 14464 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
kin | +0.144 |
upon | +0.127 |
moment | +0.122 |
rated | +0.116 |
cca | +0.114 |
Neg logit contributions | |
rob | -0.210 |
rides | -0.202 |
ons | -0.202 |
opl | -0.200 |
grand | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
isel | +0.173 |
kin | +0.165 |
footing | +0.159 |
rated | +0.159 |
loser | +0.155 |
Neg logit contributions | |
hugs | -0.069 |
rides | -0.069 |
kisses | -0.068 |
ons | -0.062 |
cand | -0.060 |
Token | He |
Token ID | 679 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
kin | +0.024 |
isel | +0.021 |
upon | +0.021 |
rated | +0.020 |
moment | +0.020 |
Neg logit contributions | |
rob | -0.020 |
rides | -0.020 |
ons | -0.019 |
opl | -0.018 |
cand | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
rob | +0.051 |
rides | +0.049 |
ons | +0.049 |
opl | +0.048 |
cand | +0.041 |
Neg logit contributions | |
kin | -0.070 |
upon | -0.063 |
isel | -0.061 |
moment | -0.060 |
rated | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
rides | +0.373 |
ons | +0.364 |
rob | +0.362 |
cand | +0.330 |
kisses | +0.325 |
Neg logit contributions | |
kin | -0.412 |
isel | -0.368 |
rated | -0.367 |
upon | -0.362 |
moment | -0.344 |
Token | " |
Token ID | 366 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
rob | +0.014 |
rides | +0.014 |
ons | +0.013 |
opl | +0.013 |
cand | +0.012 |
Neg logit contributions | |
kin | -0.008 |
isel | -0.007 |
upon | -0.007 |
rated | -0.006 |
moment | -0.006 |
Token | Yes |
Token ID | 5297 |
Feature activation | -8.96e-03 |
Pos logit contributions | |
kin | +0.177 |
moment | +0.156 |
loser | +0.144 |
particular | +0.140 |
upon | +0.140 |
Neg logit contributions | |
ons | -0.329 |
rides | -0.326 |
rob | -0.325 |
opl | -0.318 |
yard | -0.289 |
Token | , |
Token ID | 11 |
Feature activation | +6.84e-03 |
Pos logit contributions | |
kin | +0.019 |
isel | +0.018 |
rated | +0.018 |
cca | +0.017 |
udge | +0.017 |
Neg logit contributions | |
ons | -0.012 |
rides | -0.012 |
course | -0.012 |
hugs | -0.011 |
kisses | -0.011 |
Token | please |
Token ID | 3387 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
rides | +0.013 |
rob | +0.013 |
ons | +0.013 |
opl | +0.012 |
cand | +0.012 |
Neg logit contributions | |
kin | -0.012 |
isel | -0.010 |
upon | -0.010 |
rated | -0.010 |
moment | -0.009 |
Token | if |
Token ID | 611 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
kin | +0.274 |
upon | +0.232 |
isel | +0.224 |
moment | +0.213 |
rated | +0.209 |
Neg logit contributions | |
rob | -0.517 |
rides | -0.506 |
ons | -0.493 |
opl | -0.473 |
cand | -0.453 |
Token | he |
Token ID | 339 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
kin | +0.637 |
isel | +0.573 |
upon | +0.567 |
rated | +0.552 |
moment | +0.546 |
Neg logit contributions | |
rob | -0.426 |
rides | -0.422 |
ons | -0.406 |
opl | -0.366 |
cand | -0.353 |
Token | could |
Token ID | 714 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
rides | +0.197 |
ons | +0.191 |
rob | +0.185 |
cand | +0.172 |
cream | +0.171 |
Neg logit contributions | |
kin | -0.187 |
isel | -0.165 |
rated | -0.158 |
upon | -0.157 |
moment | -0.155 |
Token | have |
Token ID | 423 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
kin | +0.170 |
upon | +0.149 |
isel | +0.145 |
moment | +0.140 |
particular | +0.137 |
Neg logit contributions | |
rob | -0.189 |
rides | -0.174 |
ons | -0.171 |
opl | -0.162 |
cand | -0.152 |
Token | some |
Token ID | 617 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
rob | +0.056 |
opl | +0.054 |
rides | +0.052 |
ons | +0.051 |
yard | +0.049 |
Neg logit contributions | |
kin | -0.030 |
upon | -0.026 |
moment | -0.026 |
isel | -0.024 |
particular | -0.024 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
rob | +0.130 |
rides | +0.118 |
ons | +0.115 |
opl | +0.114 |
odic | +0.098 |
Neg logit contributions | |
kin | -0.170 |
upon | -0.153 |
moment | -0.146 |
particular | -0.144 |
isel | -0.144 |
Token | cream |
Token ID | 8566 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
rob | +0.232 |
rides | +0.222 |
ons | +0.210 |
cand | +0.176 |
opl | +0.169 |
Neg logit contributions | |
kin | -0.691 |
isel | -0.656 |
upon | -0.640 |
rated | -0.631 |
moment | -0.617 |
Token | , |
Token ID | 11 |
Feature activation | -9.08e-04 |
Pos logit contributions | |
rob | +0.495 |
rides | +0.488 |
ons | +0.476 |
opl | +0.451 |
kisses | +0.423 |
Neg logit contributions | |
kin | -0.407 |
upon | -0.346 |
isel | -0.337 |
moment | -0.328 |
rated | -0.320 |
Token | but |
Token ID | 475 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
kin | +0.001 |
upon | +0.001 |
isel | +0.001 |
moment | +0.001 |
particular | +0.001 |
Neg logit contributions | |
rob | -0.002 |
rides | -0.002 |
ons | -0.002 |
opl | -0.002 |
pill | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
kin | +0.424 |
isel | +0.411 |
rated | +0.393 |
loser | +0.374 |
udge | +0.370 |
Neg logit contributions | |
rides | -0.248 |
ons | -0.239 |
rob | -0.229 |
cand | -0.226 |
course | -0.210 |
Token | said |
Token ID | 531 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
rob | +0.143 |
rides | +0.142 |
ons | +0.137 |
opl | +0.123 |
cand | +0.118 |
Neg logit contributions | |
kin | -0.224 |
isel | -0.203 |
upon | -0.201 |
rated | -0.194 |
moment | -0.194 |
Token | Jim |
Token ID | 5395 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
rides | +0.359 |
ons | +0.346 |
rob | +0.315 |
kisses | +0.303 |
course | +0.301 |
Neg logit contributions | |
kin | -0.414 |
rated | -0.371 |
upon | -0.366 |
isel | -0.356 |
loser | -0.347 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
kin | +0.177 |
upon | +0.155 |
isel | +0.148 |
moment | +0.147 |
rated | +0.143 |
Neg logit contributions | |
rob | -0.217 |
rides | -0.206 |
ons | -0.199 |
opl | -0.193 |
course | -0.178 |
Token | " |
Token ID | 366 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
kin | +0.004 |
isel | +0.003 |
upon | +0.003 |
rated | +0.003 |
moment | +0.003 |
Neg logit contributions | |
rides | -0.003 |
rob | -0.003 |
ons | -0.003 |
opl | -0.003 |
cand | -0.003 |
Token | Now |
Token ID | 3844 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
kin | +0.262 |
isel | +0.243 |
upon | +0.229 |
rated | +0.224 |
inn | +0.212 |
Neg logit contributions | |
rob | -0.252 |
rides | -0.247 |
ons | -0.244 |
opl | -0.224 |
cream | -0.217 |
Token | it |
Token ID | 340 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
rob | +0.243 |
rides | +0.235 |
ons | +0.228 |
opl | +0.215 |
cand | +0.203 |
Neg logit contributions | |
kin | -0.251 |
upon | -0.221 |
isel | -0.220 |
moment | -0.210 |
rated | -0.210 |
Token | 's |
Token ID | 338 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
kin | +0.441 |
upon | +0.407 |
rated | +0.398 |
moment | +0.392 |
isel | +0.389 |
Neg logit contributions | |
rob | -0.267 |
rides | -0.243 |
ons | -0.224 |
opl | -0.222 |
cand | -0.198 |
Token | perfect |
Token ID | 2818 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
rides | +0.584 |
ons | +0.577 |
rob | +0.555 |
opl | +0.533 |
cand | +0.516 |
Neg logit contributions | |
kin | -0.596 |
isel | -0.538 |
upon | -0.514 |
loser | -0.510 |
moment | -0.499 |
Token | !" |
Token ID | 2474 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
kin | +0.031 |
isel | +0.028 |
upon | +0.027 |
rated | +0.026 |
inn | +0.025 |
Neg logit contributions | |
rides | -0.025 |
rob | -0.025 |
ons | -0.024 |
opl | -0.022 |
cand | -0.022 |
Token | |
Token ID | 220 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
rob | +0.117 |
rides | +0.111 |
ons | +0.107 |
opl | +0.104 |
cand | +0.100 |
Neg logit contributions | |
kin | -0.100 |
upon | -0.089 |
isel | -0.088 |
moment | -0.086 |
rated | -0.081 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
rides | +0.157 |
rob | +0.153 |
ons | +0.152 |
opl | +0.140 |
kisses | +0.132 |
Neg logit contributions | |
kin | -0.200 |
isel | -0.174 |
rated | -0.170 |
upon | -0.169 |
moment | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
rob | +0.030 |
rides | +0.029 |
ons | +0.027 |
cand | +0.026 |
opl | +0.026 |
Neg logit contributions | |
kin | -0.024 |
upon | -0.021 |
isel | -0.020 |
moment | -0.020 |
inn | -0.019 |
Token | sweep |
Token ID | 16085 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
rob | +0.125 |
rides | +0.122 |
ons | +0.119 |
opl | +0.111 |
cand | +0.107 |
Neg logit contributions | |
kin | -0.114 |
isel | -0.099 |
upon | -0.098 |
moment | -0.094 |
rated | -0.094 |
Token | , |
Token ID | 11 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
rides | +0.037 |
rob | +0.037 |
ons | +0.036 |
opl | +0.033 |
cand | +0.032 |
Neg logit contributions | |
kin | -0.036 |
isel | -0.032 |
upon | -0.031 |
rated | -0.030 |
loser | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
kin | +0.007 |
inn | +0.006 |
isel | +0.006 |
rated | +0.006 |
loser | +0.006 |
Neg logit contributions | |
rides | -0.004 |
ons | -0.004 |
rob | -0.003 |
course | -0.003 |
kisses | -0.003 |
Token | spider |
Token ID | 19230 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
kin | +0.028 |
isel | +0.025 |
upon | +0.024 |
rated | +0.024 |
inn | +0.023 |
Neg logit contributions | |
rides | -0.028 |
rob | -0.028 |
ons | -0.027 |
opl | -0.025 |
cand | -0.025 |
Token | sc |
Token ID | 629 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
kin | +0.300 |
upon | +0.259 |
isel | +0.252 |
moment | +0.247 |
rated | +0.242 |
Neg logit contributions | |
rob | -0.343 |
rides | -0.329 |
ons | -0.317 |
opl | -0.307 |
cand | -0.295 |
Token | ur |
Token ID | 333 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
rob | +0.605 |
rides | +0.562 |
ons | +0.544 |
opl | +0.507 |
cand | +0.506 |
Neg logit contributions | |
kin | -0.569 |
isel | -0.527 |
upon | -0.525 |
rated | -0.474 |
inn | -0.471 |
Token | ried |
Token ID | 2228 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
rob | +0.040 |
ons | +0.039 |
rides | +0.039 |
bars | +0.036 |
hugs | +0.034 |
Neg logit contributions | |
kin | -0.026 |
isel | -0.023 |
loser | -0.022 |
particular | -0.021 |
inn | -0.021 |
Token | out |
Token ID | 503 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
kin | +0.611 |
isel | +0.525 |
upon | +0.493 |
rated | +0.491 |
loser | +0.487 |
Neg logit contributions | |
rides | -0.598 |
rob | -0.571 |
ons | -0.565 |
opl | -0.517 |
course | -0.501 |
Token | ! |
Token ID | 0 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
kin | +0.229 |
isel | +0.201 |
upon | +0.197 |
rated | +0.193 |
moment | +0.190 |
Neg logit contributions | |
rides | -0.185 |
rob | -0.183 |
ons | -0.179 |
opl | -0.164 |
kisses | -0.156 |
Token | He |
Token ID | 679 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
rob | +0.082 |
rides | +0.081 |
ons | +0.079 |
opl | +0.074 |
cand | +0.071 |
Neg logit contributions | |
kin | -0.075 |
isel | -0.065 |
upon | -0.065 |
rated | -0.062 |
moment | -0.062 |
Token | jumped |
Token ID | 11687 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
rob | +0.053 |
rides | +0.053 |
ons | +0.051 |
opl | +0.047 |
cand | +0.046 |
Neg logit contributions | |
kin | -0.049 |
isel | -0.042 |
upon | -0.042 |
rated | -0.040 |
moment | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
rob | +0.374 |
ons | +0.346 |
rides | +0.344 |
opl | +0.340 |
cream | +0.328 |
Neg logit contributions | |
kin | -0.280 |
upon | -0.212 |
moment | -0.195 |
loser | -0.187 |
particular | -0.183 |
Token | a |
Token ID | 257 |
Feature activation | -9.02e-03 |
Pos logit contributions | |
rob | +0.003 |
rides | +0.003 |
ons | +0.003 |
opl | +0.003 |
handed | +0.002 |
Neg logit contributions | |
kin | -0.002 |
upon | -0.002 |
moment | -0.001 |
isel | -0.001 |
loser | -0.001 |
Token | princess |
Token ID | 21752 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
kin | +0.018 |
upon | +0.015 |
isel | +0.015 |
moment | +0.015 |
loser | +0.014 |
Neg logit contributions | |
rob | -0.016 |
rides | -0.015 |
ons | -0.015 |
opl | -0.014 |
cream | -0.013 |
Token | costume |
Token ID | 16569 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
kin | +0.028 |
upon | +0.024 |
isel | +0.024 |
moment | +0.023 |
rated | +0.023 |
Neg logit contributions | |
rob | -0.030 |
rides | -0.030 |
ons | -0.029 |
opl | -0.027 |
cand | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -5.70e-03 |
Pos logit contributions | |
rob | +0.380 |
ons | +0.351 |
rides | +0.350 |
opl | +0.346 |
cream | +0.336 |
Neg logit contributions | |
kin | -0.272 |
upon | -0.203 |
moment | -0.186 |
loser | -0.179 |
particular | -0.173 |
Token | a |
Token ID | 257 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
kin | +0.008 |
upon | +0.007 |
isel | +0.006 |
moment | +0.006 |
loser | +0.006 |
Neg logit contributions | |
rob | -0.013 |
opl | -0.012 |
ons | -0.012 |
rides | -0.012 |
handed | -0.011 |
Token | doctor |
Token ID | 6253 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
kin | +0.018 |
upon | +0.016 |
isel | +0.016 |
moment | +0.015 |
loser | +0.015 |
Neg logit contributions | |
rob | -0.017 |
rides | -0.017 |
ons | -0.017 |
opl | -0.016 |
cream | -0.014 |
Token | costume |
Token ID | 16569 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
rob | +0.103 |
ons | +0.099 |
rides | +0.098 |
opl | +0.095 |
course | +0.088 |
Neg logit contributions | |
kin | -0.072 |
upon | -0.059 |
moment | -0.057 |
loser | -0.054 |
ac | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
rob | +0.371 |
ons | +0.345 |
rides | +0.344 |
opl | +0.338 |
pill | +0.313 |
Neg logit contributions | |
kin | -0.267 |
upon | -0.218 |
moment | -0.197 |
loser | -0.191 |
isel | -0.187 |
Token | She |
Token ID | 1375 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
kin | +0.048 |
isel | +0.040 |
rated | +0.039 |
upon | +0.038 |
moment | +0.037 |
Neg logit contributions | |
rides | -0.059 |
rob | -0.057 |
ons | -0.054 |
opl | -0.053 |
cand | -0.052 |
Token | likes |
Token ID | 7832 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
rob | +0.222 |
ons | +0.212 |
rides | +0.206 |
opl | +0.202 |
cream | +0.192 |
Neg logit contributions | |
kin | -0.200 |
upon | -0.179 |
isel | -0.167 |
moment | -0.163 |
ac | -0.158 |
Token | little |
Token ID | 1310 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
kin | +0.067 |
isel | +0.064 |
rated | +0.061 |
ided | +0.058 |
upon | +0.058 |
Neg logit contributions | |
rides | -0.076 |
rob | -0.072 |
ons | -0.068 |
cand | -0.066 |
course | -0.065 |
Token | child |
Token ID | 1200 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
kin | +0.263 |
isel | +0.227 |
upon | +0.217 |
rated | +0.211 |
inn | +0.198 |
Neg logit contributions | |
rob | -0.423 |
rides | -0.421 |
ons | -0.404 |
opl | -0.381 |
cand | -0.380 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
kin | +0.208 |
upon | +0.189 |
moment | +0.173 |
particular | +0.170 |
inn | +0.166 |
Neg logit contributions | |
rob | -0.252 |
rides | -0.233 |
opl | -0.221 |
ons | -0.215 |
cand | -0.212 |
Token | She |
Token ID | 1375 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
kin | +0.045 |
upon | +0.040 |
isel | +0.040 |
moment | +0.038 |
rated | +0.037 |
Neg logit contributions | |
rob | -0.043 |
rides | -0.042 |
ons | -0.040 |
opl | -0.037 |
cand | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
rob | +0.241 |
rides | +0.229 |
ons | +0.227 |
opl | +0.220 |
cand | +0.209 |
Neg logit contributions | |
kin | -0.174 |
upon | -0.155 |
moment | -0.144 |
isel | -0.143 |
rated | -0.140 |
Token | very |
Token ID | 845 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
kin | +0.099 |
upon | +0.091 |
isel | +0.086 |
moment | +0.083 |
particular | +0.080 |
Neg logit contributions | |
rob | -0.114 |
rides | -0.108 |
ons | -0.107 |
opl | -0.101 |
cand | -0.096 |
Token | curious |
Token ID | 11040 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
rides | +0.200 |
rob | +0.199 |
ons | +0.192 |
opl | +0.180 |
cand | +0.173 |
Neg logit contributions | |
kin | -0.194 |
isel | -0.170 |
upon | -0.167 |
rated | -0.162 |
moment | -0.161 |
Token | and |
Token ID | 290 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
kin | +0.164 |
upon | +0.151 |
moment | +0.142 |
isel | +0.140 |
rated | +0.137 |
Neg logit contributions | |
rob | -0.232 |
rides | -0.212 |
ons | -0.210 |
opl | -0.202 |
cand | -0.188 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
kin | +0.004 |
upon | +0.004 |
isel | +0.004 |
moment | +0.003 |
rated | +0.003 |
Neg logit contributions | |
rob | -0.006 |
rides | -0.005 |
ons | -0.005 |
opl | -0.005 |
cand | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
rob | +0.087 |
opl | +0.076 |
ons | +0.076 |
rides | +0.075 |
handed | +0.071 |
Neg logit contributions | |
upon | -0.064 |
kin | -0.060 |
moment | -0.059 |
isel | -0.056 |
particular | -0.054 |
Token | collect |
Token ID | 2824 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
rob | +0.123 |
ons | +0.109 |
rides | +0.106 |
cand | +0.104 |
cream | +0.102 |
Neg logit contributions | |
kin | -0.087 |
isel | -0.083 |
particular | -0.081 |
upon | -0.080 |
moment | -0.079 |
Token | me |
Token ID | 502 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
rob | +0.098 |
rides | +0.090 |
ons | +0.087 |
opl | +0.084 |
cand | +0.080 |
Neg logit contributions | |
kin | -0.091 |
upon | -0.083 |
isel | -0.078 |
moment | -0.078 |
rated | -0.078 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
rob | +0.363 |
rides | +0.363 |
ons | +0.352 |
opl | +0.332 |
cand | +0.319 |
Neg logit contributions | |
kin | -0.282 |
isel | -0.243 |
upon | -0.238 |
rated | -0.226 |
moment | -0.225 |
Token | !" |
Token ID | 2474 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
kin | +0.029 |
upon | +0.026 |
isel | +0.025 |
moment | +0.025 |
rated | +0.025 |
Neg logit contributions | |
rob | -0.031 |
rides | -0.030 |
ons | -0.030 |
opl | -0.028 |
cand | -0.026 |
Token | |
Token ID | 220 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
rob | +0.124 |
opl | +0.117 |
ons | +0.113 |
rides | +0.113 |
odic | +0.110 |
Neg logit contributions | |
upon | -0.069 |
moment | -0.069 |
kin | -0.062 |
don | -0.057 |
L | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
rides | +0.162 |
rob | +0.160 |
ons | +0.156 |
opl | +0.146 |
kisses | +0.134 |
Neg logit contributions | |
kin | -0.202 |
isel | -0.177 |
rated | -0.172 |
upon | -0.171 |
moment | -0.169 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
rob | +0.030 |
rides | +0.029 |
ons | +0.028 |
opl | +0.028 |
cand | +0.027 |
Neg logit contributions | |
kin | -0.023 |
upon | -0.021 |
moment | -0.020 |
isel | -0.019 |
inn | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
rob | +0.033 |
ons | +0.031 |
rides | +0.031 |
opl | +0.030 |
kisses | +0.029 |
Neg logit contributions | |
kin | -0.022 |
upon | -0.019 |
moment | -0.018 |
cca | -0.018 |
isel | -0.018 |
Token | little |
Token ID | 1310 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
rides | +0.151 |
rob | +0.140 |
ons | +0.138 |
cand | +0.137 |
opl | +0.128 |
Neg logit contributions | |
kin | -0.127 |
isel | -0.116 |
inn | -0.109 |
rated | -0.106 |
udge | -0.106 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
kin | +0.232 |
isel | +0.192 |
upon | +0.181 |
rated | +0.180 |
inn | +0.175 |
Neg logit contributions | |
rides | -0.391 |
rob | -0.385 |
ons | -0.372 |
cand | -0.360 |
opl | -0.345 |
Token | smiled |
Token ID | 13541 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
kin | +0.307 |
upon | +0.276 |
moment | +0.259 |
isel | +0.256 |
rated | +0.249 |
Neg logit contributions | |
rob | -0.372 |
opl | -0.344 |
rides | -0.341 |
ons | -0.340 |
pill | -0.301 |
Token | and |
Token ID | 290 |
Feature activation | -1.94e-03 |
Pos logit contributions | |
rides | +0.049 |
kisses | +0.043 |
rob | +0.043 |
hugs | +0.042 |
ons | +0.040 |
Neg logit contributions | |
kin | -0.083 |
isel | -0.076 |
rated | -0.072 |
loser | -0.071 |
footing | -0.068 |
Token | hug |
Token ID | 16225 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
kin | +0.022 |
upon | +0.020 |
moment | +0.019 |
isel | +0.018 |
particular | +0.017 |
Neg logit contributions | |
rob | -0.022 |
rides | -0.021 |
opl | -0.021 |
ons | -0.020 |
handed | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
rob | +0.270 |
rides | +0.262 |
ons | +0.255 |
opl | +0.245 |
pill | +0.229 |
Neg logit contributions | |
kin | -0.202 |
upon | -0.170 |
moment | -0.163 |
isel | -0.158 |
loser | -0.154 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
opl | +0.006 |
rob | +0.006 |
ons | +0.005 |
handed | +0.005 |
rell | +0.005 |
Neg logit contributions | |
kin | -0.003 |
upon | -0.002 |
moment | -0.002 |
isel | -0.002 |
disaster | -0.002 |
Token | kiss |
Token ID | 9245 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
kin | +0.022 |
upon | +0.020 |
moment | +0.020 |
isel | +0.017 |
particular | +0.017 |
Neg logit contributions | |
rob | -0.023 |
rides | -0.022 |
opl | -0.021 |
ons | -0.021 |
handed | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
rob | +0.124 |
rides | +0.122 |
ons | +0.119 |
opl | +0.110 |
cand | +0.107 |
Neg logit contributions | |
kin | -0.116 |
isel | -0.105 |
upon | -0.102 |
rated | -0.099 |
moment | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
rob | +0.008 |
rides | +0.007 |
ons | +0.007 |
opl | +0.007 |
cand | +0.007 |
Neg logit contributions | |
kin | -0.005 |
upon | -0.004 |
isel | -0.004 |
moment | -0.004 |
rated | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
opl | +0.006 |
rob | +0.005 |
ons | +0.005 |
rell | +0.005 |
rides | +0.005 |
Neg logit contributions | |
kin | -0.005 |
upon | -0.004 |
moment | -0.004 |
isel | -0.004 |
cca | -0.004 |
Token | cookie |
Token ID | 19751 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
kin | +0.023 |
moment | +0.020 |
upon | +0.020 |
loser | +0.018 |
isel | +0.018 |
Neg logit contributions | |
rob | -0.023 |
rides | -0.021 |
ons | -0.021 |
opl | -0.020 |
cream | -0.019 |
Token | each |
Token ID | 1123 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
rob | +0.382 |
rides | +0.365 |
ons | +0.362 |
opl | +0.356 |
pill | +0.330 |
Neg logit contributions | |
kin | -0.264 |
moment | -0.191 |
upon | -0.191 |
loser | -0.182 |
inn | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
rob | +0.006 |
rides | +0.006 |
ons | +0.006 |
opl | +0.005 |
cand | +0.005 |
Neg logit contributions | |
kin | -0.005 |
isel | -0.005 |
upon | -0.005 |
rated | -0.004 |
moment | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
kin | +0.026 |
rated | +0.024 |
isel | +0.023 |
upon | +0.022 |
moment | +0.022 |
Neg logit contributions | |
rides | -0.016 |
rob | -0.015 |
ons | -0.015 |
opl | -0.014 |
kisses | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
kin | +0.005 |
isel | +0.005 |
rated | +0.005 |
cca | +0.005 |
upon | +0.005 |
Neg logit contributions | |
rides | -0.004 |
ons | -0.004 |
rob | -0.003 |
course | -0.003 |
kisses | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
rob | +0.027 |
rides | +0.026 |
ons | +0.026 |
opl | +0.024 |
cand | +0.024 |
Neg logit contributions | |
kin | -0.014 |
isel | -0.012 |
upon | -0.012 |
rated | -0.011 |
moment | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
kin | +0.228 |
upon | +0.207 |
moment | +0.193 |
ac | +0.174 |
loser | +0.174 |
Neg logit contributions | |
rob | -0.420 |
rides | -0.402 |
ons | -0.385 |
opl | -0.378 |
pill | -0.361 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
kin | +0.047 |
isel | +0.043 |
upon | +0.042 |
rated | +0.041 |
moment | +0.040 |
Neg logit contributions | |
rides | -0.036 |
rob | -0.036 |
ons | -0.034 |
opl | -0.031 |
kisses | -0.031 |
Token | 's |
Token ID | 338 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
kin | +0.258 |
moment | +0.245 |
upon | +0.244 |
rated | +0.240 |
disaster | +0.230 |
Neg logit contributions | |
rob | -0.120 |
opl | -0.100 |
rides | -0.098 |
ons | -0.098 |
cream | -0.089 |
Token | dance |
Token ID | 9280 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
rides | +0.517 |
ons | +0.455 |
kisses | +0.441 |
rob | +0.434 |
hugs | +0.422 |
Neg logit contributions | |
kin | -0.706 |
isel | -0.663 |
rated | -0.640 |
upon | -0.631 |
inn | -0.627 |
Token | together |
Token ID | 1978 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
kin | +0.075 |
isel | +0.074 |
rated | +0.068 |
upon | +0.066 |
inn | +0.064 |
Neg logit contributions | |
rides | -0.064 |
rob | -0.061 |
ons | -0.058 |
kisses | -0.054 |
opl | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
rides | +0.189 |
rob | +0.180 |
ons | +0.178 |
opl | +0.162 |
kisses | +0.160 |
Neg logit contributions | |
kin | -0.206 |
isel | -0.193 |
rated | -0.178 |
upon | -0.177 |
inn | -0.171 |
Token | And |
Token ID | 843 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
kin | +0.045 |
isel | +0.040 |
upon | +0.040 |
rated | +0.039 |
inn | +0.037 |
Neg logit contributions | |
rides | -0.038 |
rob | -0.037 |
ons | -0.034 |
kisses | -0.034 |
opl | -0.033 |
Token | then |
Token ID | 788 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
rides | +0.207 |
rob | +0.183 |
ons | +0.179 |
kisses | +0.171 |
cand | +0.169 |
Neg logit contributions | |
kin | -0.257 |
isel | -0.241 |
rated | -0.235 |
inn | -0.228 |
upon | -0.227 |
Token | we |
Token ID | 356 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
rides | +0.013 |
ons | +0.012 |
rob | +0.012 |
kisses | +0.011 |
hugs | +0.011 |
Neg logit contributions | |
kin | -0.020 |
isel | -0.018 |
inn | -0.018 |
upon | -0.017 |
rated | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
kin | +0.032 |
isel | +0.028 |
rated | +0.027 |
upon | +0.027 |
moment | +0.026 |
Neg logit contributions | |
rides | -0.032 |
rob | -0.031 |
ons | -0.031 |
opl | -0.028 |
cand | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
kin | +0.058 |
rated | +0.054 |
isel | +0.053 |
footing | +0.051 |
upon | +0.049 |
Neg logit contributions | |
rides | -0.031 |
rob | -0.028 |
ons | -0.027 |
kisses | -0.026 |
opl | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
rob | +0.045 |
rides | +0.043 |
ons | +0.042 |
opl | +0.040 |
cand | +0.038 |
Neg logit contributions | |
kin | -0.040 |
upon | -0.036 |
isel | -0.035 |
moment | -0.034 |
rated | -0.032 |
Token | After |
Token ID | 3260 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
rob | +0.047 |
rides | +0.047 |
ons | +0.046 |
opl | +0.043 |
cand | +0.041 |
Neg logit contributions | |
kin | -0.039 |
isel | -0.034 |
upon | -0.034 |
rated | -0.032 |
moment | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
kin | +0.111 |
upon | +0.092 |
isel | +0.090 |
moment | +0.089 |
loser | +0.084 |
Neg logit contributions | |
rob | -0.142 |
rides | -0.135 |
opl | -0.132 |
ons | -0.130 |
pill | -0.119 |
Token | while |
Token ID | 981 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
kin | +0.008 |
isel | +0.007 |
rated | +0.006 |
upon | +0.006 |
ac | +0.006 |
Neg logit contributions | |
rides | -0.011 |
rob | -0.011 |
ons | -0.011 |
cand | -0.011 |
course | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +6.33e-03 |
Pos logit contributions | |
kin | +0.417 |
rated | +0.407 |
isel | +0.388 |
upon | +0.376 |
cca | +0.368 |
Neg logit contributions | |
rides | -0.301 |
ons | -0.296 |
rob | -0.277 |
kisses | -0.252 |
course | -0.251 |
Token | they |
Token ID | 484 |
Feature activation | -3.93e-03 |
Pos logit contributions | |
rides | +0.008 |
cookies | +0.007 |
ons | +0.006 |
kisses | +0.006 |
bars | +0.006 |
Neg logit contributions | |
rated | -0.015 |
kin | -0.015 |
isel | -0.015 |
ac | -0.015 |
inn | -0.014 |
Token | finish |
Token ID | 5461 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
kin | +0.007 |
isel | +0.006 |
upon | +0.006 |
moment | +0.006 |
rated | +0.006 |
Neg logit contributions | |
rob | -0.007 |
rides | -0.007 |
ons | -0.007 |
opl | -0.007 |
cand | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
rides | +0.147 |
ons | +0.143 |
rob | +0.121 |
kisses | +0.120 |
cookies | +0.118 |
Neg logit contributions | |
rated | -0.209 |
kin | -0.202 |
isel | -0.200 |
loser | -0.188 |
cca | -0.179 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
kin | +0.036 |
upon | +0.032 |
moment | +0.032 |
isel | +0.031 |
loser | +0.030 |
Neg logit contributions | |
rob | -0.025 |
rides | -0.023 |
ons | -0.022 |
opl | -0.021 |
cream | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
kin | +0.039 |
isel | +0.034 |
rated | +0.033 |
upon | +0.032 |
moment | +0.032 |
Neg logit contributions | |
rides | -0.037 |
rob | -0.036 |
ons | -0.035 |
opl | -0.033 |
cand | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
rides | +0.019 |
rob | +0.019 |
ons | +0.018 |
opl | +0.016 |
kisses | +0.015 |
Neg logit contributions | |
kin | -0.028 |
isel | -0.025 |
rated | -0.025 |
loser | -0.024 |
upon | -0.023 |
Token | " |
Token ID | 1 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
rides | +0.023 |
rob | +0.023 |
ons | +0.022 |
opl | +0.020 |
course | +0.019 |
Neg logit contributions | |
kin | -0.023 |
isel | -0.021 |
upon | -0.020 |
rated | -0.020 |
moment | -0.019 |
Token | Look |
Token ID | 8567 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
kin | +0.121 |
isel | +0.112 |
upon | +0.105 |
rated | +0.102 |
footing | +0.100 |
Neg logit contributions | |
rob | -0.150 |
rides | -0.142 |
ons | -0.133 |
course | -0.127 |
cand | -0.126 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
kin | +0.133 |
rated | +0.119 |
isel | +0.119 |
moment | +0.115 |
loser | +0.113 |
Neg logit contributions | |
rides | -0.107 |
ons | -0.106 |
rob | -0.095 |
cand | -0.090 |
kisses | -0.089 |
Token | Sam |
Token ID | 3409 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
kin | +0.004 |
isel | +0.003 |
rated | +0.003 |
upon | +0.003 |
moment | +0.003 |
Neg logit contributions | |
rides | -0.005 |
rob | -0.004 |
ons | -0.004 |
cand | -0.004 |
opl | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -7.75e-04 |
Pos logit contributions | |
kin | +0.179 |
upon | +0.156 |
isel | +0.155 |
moment | +0.148 |
rated | +0.148 |
Neg logit contributions | |
rob | -0.190 |
rides | -0.188 |
ons | -0.182 |
opl | -0.171 |
cand | -0.163 |
Token | that |
Token ID | 326 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
kin | +0.001 |
isel | +0.001 |
upon | +0.001 |
moment | +0.001 |
rated | +0.001 |
Neg logit contributions | |
rob | -0.001 |
rides | -0.001 |
ons | -0.001 |
opl | -0.001 |
cand | -0.001 |
Token | star |
Token ID | 3491 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
rob | +0.474 |
rides | +0.454 |
ons | +0.443 |
opl | +0.424 |
cand | +0.402 |
Neg logit contributions | |
kin | -0.428 |
upon | -0.382 |
moment | -0.371 |
isel | -0.363 |
rated | -0.349 |
Token | is |
Token ID | 318 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
kin | +0.272 |
upon | +0.236 |
moment | +0.227 |
rated | +0.216 |
isel | +0.215 |
Neg logit contributions | |
rob | -0.293 |
rides | -0.278 |
opl | -0.257 |
ons | -0.257 |
cand | -0.246 |
Token | so |
Token ID | 523 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
rob | +0.077 |
rides | +0.073 |
ons | +0.071 |
opl | +0.065 |
cand | +0.062 |
Neg logit contributions | |
kin | -0.093 |
upon | -0.084 |
isel | -0.081 |
moment | -0.080 |
rated | -0.078 |
Token | clock |
Token ID | 8801 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
kin | +0.076 |
isel | +0.067 |
upon | +0.067 |
rated | +0.064 |
moment | +0.064 |
Neg logit contributions | |
rob | -0.071 |
rides | -0.071 |
ons | -0.068 |
opl | -0.064 |
cand | -0.061 |
Token | to |
Token ID | 284 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
rob | +0.023 |
rides | +0.021 |
ons | +0.020 |
opl | +0.020 |
cand | +0.019 |
Neg logit contributions | |
kin | -0.019 |
upon | -0.017 |
moment | -0.016 |
isel | -0.016 |
rated | -0.015 |
Token | Sus |
Token ID | 8932 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
rides | +0.094 |
rob | +0.093 |
ons | +0.091 |
opl | +0.084 |
cand | +0.081 |
Neg logit contributions | |
kin | -0.086 |
isel | -0.075 |
upon | -0.074 |
rated | -0.072 |
moment | -0.070 |
Token | ie |
Token ID | 494 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
kin | +0.319 |
isel | +0.279 |
upon | +0.268 |
moment | +0.259 |
loser | +0.259 |
Neg logit contributions | |
rob | -0.335 |
rides | -0.331 |
ons | -0.328 |
opl | -0.300 |
cand | -0.288 |
Token | 's |
Token ID | 338 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
kin | +0.119 |
upon | +0.108 |
moment | +0.102 |
isel | +0.101 |
rated | +0.097 |
Neg logit contributions | |
rob | -0.125 |
rides | -0.113 |
ons | -0.110 |
opl | -0.107 |
cand | -0.100 |
Token | bedroom |
Token ID | 14043 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
rob | +0.630 |
rides | +0.595 |
ons | +0.587 |
opl | +0.550 |
cand | +0.519 |
Neg logit contributions | |
kin | -0.547 |
upon | -0.480 |
isel | -0.469 |
moment | -0.455 |
rated | -0.438 |
Token | wall |
Token ID | 3355 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
kin | +0.131 |
upon | +0.114 |
isel | +0.110 |
moment | +0.107 |
rated | +0.105 |
Neg logit contributions | |
rob | -0.150 |
rides | -0.144 |
ons | -0.141 |
opl | -0.134 |
cand | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
kin | +0.038 |
upon | +0.033 |
moment | +0.031 |
isel | +0.031 |
rated | +0.030 |
Neg logit contributions | |
rob | -0.046 |
rides | -0.043 |
ons | -0.042 |
opl | -0.041 |
cand | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +3.80e-03 |
Pos logit contributions | |
kin | +0.064 |
isel | +0.054 |
rated | +0.053 |
loser | +0.052 |
upon | +0.051 |
Neg logit contributions | |
rides | -0.053 |
rob | -0.052 |
ons | -0.051 |
opl | -0.048 |
kisses | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +4.01e-03 |
Pos logit contributions | |
rides | +0.006 |
rob | +0.006 |
ons | +0.006 |
opl | +0.005 |
kisses | +0.005 |
Neg logit contributions | |
kin | -0.008 |
isel | -0.007 |
rated | -0.007 |
loser | -0.007 |
footing | -0.007 |
Token | Sus |
Token ID | 30746 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
rides | +0.007 |
rob | +0.007 |
ons | +0.007 |
opl | +0.006 |
cand | +0.006 |
Neg logit contributions | |
kin | -0.007 |
isel | -0.007 |
rated | -0.006 |
upon | -0.006 |
moment | -0.006 |
Token | cr |
Token ID | 1067 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
kin | +0.043 |
isel | +0.039 |
rated | +0.038 |
upon | +0.038 |
inn | +0.036 |
Neg logit contributions | |
rides | -0.039 |
rob | -0.039 |
ons | -0.038 |
cand | -0.035 |
opl | -0.034 |
Token | ay |
Token ID | 323 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
rob | +0.137 |
rides | +0.134 |
ons | +0.122 |
cand | +0.118 |
opl | +0.115 |
Neg logit contributions | |
kin | -0.112 |
isel | -0.097 |
upon | -0.094 |
inn | -0.091 |
rated | -0.087 |
Token | on |
Token ID | 261 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
kin | +0.029 |
upon | +0.026 |
isel | +0.026 |
moment | +0.025 |
rated | +0.025 |
Neg logit contributions | |
rob | -0.011 |
rides | -0.011 |
ons | -0.009 |
opl | -0.009 |
cand | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
rob | +0.436 |
rides | +0.418 |
ons | +0.398 |
opl | +0.380 |
cand | +0.363 |
Neg logit contributions | |
kin | -0.419 |
upon | -0.362 |
isel | -0.350 |
moment | -0.340 |
rated | -0.334 |
Token | He |
Token ID | 679 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
rob | +0.065 |
rides | +0.065 |
ons | +0.063 |
opl | +0.059 |
cand | +0.056 |
Neg logit contributions | |
kin | -0.067 |
isel | -0.058 |
upon | -0.058 |
rated | -0.056 |
moment | -0.056 |
Token | felt |
Token ID | 2936 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
rides | +0.032 |
ons | +0.032 |
rob | +0.031 |
cand | +0.028 |
kisses | +0.028 |
Neg logit contributions | |
kin | -0.034 |
isel | -0.030 |
upon | -0.029 |
loser | -0.029 |
rated | -0.029 |
Token | excited |
Token ID | 6568 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
kin | +0.109 |
isel | +0.095 |
upon | +0.095 |
rated | +0.095 |
moment | +0.092 |
Neg logit contributions | |
rides | -0.098 |
ons | -0.094 |
rob | -0.093 |
opl | -0.086 |
cand | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
kin | +0.135 |
upon | +0.125 |
moment | +0.118 |
isel | +0.116 |
rated | +0.114 |
Neg logit contributions | |
rob | -0.184 |
rides | -0.172 |
ons | -0.170 |
opl | -0.164 |
cand | -0.152 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
kin | +0.015 |
upon | +0.013 |
isel | +0.013 |
moment | +0.012 |
rated | +0.012 |
Neg logit contributions | |
rob | -0.019 |
rides | -0.018 |
ons | -0.017 |
opl | -0.017 |
cand | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
kin | +0.096 |
rated | +0.092 |
loser | +0.085 |
upon | +0.081 |
OO | +0.080 |
Neg logit contributions | |
ons | -0.075 |
rides | -0.072 |
hugs | -0.063 |
course | -0.062 |
rob | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
kin | +0.319 |
upon | +0.281 |
isel | +0.267 |
moment | +0.263 |
rated | +0.254 |
Neg logit contributions | |
rob | -0.424 |
rides | -0.400 |
ons | -0.392 |
opl | -0.375 |
cand | -0.354 |
Token | in |
Token ID | 287 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
kin | +0.057 |
upon | +0.049 |
isel | +0.044 |
moment | +0.044 |
inn | +0.040 |
Neg logit contributions | |
rob | -0.114 |
opl | -0.107 |
ons | -0.104 |
rides | -0.103 |
pill | -0.100 |
Token | it |
Token ID | 340 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
kin | +0.182 |
isel | +0.170 |
rated | +0.169 |
inn | +0.158 |
upon | +0.156 |
Neg logit contributions | |
rides | -0.169 |
ons | -0.160 |
rob | -0.151 |
course | -0.144 |
opl | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
kin | +0.284 |
upon | +0.244 |
moment | +0.226 |
rated | +0.211 |
isel | +0.210 |
Neg logit contributions | |
rob | -0.446 |
rides | -0.409 |
ons | -0.406 |
opl | -0.397 |
pill | -0.373 |
Token | But |
Token ID | 887 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
kin | +0.035 |
isel | +0.030 |
upon | +0.030 |
rated | +0.029 |
moment | +0.028 |
Neg logit contributions | |
rides | -0.032 |
rob | -0.031 |
ons | -0.030 |
opl | -0.028 |
cand | -0.026 |
Token | over |
Token ID | 625 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
kin | +0.292 |
isel | +0.276 |
rated | +0.264 |
udge | +0.256 |
inn | +0.249 |
Neg logit contributions | |
rides | -0.286 |
ons | -0.265 |
rob | -0.261 |
course | -0.257 |
cand | -0.250 |
Token | time |
Token ID | 640 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
kin | +0.113 |
isel | +0.101 |
rated | +0.100 |
inn | +0.096 |
upon | +0.093 |
Neg logit contributions | |
rides | -0.090 |
ons | -0.084 |
course | -0.080 |
rob | -0.080 |
cand | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -8.01e-04 |
Pos logit contributions | |
kin | +0.626 |
isel | +0.592 |
rated | +0.569 |
inn | +0.543 |
udge | +0.541 |
Neg logit contributions | |
rides | -0.474 |
ons | -0.445 |
rob | -0.414 |
cand | -0.378 |
kisses | -0.362 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
kin | +0.002 |
isel | +0.001 |
rated | +0.001 |
inn | +0.001 |
upon | +0.001 |
Neg logit contributions | |
rides | -0.001 |
ons | -0.001 |
rob | -0.001 |
cand | -0.001 |
course | -0.001 |
Token | bin |
Token ID | 9874 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
kin | +0.044 |
isel | +0.040 |
upon | +0.039 |
rated | +0.038 |
inn | +0.037 |
Neg logit contributions | |
rides | -0.028 |
rob | -0.027 |
ons | -0.026 |
cand | -0.024 |
opl | -0.024 |
Token | began |
Token ID | 2540 |
Feature activation | +8.29e-03 |
Pos logit contributions | |
rob | +0.202 |
rides | +0.198 |
ons | +0.192 |
opl | +0.182 |
cand | +0.174 |
Neg logit contributions | |
kin | -0.166 |
upon | -0.143 |
isel | -0.142 |
moment | -0.135 |
rated | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
rides | +0.013 |
rob | +0.012 |
ons | +0.012 |
opl | +0.011 |
cand | +0.011 |
Neg logit contributions | |
kin | -0.018 |
isel | -0.016 |
upon | -0.015 |
rated | -0.015 |
moment | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
kin | +0.005 |
upon | +0.005 |
isel | +0.005 |
moment | +0.005 |
rated | +0.005 |
Neg logit contributions | |
rob | -0.005 |
rides | -0.005 |
ons | -0.005 |
opl | -0.005 |
cand | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
rides | +0.326 |
ons | +0.320 |
rob | +0.298 |
cand | +0.286 |
kisses | +0.282 |
Neg logit contributions | |
kin | -0.435 |
isel | -0.397 |
rated | -0.395 |
upon | -0.372 |
loser | -0.370 |
Token | " |
Token ID | 366 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
kin | +0.004 |
isel | +0.003 |
rated | +0.003 |
loser | +0.003 |
ac | +0.003 |
Neg logit contributions | |
rides | -0.005 |
ons | -0.005 |
rob | -0.005 |
kisses | -0.004 |
opl | -0.004 |
Token | It |
Token ID | 1026 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
kin | +0.237 |
isel | +0.202 |
upon | +0.195 |
rated | +0.187 |
loser | +0.180 |
Neg logit contributions | |
rob | -0.300 |
rides | -0.294 |
ons | -0.285 |
opl | -0.267 |
course | -0.259 |
Token | 's |
Token ID | 338 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
kin | +0.247 |
upon | +0.238 |
moment | +0.232 |
rated | +0.231 |
isel | +0.228 |
Neg logit contributions | |
rob | -0.119 |
rides | -0.104 |
ons | -0.096 |
opl | -0.095 |
cand | -0.084 |
Token | time |
Token ID | 640 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
rides | +0.594 |
ons | +0.572 |
opl | +0.556 |
kisses | +0.545 |
rob | +0.545 |
Neg logit contributions | |
kin | -0.572 |
isel | -0.543 |
loser | -0.493 |
ges | -0.474 |
udge | -0.464 |
Token | for |
Token ID | 329 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
kin | +0.607 |
isel | +0.540 |
rated | +0.508 |
upon | +0.504 |
loser | +0.504 |
Neg logit contributions | |
rides | -0.461 |
ons | -0.444 |
rob | -0.440 |
opl | -0.396 |
kisses | -0.394 |
Token | bed |
Token ID | 3996 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
kin | +0.022 |
upon | +0.020 |
moment | +0.019 |
isel | +0.019 |
disaster | +0.019 |
Neg logit contributions | |
rob | -0.020 |
rides | -0.017 |
opl | -0.017 |
ons | -0.017 |
pill | -0.016 |
Token | now |
Token ID | 783 |
Feature activation | +5.74e-03 |
Pos logit contributions | |
rob | +0.277 |
rides | +0.268 |
ons | +0.264 |
opl | +0.250 |
cand | +0.236 |
Neg logit contributions | |
kin | -0.236 |
upon | -0.202 |
isel | -0.192 |
moment | -0.191 |
rated | -0.191 |
Token | ." |
Token ID | 526 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
rob | +0.011 |
rides | +0.010 |
ons | +0.010 |
opl | +0.009 |
cand | +0.009 |
Neg logit contributions | |
kin | -0.010 |
isel | -0.009 |
upon | -0.009 |
rated | -0.009 |
moment | -0.009 |
Token | As |
Token ID | 1081 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
rob | +0.037 |
rides | +0.037 |
ons | +0.035 |
opl | +0.033 |
cand | +0.032 |
Neg logit contributions | |
kin | -0.040 |
isel | -0.036 |
upon | -0.035 |
rated | -0.034 |
moment | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
rob | +0.042 |
opl | +0.037 |
rides | +0.036 |
ons | +0.036 |
odic | +0.034 |
Neg logit contributions | |
kin | -0.030 |
upon | -0.029 |
isel | -0.028 |
moment | -0.027 |
loser | -0.026 |
Token | keep |
Token ID | 1394 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
rob | +0.145 |
ons | +0.129 |
rides | +0.126 |
pill | +0.125 |
opl | +0.123 |
Neg logit contributions | |
kin | -0.100 |
isel | -0.087 |
upon | -0.086 |
moment | -0.085 |
don | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
kin | +0.090 |
upon | +0.082 |
moment | +0.077 |
halfway | +0.077 |
isel | +0.076 |
Neg logit contributions | |
rob | -0.128 |
opl | -0.112 |
rides | -0.110 |
pill | -0.108 |
grand | -0.107 |
Token | tw |
Token ID | 665 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
kin | +0.038 |
upon | +0.033 |
moment | +0.033 |
isel | +0.033 |
rated | +0.032 |
Neg logit contributions | |
rob | -0.032 |
rides | -0.031 |
ons | -0.030 |
opl | -0.029 |
cream | -0.026 |
Token | ig |
Token ID | 328 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
kin | +0.012 |
isel | +0.010 |
upon | +0.010 |
rated | +0.010 |
loser | +0.010 |
Neg logit contributions | |
rob | -0.017 |
rides | -0.017 |
ons | -0.017 |
opl | -0.016 |
cand | -0.015 |
Token | if |
Token ID | 611 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
kin | +0.266 |
upon | +0.225 |
moment | +0.218 |
rated | +0.210 |
isel | +0.206 |
Neg logit contributions | |
rob | -0.321 |
rides | -0.305 |
ons | -0.287 |
opl | -0.280 |
pill | -0.268 |
Token | you |
Token ID | 345 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
kin | +0.765 |
isel | +0.704 |
upon | +0.694 |
rated | +0.680 |
moment | +0.672 |
Neg logit contributions | |
rides | -0.321 |
rob | -0.315 |
ons | -0.303 |
opl | -0.257 |
cand | -0.244 |
Token | don |
Token ID | 836 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
rob | +0.569 |
rides | +0.560 |
ons | +0.547 |
opl | +0.519 |
cand | +0.500 |
Neg logit contributions | |
kin | -0.353 |
upon | -0.296 |
isel | -0.295 |
rated | -0.276 |
moment | -0.276 |
Token | 't |
Token ID | 470 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
kin | +0.566 |
upon | +0.474 |
inn | +0.472 |
isel | +0.471 |
loser | +0.462 |
Neg logit contributions | |
rob | -0.716 |
rides | -0.686 |
cand | -0.645 |
ons | -0.640 |
kisses | -0.626 |
Token | like |
Token ID | 588 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
rob | +0.097 |
rides | +0.093 |
ons | +0.092 |
opl | +0.087 |
cand | +0.083 |
Neg logit contributions | |
kin | -0.062 |
upon | -0.053 |
isel | -0.053 |
rated | -0.050 |
moment | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
kin | +0.220 |
isel | +0.184 |
upon | +0.179 |
rated | +0.175 |
moment | +0.167 |
Neg logit contributions | |
rides | -0.380 |
rob | -0.369 |
ons | -0.368 |
opl | -0.345 |
cand | -0.337 |
Token | were |
Token ID | 547 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
kin | +0.007 |
upon | +0.006 |
isel | +0.006 |
moment | +0.006 |
rated | +0.006 |
Neg logit contributions | |
rob | -0.009 |
rides | -0.009 |
ons | -0.008 |
opl | -0.008 |
pill | -0.008 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
rob | +0.074 |
rides | +0.069 |
ons | +0.068 |
opl | +0.067 |
pill | +0.063 |
Neg logit contributions | |
kin | -0.064 |
upon | -0.052 |
isel | -0.051 |
loser | -0.049 |
cca | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
kin | +0.030 |
upon | +0.026 |
isel | +0.025 |
moment | +0.024 |
rated | +0.024 |
Neg logit contributions | |
rob | -0.035 |
rides | -0.034 |
ons | -0.033 |
opl | -0.031 |
cand | -0.030 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.21e-03 |
Pos logit contributions | |
kin | +0.019 |
isel | +0.018 |
rated | +0.017 |
upon | +0.016 |
footing | +0.016 |
Neg logit contributions | |
rides | -0.012 |
rob | -0.012 |
kisses | -0.011 |
ons | -0.010 |
opl | -0.010 |
Token | L |
Token ID | 43 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
kin | +0.011 |
isel | +0.010 |
rated | +0.010 |
upon | +0.010 |
moment | +0.009 |
Neg logit contributions | |
rob | -0.011 |
rides | -0.011 |
ons | -0.011 |
opl | -0.010 |
cand | -0.009 |
Token | ila |
Token ID | 10102 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
kin | +0.128 |
isel | +0.110 |
rated | +0.106 |
upon | +0.101 |
moment | +0.100 |
Neg logit contributions | |
rides | -0.239 |
rob | -0.239 |
ons | -0.238 |
opl | -0.216 |
cand | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | +2.46e-03 |
Pos logit contributions | |
kin | +0.479 |
upon | +0.410 |
moment | +0.385 |
isel | +0.383 |
rated | +0.367 |
Neg logit contributions | |
rob | -0.652 |
rides | -0.617 |
ons | -0.611 |
opl | -0.603 |
cand | -0.563 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
rob | +0.005 |
rides | +0.005 |
ons | +0.005 |
opl | +0.005 |
cand | +0.005 |
Neg logit contributions | |
kin | -0.004 |
upon | -0.003 |
isel | -0.003 |
moment | -0.003 |
rated | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
kin | +0.288 |
upon | +0.252 |
isel | +0.250 |
moment | +0.239 |
rated | +0.238 |
Neg logit contributions | |
rob | -0.302 |
rides | -0.295 |
ons | -0.288 |
opl | -0.271 |
cand | -0.257 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
rob | +0.073 |
rides | +0.065 |
ons | +0.064 |
opl | +0.063 |
cream | +0.063 |
Neg logit contributions | |
kin | -0.066 |
upon | -0.065 |
ac | -0.055 |
inn | -0.054 |
isel | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
rides | +0.346 |
rob | +0.339 |
ons | +0.332 |
course | +0.302 |
cand | +0.289 |
Neg logit contributions | |
kin | -0.319 |
isel | -0.297 |
rated | -0.297 |
upon | -0.278 |
moment | -0.270 |
Token | loyal |
Token ID | 9112 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
kin | +0.023 |
upon | +0.020 |
isel | +0.020 |
moment | +0.019 |
rated | +0.019 |
Neg logit contributions | |
rob | -0.021 |
rides | -0.021 |
ons | -0.020 |
opl | -0.019 |
cand | -0.018 |
Token | dog |
Token ID | 3290 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
rides | +0.144 |
rob | +0.133 |
ons | +0.129 |
cand | +0.129 |
opl | +0.121 |
Neg logit contributions | |
kin | -0.144 |
isel | -0.131 |
rated | -0.128 |
upon | -0.125 |
inn | -0.121 |
Token | ." |
Token ID | 526 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
rob | +0.055 |
ons | +0.052 |
rides | +0.052 |
opl | +0.050 |
cand | +0.047 |
Neg logit contributions | |
kin | -0.042 |
upon | -0.038 |
moment | -0.034 |
loser | -0.034 |
rated | -0.033 |
Token | Jack |
Token ID | 3619 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
rob | +0.046 |
rides | +0.043 |
opl | +0.042 |
ons | +0.042 |
cand | +0.039 |
Neg logit contributions | |
kin | -0.023 |
upon | -0.022 |
moment | -0.020 |
isel | -0.020 |
inn | -0.018 |
Token | cheer |
Token ID | 14042 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
kin | +0.048 |
upon | +0.042 |
isel | +0.040 |
moment | +0.040 |
rated | +0.039 |
Neg logit contributions | |
rob | -0.061 |
rides | -0.058 |
ons | -0.058 |
opl | -0.056 |
cand | -0.051 |
Token | fully |
Token ID | 2759 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
ons | +0.096 |
rides | +0.095 |
rob | +0.090 |
hugs | +0.090 |
kisses | +0.090 |
Neg logit contributions | |
isel | -0.068 |
kin | -0.066 |
loser | -0.060 |
particular | -0.055 |
bet | -0.055 |
Token | said |
Token ID | 531 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
kin | +0.415 |
moment | +0.375 |
upon | +0.372 |
ided | +0.364 |
inn | +0.358 |
Neg logit contributions | |
rob | -0.725 |
ons | -0.660 |
opl | -0.660 |
rides | -0.608 |
pill | -0.584 |
Token | , |
Token ID | 11 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
rides | +0.350 |
ons | +0.341 |
rob | +0.322 |
cand | +0.308 |
kisses | +0.306 |
Neg logit contributions | |
kin | -0.409 |
isel | -0.380 |
upon | -0.371 |
rated | -0.370 |
inn | -0.353 |
Token | " |
Token ID | 366 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
rides | +0.006 |
rob | +0.006 |
ons | +0.006 |
opl | +0.005 |
cand | +0.005 |
Neg logit contributions | |
kin | -0.004 |
isel | -0.003 |
upon | -0.003 |
rated | -0.003 |
loser | -0.003 |
Token | Yes |
Token ID | 5297 |
Feature activation | -8.74e-03 |
Pos logit contributions | |
kin | +0.278 |
isel | +0.246 |
upon | +0.241 |
rated | +0.231 |
moment | +0.227 |
Neg logit contributions | |
rob | -0.238 |
rides | -0.235 |
ons | -0.224 |
opl | -0.209 |
cand | -0.197 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
kin | +0.018 |
isel | +0.016 |
upon | +0.016 |
rated | +0.016 |
moment | +0.015 |
Neg logit contributions | |
rides | -0.013 |
ons | -0.013 |
rob | -0.012 |
course | -0.012 |
cand | -0.011 |