Token | disob |
Token ID | 30163 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
them | +0.217 |
wreck | +0.201 |
polar | +0.194 |
mate | +0.183 |
inn | +0.181 |
Neg logit contributions | |
� | -0.213 |
cious | -0.209 |
's | -0.204 |
ience | -0.201 |
ages | -0.201 |
Token | edient |
Token ID | 35279 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
� | +0.189 |
's | +0.176 |
cious | +0.176 |
ience | +0.176 |
ages | +0.175 |
Neg logit contributions | |
them | -0.283 |
wreck | -0.262 |
mate | -0.259 |
polar | -0.253 |
inn | -0.247 |
Token | � |
Token ID | 6184 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
� | +0.213 |
cious | +0.208 |
ience | +0.203 |
ages | +0.203 |
's | +0.202 |
Neg logit contributions | |
them | -0.149 |
wreck | -0.129 |
mate | -0.128 |
polar | -0.123 |
inn | -0.117 |
Token | � |
Token ID | 95 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
� | +0.012 |
's | +0.012 |
ages | +0.012 |
cious | +0.012 |
ience | +0.011 |
Neg logit contributions | |
them | -0.013 |
wreck | -0.013 |
mate | -0.012 |
polar | -0.012 |
inn | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
mate | +0.011 |
wreck | +0.011 |
them | +0.011 |
inn | +0.011 |
ramp | +0.010 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.009 |
� | -0.009 |
cious | -0.009 |
's | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.200 |
persever | +0.191 |
decisions | +0.190 |
dedication | +0.186 |
aul | +0.186 |
Neg logit contributions | |
them | -0.212 |
wreck | -0.193 |
polar | -0.184 |
mate | -0.178 |
ramp | -0.176 |
Token | � |
Token ID | 250 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
cious | +0.832 |
� | +0.829 |
's | +0.805 |
ages | +0.800 |
ita | +0.775 |
Neg logit contributions | |
them | -0.654 |
wreck | -0.626 |
mate | -0.585 |
polar | -0.558 |
tow | -0.535 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
them | +0.012 |
wreck | +0.011 |
mate | +0.011 |
polar | +0.011 |
inn | +0.010 |
Neg logit contributions | |
� | -0.009 |
's | -0.009 |
ages | -0.008 |
cious | -0.008 |
ience | -0.008 |
Token | T |
Token ID | 51 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ages | +0.065 |
ience | +0.064 |
cious | +0.063 |
� | +0.062 |
's | +0.060 |
Neg logit contributions | |
them | -0.056 |
mate | -0.048 |
wreck | -0.047 |
polar | -0.047 |
inn | -0.045 |
Token | essa |
Token ID | 21411 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
� | +0.122 |
cious | +0.115 |
's | +0.114 |
ages | +0.114 |
ience | +0.113 |
Neg logit contributions | |
them | -0.155 |
wreck | -0.141 |
mate | -0.139 |
polar | -0.139 |
inn | -0.135 |
Token | was |
Token ID | 373 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
cious | +0.260 |
ages | +0.255 |
� | +0.253 |
ience | +0.251 |
Michelle | +0.249 |
Neg logit contributions | |
them | -0.161 |
polar | -0.140 |
wreck | -0.139 |
mate | -0.127 |
rock | -0.123 |
Token | something |
Token ID | 1223 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
them | +0.040 |
polar | +0.031 |
wreck | +0.031 |
mate | +0.031 |
his | +0.029 |
Neg logit contributions | |
ages | -0.050 |
� | -0.049 |
cious | -0.049 |
ience | -0.048 |
's | -0.047 |
Token | strange |
Token ID | 6283 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
� | +0.307 |
's | +0.291 |
cious | +0.288 |
ages | +0.284 |
ience | +0.283 |
Neg logit contributions | |
them | -0.259 |
wreck | -0.235 |
mate | -0.233 |
polar | -0.227 |
inn | -0.218 |
Token | � |
Token ID | 6184 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
� | +0.103 |
ages | +0.102 |
cious | +0.101 |
ience | +0.101 |
's | +0.098 |
Neg logit contributions | |
them | -0.071 |
wreck | -0.059 |
mate | -0.058 |
polar | -0.055 |
inn | -0.052 |
Token | � |
Token ID | 95 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ages | +0.014 |
's | +0.013 |
� | +0.012 |
pads | +0.012 |
ita | +0.012 |
Neg logit contributions | |
them | -0.012 |
wreck | -0.011 |
mate | -0.011 |
ramp | -0.011 |
inn | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
them | +0.010 |
mate | +0.010 |
wreck | +0.010 |
inn | +0.009 |
tow | +0.009 |
Neg logit contributions | |
ages | -0.009 |
ience | -0.009 |
thoughts | -0.008 |
bey | -0.008 |
aul | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.228 |
decisions | +0.220 |
dedication | +0.215 |
persever | +0.213 |
aul | +0.211 |
Neg logit contributions | |
them | -0.193 |
row | -0.156 |
Mike | -0.153 |
room | -0.153 |
block | -0.151 |
Token | � |
Token ID | 250 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ages | +0.974 |
cious | +0.935 |
thoughts | +0.923 |
decisions | +0.900 |
ita | +0.891 |
Neg logit contributions | |
them | -0.539 |
wreck | -0.480 |
mate | -0.426 |
ramp | -0.416 |
inn | -0.411 |
Token | the |
Token ID | 262 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
them | +0.011 |
wreck | +0.010 |
mate | +0.010 |
polar | +0.010 |
inn | +0.009 |
Neg logit contributions | |
� | -0.011 |
ages | -0.011 |
's | -0.010 |
ience | -0.010 |
cious | -0.010 |
Token | k |
Token ID | 479 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
� | +0.025 |
ages | +0.025 |
cious | +0.024 |
ience | +0.024 |
's | +0.024 |
Neg logit contributions | |
them | -0.020 |
wreck | -0.018 |
mate | -0.018 |
polar | -0.018 |
tow | -0.016 |
Token | itty |
Token ID | 9760 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
� | +0.029 |
's | +0.028 |
cious | +0.028 |
ages | +0.028 |
ience | +0.027 |
Neg logit contributions | |
them | -0.026 |
wreck | -0.024 |
mate | -0.024 |
polar | -0.023 |
inn | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
them | +0.054 |
wreck | +0.049 |
mate | +0.048 |
polar | +0.047 |
rock | +0.046 |
Neg logit contributions | |
ages | -0.051 |
List | -0.051 |
aul | -0.049 |
cious | -0.049 |
assy | -0.048 |
Token | hung |
Token ID | 9174 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
them | +0.067 |
wreck | +0.050 |
his | +0.050 |
rock | +0.048 |
mate | +0.047 |
Neg logit contributions | |
ages | -0.121 |
cious | -0.120 |
ience | -0.114 |
grand | -0.114 |
aul | -0.112 |
Token | rily |
Token ID | 28904 |
Feature activation | -7.77e+00 |
Pos logit contributions | |
� | +0.054 |
's | +0.051 |
cious | +0.051 |
ages | +0.050 |
ience | +0.050 |
Neg logit contributions | |
them | -0.041 |
wreck | -0.038 |
mate | -0.037 |
polar | -0.036 |
inn | -0.034 |
Token | � |
Token ID | 6184 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
them | +0.404 |
mate | +0.345 |
wreck | +0.341 |
polar | +0.321 |
inn | +0.303 |
Neg logit contributions | |
� | -0.602 |
cious | -0.584 |
ages | -0.584 |
ience | -0.576 |
's | -0.563 |
Token | � |
Token ID | 95 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ages | +0.015 |
's | +0.015 |
� | +0.015 |
ience | +0.014 |
listens | +0.014 |
Neg logit contributions | |
them | -0.010 |
mate | -0.009 |
wreck | -0.009 |
inn | -0.009 |
tow | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
inn | +0.010 |
mate | +0.010 |
them | +0.010 |
wreck | +0.010 |
load | +0.010 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.008 |
praying | -0.008 |
rises | -0.008 |
's | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.223 |
decisions | +0.220 |
persever | +0.214 |
dedication | +0.212 |
List | +0.211 |
Neg logit contributions | |
them | -0.181 |
block | -0.158 |
room | -0.157 |
row | -0.153 |
ramp | -0.145 |
Token | � |
Token ID | 250 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ages | +0.887 |
cious | +0.887 |
� | +0.861 |
's | +0.857 |
ita | +0.839 |
Neg logit contributions | |
them | -0.581 |
wreck | -0.539 |
mate | -0.505 |
inn | -0.472 |
polar | -0.471 |
Token | she |
Token ID | 673 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
them | +0.011 |
wreck | +0.010 |
mate | +0.010 |
polar | +0.010 |
inn | +0.010 |
Neg logit contributions | |
� | -0.011 |
's | -0.010 |
cious | -0.010 |
ages | -0.010 |
ience | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
cious | +0.176 |
List | +0.165 |
rises | +0.164 |
Michelle | +0.163 |
andra | +0.161 |
Neg logit contributions | |
them | -0.261 |
match | -0.251 |
wreck | -0.243 |
rock | -0.234 |
load | -0.231 |
Token | seen |
Token ID | 1775 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ages | +0.121 |
ience | +0.121 |
cious | +0.121 |
� | +0.120 |
aul | +0.117 |
Neg logit contributions | |
them | -0.101 |
wreck | -0.079 |
polar | -0.077 |
mate | -0.074 |
his | -0.073 |
Token | milk |
Token ID | 7545 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
them | +0.114 |
wreck | +0.088 |
mate | +0.087 |
polar | +0.087 |
his | +0.081 |
Neg logit contributions | |
ages | -0.144 |
cious | -0.144 |
� | -0.141 |
ience | -0.140 |
listens | -0.134 |
Token | it |
Token ID | 340 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
them | +0.013 |
wreck | +0.011 |
mate | +0.010 |
his | +0.009 |
polar | +0.009 |
Neg logit contributions | |
cious | -0.019 |
ages | -0.019 |
ience | -0.019 |
aul | -0.018 |
� | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
them | +0.084 |
wreck | +0.075 |
mate | +0.067 |
match | +0.067 |
rock | +0.066 |
Neg logit contributions | |
cious | -0.104 |
ages | -0.102 |
aul | -0.101 |
Michelle | -0.098 |
Denise | -0.095 |
Token | ugly |
Token ID | 13400 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
them | +0.030 |
wreck | +0.027 |
mate | +0.027 |
polar | +0.026 |
inn | +0.025 |
Neg logit contributions | |
� | -0.033 |
's | -0.031 |
cious | -0.031 |
ages | -0.031 |
ience | -0.031 |
Token | â |
Token ID | 22940 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
� | +0.019 |
cious | +0.018 |
's | +0.018 |
ages | +0.018 |
ience | +0.018 |
Neg logit contributions | |
them | -0.013 |
wreck | -0.012 |
mate | -0.012 |
polar | -0.011 |
inn | -0.011 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ience | +0.060 |
cious | +0.059 |
ages | +0.058 |
praying | +0.058 |
Louise | +0.057 |
Neg logit contributions | |
inn | -0.058 |
mate | -0.058 |
them | -0.057 |
match | -0.052 |
room | -0.052 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.167 |
aul | +0.163 |
Michelle | +0.162 |
persever | +0.158 |
List | +0.156 |
Neg logit contributions | |
them | -0.262 |
room | -0.220 |
wreck | -0.219 |
mate | -0.215 |
ramp | -0.214 |
Token | � |
Token ID | 251 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
cious | +0.896 |
� | +0.884 |
ages | +0.879 |
's | +0.851 |
ience | +0.846 |
Neg logit contributions | |
them | -0.608 |
wreck | -0.544 |
mate | -0.529 |
inn | -0.485 |
ramp | -0.485 |
Token | they |
Token ID | 9930 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
cious | +0.054 |
ience | +0.054 |
ages | +0.054 |
� | +0.052 |
Michelle | +0.051 |
Neg logit contributions | |
them | -0.038 |
wreck | -0.029 |
mate | -0.028 |
polar | -0.027 |
his | -0.027 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
them | +0.007 |
wreck | +0.006 |
mate | +0.006 |
polar | +0.006 |
inn | +0.006 |
Neg logit contributions | |
� | -0.007 |
's | -0.007 |
cious | -0.007 |
ience | -0.006 |
ages | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
� | +0.087 |
's | +0.084 |
cious | +0.082 |
ience | +0.080 |
ages | +0.080 |
Neg logit contributions | |
them | -0.055 |
wreck | -0.054 |
mate | -0.054 |
inn | -0.053 |
polar | -0.052 |
Token | just |
Token ID | 655 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
them | +0.071 |
wreck | +0.061 |
mate | +0.060 |
polar | +0.057 |
inn | +0.054 |
Neg logit contributions | |
cious | -0.113 |
ages | -0.112 |
� | -0.111 |
ience | -0.111 |
aul | -0.108 |
Token | high |
Token ID | 1029 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
� | +0.088 |
's | +0.081 |
cious | +0.080 |
ience | +0.078 |
ages | +0.076 |
Neg logit contributions | |
them | -0.081 |
inn | -0.070 |
mate | -0.070 |
wreck | -0.066 |
polar | -0.063 |
Token | rat |
Token ID | 4227 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
� | +0.046 |
's | +0.044 |
ience | +0.042 |
cious | +0.041 |
ages | +0.040 |
Neg logit contributions | |
them | -0.036 |
mate | -0.030 |
polar | -0.028 |
inn | -0.028 |
wreck | -0.028 |
Token | � |
Token ID | 6184 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
them | +0.020 |
wreck | +0.018 |
mate | +0.018 |
polar | +0.017 |
inn | +0.016 |
Neg logit contributions | |
� | -0.028 |
cious | -0.027 |
ages | -0.027 |
's | -0.027 |
ience | -0.027 |
Token | � |
Token ID | 95 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ages | +0.012 |
's | +0.012 |
� | +0.012 |
ience | +0.011 |
pays | +0.011 |
Neg logit contributions | |
mate | -0.012 |
them | -0.012 |
wreck | -0.012 |
inn | -0.011 |
polar | -0.011 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
mate | +0.010 |
them | +0.009 |
wreck | +0.009 |
ramp | +0.009 |
inn | +0.009 |
Neg logit contributions | |
ience | -0.009 |
� | -0.008 |
ages | -0.008 |
rises | -0.008 |
bey | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.221 |
decisions | +0.214 |
persever | +0.210 |
List | +0.209 |
dedication | +0.208 |
Neg logit contributions | |
them | -0.182 |
block | -0.170 |
snowball | -0.170 |
ramp | -0.168 |
room | -0.167 |
Token | � |
Token ID | 250 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ages | +0.863 |
cious | +0.858 |
� | +0.825 |
ita | +0.824 |
's | +0.824 |
Neg logit contributions | |
them | -0.602 |
wreck | -0.570 |
mate | -0.526 |
polar | -0.507 |
ramp | -0.506 |
Token | much |
Token ID | 881 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
them | +0.011 |
wreck | +0.010 |
mate | +0.010 |
polar | +0.010 |
inn | +0.009 |
Neg logit contributions | |
� | -0.010 |
cious | -0.010 |
's | -0.010 |
ages | -0.009 |
ience | -0.009 |
Token | bigger |
Token ID | 5749 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
cious | +0.189 |
� | +0.188 |
ages | +0.185 |
's | +0.181 |
ience | +0.179 |
Neg logit contributions | |
them | -0.161 |
wreck | -0.147 |
mate | -0.142 |
polar | -0.140 |
tow | -0.130 |
Token | than |
Token ID | 621 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
them | +0.071 |
wreck | +0.063 |
mate | +0.063 |
polar | +0.061 |
inn | +0.057 |
Neg logit contributions | |
� | -0.101 |
cious | -0.097 |
's | -0.096 |
ages | -0.095 |
ience | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
� | +0.168 |
's | +0.157 |
cious | +0.156 |
ages | +0.154 |
ience | +0.153 |
Neg logit contributions | |
them | -0.187 |
wreck | -0.174 |
mate | -0.170 |
polar | -0.169 |
inn | -0.163 |
Token | something |
Token ID | 1223 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
them | +0.108 |
wreck | +0.093 |
mate | +0.091 |
polar | +0.090 |
tow | +0.083 |
Neg logit contributions | |
� | -0.144 |
cious | -0.139 |
ages | -0.138 |
ience | -0.137 |
's | -0.136 |
Token | tasty |
Token ID | 25103 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
� | +0.300 |
's | +0.285 |
cious | +0.277 |
ages | +0.270 |
ience | +0.269 |
Neg logit contributions | |
them | -0.267 |
mate | -0.246 |
wreck | -0.246 |
polar | -0.238 |
inn | -0.231 |
Token | � |
Token ID | 6184 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
� | +0.104 |
's | +0.100 |
cious | +0.098 |
ages | +0.097 |
ience | +0.095 |
Neg logit contributions | |
them | -0.080 |
wreck | -0.074 |
mate | -0.072 |
polar | -0.072 |
inn | -0.068 |
Token | � |
Token ID | 95 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ages | +0.016 |
's | +0.015 |
� | +0.015 |
ience | +0.015 |
ita | +0.015 |
Neg logit contributions | |
wreck | -0.009 |
mate | -0.008 |
them | -0.008 |
inn | -0.008 |
tow | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
mate | +0.010 |
wreck | +0.010 |
them | +0.010 |
tow | +0.009 |
inn | +0.009 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.009 |
� | -0.009 |
listens | -0.008 |
cious | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.228 |
dedication | +0.213 |
decisions | +0.212 |
persever | +0.210 |
masse | +0.209 |
Neg logit contributions | |
them | -0.184 |
block | -0.170 |
wreck | -0.170 |
room | -0.164 |
row | -0.162 |
Token | � |
Token ID | 250 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ages | +0.831 |
� | +0.822 |
cious | +0.815 |
ita | +0.792 |
's | +0.788 |
Neg logit contributions | |
them | -0.639 |
wreck | -0.596 |
mate | -0.543 |
polar | -0.532 |
ramp | -0.519 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
them | +0.011 |
wreck | +0.010 |
mate | +0.010 |
polar | +0.009 |
inn | +0.009 |
Neg logit contributions | |
� | -0.010 |
's | -0.010 |
cious | -0.010 |
ages | -0.010 |
ience | -0.010 |
Token | mineral |
Token ID | 18352 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
� | +0.088 |
cious | +0.083 |
's | +0.083 |
ience | +0.081 |
ages | +0.080 |
Neg logit contributions | |
them | -0.079 |
mate | -0.069 |
wreck | -0.068 |
inn | -0.067 |
polar | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
� | +0.003 |
cious | +0.003 |
ages | +0.003 |
's | +0.003 |
ience | +0.003 |
Neg logit contributions | |
them | -0.002 |
wreck | -0.002 |
mate | -0.002 |
polar | -0.002 |
inn | -0.002 |
Token | But |
Token ID | 887 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ages | +0.006 |
cious | +0.005 |
ience | +0.005 |
ita | +0.005 |
's | +0.005 |
Neg logit contributions | |
them | -0.011 |
mate | -0.010 |
tow | -0.010 |
polar | -0.010 |
inn | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
� | +0.196 |
's | +0.186 |
cious | +0.184 |
ages | +0.183 |
ience | +0.179 |
Neg logit contributions | |
them | -0.156 |
wreck | -0.145 |
mate | -0.142 |
polar | -0.139 |
inn | -0.134 |
Token | surprises |
Token ID | 24072 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
� | +0.037 |
cious | +0.037 |
ience | +0.037 |
ages | +0.036 |
aul | +0.035 |
Neg logit contributions | |
them | -0.031 |
wreck | -0.026 |
polar | -0.025 |
mate | -0.025 |
tow | -0.024 |
Token | � |
Token ID | 6184 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
� | +0.244 |
's | +0.233 |
ages | +0.225 |
cious | +0.224 |
ience | +0.218 |
Neg logit contributions | |
them | -0.184 |
wreck | -0.180 |
polar | -0.175 |
mate | -0.172 |
inn | -0.168 |
Token | � |
Token ID | 95 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
's | +0.011 |
ages | +0.011 |
� | +0.011 |
ience | +0.011 |
ita | +0.010 |
Neg logit contributions | |
them | -0.013 |
mate | -0.012 |
wreck | -0.012 |
inn | -0.012 |
tow | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
them | +0.011 |
mate | +0.011 |
tow | +0.010 |
inn | +0.010 |
room | +0.010 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.009 |
aul | -0.008 |
praying | -0.008 |
rises | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.197 |
decisions | +0.186 |
persever | +0.182 |
masse | +0.179 |
Tooth | +0.176 |
Neg logit contributions | |
them | -0.224 |
room | -0.208 |
block | -0.194 |
tow | -0.190 |
row | -0.189 |
Token | � |
Token ID | 250 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
� | +0.861 |
ages | +0.852 |
cious | +0.849 |
's | +0.846 |
ience | +0.828 |
Neg logit contributions | |
them | -0.620 |
wreck | -0.553 |
mate | -0.541 |
polar | -0.510 |
inn | -0.507 |
Token | Amy |
Token ID | 14235 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
them | +0.012 |
wreck | +0.011 |
polar | +0.011 |
mate | +0.011 |
ramp | +0.010 |
Neg logit contributions | |
� | -0.010 |
cious | -0.009 |
's | -0.009 |
ages | -0.009 |
ience | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
cious | +0.185 |
ience | +0.184 |
� | +0.184 |
ages | +0.182 |
List | +0.178 |
Neg logit contributions | |
them | -0.128 |
mate | -0.109 |
wreck | -0.104 |
polar | -0.104 |
tow | -0.095 |
Token | managed |
Token ID | 5257 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
� | +0.117 |
cious | +0.112 |
ages | +0.111 |
ience | +0.111 |
's | +0.111 |
Neg logit contributions | |
them | -0.107 |
wreck | -0.094 |
mate | -0.092 |
polar | -0.091 |
inn | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
them | +0.015 |
wreck | +0.013 |
mate | +0.012 |
polar | +0.012 |
inn | +0.011 |
Neg logit contributions | |
� | -0.019 |
cious | -0.019 |
ages | -0.019 |
ience | -0.019 |
's | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
them | +0.147 |
mate | +0.133 |
wreck | +0.132 |
polar | +0.126 |
inn | +0.122 |
Neg logit contributions | |
� | -0.252 |
's | -0.242 |
cious | -0.238 |
ages | -0.236 |
ience | -0.235 |
Token | food |
Token ID | 2057 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
them | +0.230 |
wreck | +0.208 |
polar | +0.204 |
mate | +0.190 |
match | +0.183 |
Neg logit contributions | |
� | -0.294 |
ience | -0.272 |
cious | -0.271 |
ages | -0.266 |
's | -0.263 |
Token | � |
Token ID | 6184 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
� | +0.228 |
's | +0.219 |
ages | +0.211 |
cious | +0.208 |
ience | +0.204 |
Neg logit contributions | |
them | -0.178 |
wreck | -0.162 |
mate | -0.160 |
polar | -0.159 |
inn | -0.153 |
Token | � |
Token ID | 95 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
� | +0.014 |
's | +0.013 |
ages | +0.013 |
cious | +0.013 |
ience | +0.013 |
Neg logit contributions | |
them | -0.012 |
wreck | -0.011 |
mate | -0.011 |
inn | -0.011 |
polar | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
wreck | +0.011 |
mate | +0.011 |
them | +0.011 |
inn | +0.011 |
tow | +0.010 |
Neg logit contributions | |
ience | -0.009 |
cious | -0.008 |
� | -0.008 |
ages | -0.008 |
's | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.203 |
decisions | +0.185 |
ita | +0.184 |
Michelle | +0.182 |
persever | +0.182 |
Neg logit contributions | |
them | -0.212 |
wreck | -0.207 |
room | -0.198 |
block | -0.196 |
ramp | -0.194 |
Token | � |
Token ID | 251 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
cious | +0.866 |
ages | +0.848 |
� | +0.823 |
's | +0.816 |
ita | +0.806 |
Neg logit contributions | |
them | -0.607 |
wreck | -0.579 |
mate | -0.533 |
snowball | -0.513 |
inn | -0.511 |
Token | only |
Token ID | 691 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
cious | +0.048 |
ience | +0.047 |
ages | +0.046 |
� | +0.046 |
's | +0.044 |
Neg logit contributions | |
them | -0.043 |
wreck | -0.037 |
polar | -0.036 |
mate | -0.036 |
his | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
them | +0.105 |
wreck | +0.096 |
polar | +0.095 |
mate | +0.094 |
inn | +0.089 |
Neg logit contributions | |
ages | -0.118 |
� | -0.116 |
cious | -0.114 |
aul | -0.113 |
ience | -0.111 |
Token | find |
Token ID | 1064 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
� | +0.047 |
's | +0.045 |
cious | +0.045 |
ages | +0.044 |
ience | +0.044 |
Neg logit contributions | |
them | -0.032 |
wreck | -0.028 |
mate | -0.028 |
polar | -0.027 |
inn | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
them | +0.064 |
wreck | +0.059 |
mate | +0.058 |
polar | +0.057 |
inn | +0.055 |
Neg logit contributions | |
� | -0.066 |
's | -0.062 |
cious | -0.062 |
ages | -0.061 |
ience | -0.061 |
Token | something |
Token ID | 1223 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
them | +0.042 |
wreck | +0.034 |
mate | +0.034 |
polar | +0.032 |
his | +0.031 |
Neg logit contributions | |
ages | -0.047 |
cious | -0.047 |
� | -0.047 |
ience | -0.046 |
's | -0.044 |
Token | important |
Token ID | 1593 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
� | +0.302 |
's | +0.284 |
cious | +0.273 |
ience | +0.267 |
ages | +0.263 |
Neg logit contributions | |
them | -0.265 |
mate | -0.247 |
wreck | -0.247 |
polar | -0.244 |
inn | -0.232 |
Token | � |
Token ID | 6184 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
� | +0.308 |
ages | +0.301 |
ience | +0.300 |
cious | +0.299 |
's | +0.292 |
Neg logit contributions | |
them | -0.236 |
mate | -0.205 |
wreck | -0.197 |
inn | -0.184 |
polar | -0.182 |
Token | � |
Token ID | 95 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ages | +0.013 |
's | +0.013 |
� | +0.012 |
pads | +0.012 |
ita | +0.012 |
Neg logit contributions | |
them | -0.012 |
wreck | -0.012 |
mate | -0.012 |
inn | -0.011 |
ramp | -0.011 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
mate | +0.010 |
them | +0.010 |
room | +0.009 |
inn | +0.009 |
ramp | +0.009 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.009 |
bey | -0.008 |
decisions | -0.008 |
aul | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.198 |
decisions | +0.192 |
List | +0.183 |
dedication | +0.182 |
persever | +0.181 |
Neg logit contributions | |
them | -0.214 |
room | -0.195 |
block | -0.184 |
row | -0.178 |
ramp | -0.176 |
Token | � |
Token ID | 250 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ages | +1.018 |
cious | +1.003 |
thoughts | +0.987 |
decisions | +0.958 |
ita | +0.957 |
Neg logit contributions | |
them | -0.473 |
wreck | -0.411 |
mate | -0.359 |
ramp | -0.349 |
inn | -0.344 |
Token | the |
Token ID | 262 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
them | +0.011 |
wreck | +0.010 |
mate | +0.010 |
polar | +0.010 |
inn | +0.010 |
Neg logit contributions | |
� | -0.010 |
's | -0.010 |
cious | -0.010 |
ages | -0.010 |
ience | -0.010 |
Token | doll |
Token ID | 3654 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
� | +0.026 |
's | +0.025 |
cious | +0.025 |
ages | +0.024 |
ience | +0.024 |
Neg logit contributions | |
them | -0.020 |
wreck | -0.018 |
mate | -0.017 |
polar | -0.017 |
inn | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
them | +0.240 |
wreck | +0.223 |
mate | +0.218 |
polar | +0.204 |
match | +0.201 |
Neg logit contributions | |
cious | -0.219 |
ages | -0.216 |
List | -0.209 |
aul | -0.206 |
� | -0.204 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
� | +0.117 |
ages | +0.116 |
cious | +0.115 |
ience | +0.114 |
aul | +0.112 |
Neg logit contributions | |
them | -0.107 |
wreck | -0.092 |
mate | -0.087 |
polar | -0.087 |
tow | -0.083 |
Token | and |
Token ID | 290 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
ages | +0.362 |
ience | +0.353 |
cious | +0.351 |
� | +0.342 |
aul | +0.340 |
Neg logit contributions | |
them | -0.189 |
wreck | -0.137 |
mate | -0.127 |
polar | -0.127 |
match | -0.127 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ages | +0.045 |
cious | +0.042 |
aul | +0.041 |
� | +0.040 |
ience | +0.040 |
Neg logit contributions | |
them | -0.030 |
wreck | -0.023 |
his | -0.023 |
rock | -0.021 |
polar | -0.020 |
Token | � |
Token ID | 6184 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
� | +0.206 |
ages | +0.203 |
cious | +0.201 |
ience | +0.201 |
's | +0.195 |
Neg logit contributions | |
them | -0.135 |
wreck | -0.110 |
mate | -0.110 |
polar | -0.109 |
inn | -0.100 |
Token | � |
Token ID | 95 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ages | +0.012 |
's | +0.012 |
Michelle | +0.011 |
� | +0.011 |
cious | +0.011 |
Neg logit contributions | |
them | -0.013 |
wreck | -0.013 |
mate | -0.012 |
inn | -0.012 |
ramp | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
them | +0.010 |
wreck | +0.010 |
mate | +0.010 |
tow | +0.010 |
room | +0.010 |
Neg logit contributions | |
ages | -0.009 |
ience | -0.009 |
cious | -0.008 |
pads | -0.008 |
bey | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.247 |
masse | +0.237 |
decisions | +0.235 |
Tooth | +0.230 |
persever | +0.228 |
Neg logit contributions | |
them | -0.169 |
room | -0.154 |
block | -0.151 |
wreck | -0.143 |
ramp | -0.137 |
Token | � |
Token ID | 251 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ages | +0.890 |
cious | +0.875 |
� | +0.841 |
's | +0.837 |
ita | +0.833 |
Neg logit contributions | |
them | -0.600 |
wreck | -0.540 |
mate | -0.512 |
tow | -0.477 |
ramp | -0.476 |
Token | it |
Token ID | 340 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ages | +0.059 |
cious | +0.058 |
ience | +0.058 |
ccoli | +0.055 |
ita | +0.054 |
Neg logit contributions | |
them | -0.035 |
his | -0.026 |
mate | -0.024 |
tow | -0.022 |
inn | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
them | +0.079 |
wreck | +0.066 |
polar | +0.065 |
mate | +0.064 |
his | +0.062 |
Neg logit contributions | |
aul | -0.104 |
ages | -0.104 |
cious | -0.103 |
Michelle | -0.100 |
decisions | -0.096 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
them | +0.028 |
polar | +0.023 |
wreck | +0.022 |
mate | +0.022 |
tow | +0.022 |
Neg logit contributions | |
ages | -0.037 |
cious | -0.036 |
ience | -0.036 |
� | -0.034 |
's | -0.034 |
Token | special |
Token ID | 2041 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
� | +0.085 |
cious | +0.081 |
's | +0.081 |
ages | +0.081 |
ience | +0.080 |
Neg logit contributions | |
them | -0.077 |
wreck | -0.071 |
mate | -0.069 |
polar | -0.068 |
inn | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
them | +0.081 |
wreck | +0.073 |
mate | +0.071 |
polar | +0.070 |
inn | +0.065 |
Neg logit contributions | |
cious | -0.106 |
ages | -0.102 |
aul | -0.101 |
ience | -0.099 |
� | -0.099 |
Token | too |
Token ID | 1165 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
them | +0.025 |
mate | +0.023 |
wreck | +0.023 |
polar | +0.022 |
inn | +0.021 |
Neg logit contributions | |
� | -0.038 |
's | -0.036 |
ages | -0.035 |
ience | -0.035 |
cious | -0.034 |
Token | late |
Token ID | 2739 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
them | +0.220 |
wreck | +0.206 |
polar | +0.199 |
inn | +0.195 |
mate | +0.192 |
Neg logit contributions | |
cious | -0.166 |
� | -0.163 |
's | -0.158 |
ages | -0.156 |
ience | -0.155 |
Token | â |
Token ID | 22940 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
� | +0.321 |
cious | +0.320 |
ages | +0.318 |
ience | +0.316 |
's | +0.308 |
Neg logit contributions | |
them | -0.195 |
mate | -0.158 |
wreck | -0.155 |
polar | -0.142 |
inn | -0.141 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
cious | +0.055 |
ience | +0.053 |
pill | +0.051 |
� | +0.050 |
ups | +0.050 |
Neg logit contributions | |
inn | -0.065 |
mate | -0.064 |
wreck | -0.061 |
them | -0.060 |
ramp | -0.058 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.177 |
aul | +0.162 |
ita | +0.161 |
Michelle | +0.159 |
Louise | +0.156 |
Neg logit contributions | |
them | -0.247 |
wreck | -0.232 |
ramp | -0.229 |
mate | -0.221 |
room | -0.216 |
Token | � |
Token ID | 251 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
cious | +0.952 |
� | +0.935 |
ages | +0.914 |
's | +0.914 |
ita | +0.899 |
Neg logit contributions | |
them | -0.550 |
wreck | -0.497 |
mate | -0.482 |
ramp | -0.443 |
inn | -0.441 |
Token | the |
Token ID | 1169 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
cious | +0.047 |
ience | +0.046 |
� | +0.046 |
ages | +0.044 |
's | +0.044 |
Neg logit contributions | |
them | -0.044 |
wreck | -0.037 |
mate | -0.037 |
polar | -0.036 |
inn | -0.035 |
Token | o |
Token ID | 267 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
� | +0.108 |
cious | +0.104 |
's | +0.103 |
ages | +0.102 |
ience | +0.101 |
Neg logit contributions | |
them | -0.076 |
wreck | -0.069 |
mate | -0.067 |
polar | -0.066 |
inn | -0.062 |
Token | at |
Token ID | 265 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
mate | +0.086 |
wreck | +0.085 |
them | +0.084 |
polar | +0.079 |
inn | +0.079 |
Neg logit contributions | |
� | -0.100 |
ience | -0.097 |
cious | -0.096 |
Michelle | -0.094 |
's | -0.092 |
Token | had |
Token ID | 550 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
� | +0.245 |
cious | +0.238 |
ience | +0.231 |
ages | +0.228 |
's | +0.227 |
Neg logit contributions | |
them | -0.250 |
wreck | -0.232 |
mate | -0.227 |
polar | -0.222 |
inn | -0.210 |
Token | big |
Token ID | 1263 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
� | +0.093 |
's | +0.087 |
cious | +0.084 |
ience | +0.082 |
ages | +0.080 |
Neg logit contributions | |
them | -0.075 |
inn | -0.066 |
mate | -0.065 |
wreck | -0.060 |
polar | -0.059 |
Token | surprise |
Token ID | 5975 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
them | +0.080 |
mate | +0.072 |
inn | +0.072 |
polar | +0.064 |
wreck | +0.062 |
Neg logit contributions | |
� | -0.099 |
's | -0.094 |
ience | -0.088 |
cious | -0.086 |
Michelle | -0.084 |
Token | � |
Token ID | 6184 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
them | +0.240 |
tant | +0.233 |
wreck | +0.231 |
inn | +0.226 |
polar | +0.223 |
Neg logit contributions | |
� | -0.259 |
's | -0.243 |
cious | -0.216 |
Michelle | -0.207 |
ages | -0.201 |
Token | � |
Token ID | 95 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ages | +0.013 |
's | +0.013 |
� | +0.013 |
ience | +0.012 |
cious | +0.012 |
Neg logit contributions | |
wreck | -0.012 |
them | -0.012 |
mate | -0.011 |
ramp | -0.011 |
inn | -0.011 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
mate | +0.010 |
them | +0.010 |
wreck | +0.010 |
ramp | +0.010 |
inn | +0.010 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.009 |
cious | -0.008 |
bey | -0.008 |
ita | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.218 |
persever | +0.204 |
decisions | +0.202 |
dedication | +0.199 |
aul | +0.199 |
Neg logit contributions | |
them | -0.203 |
room | -0.184 |
wreck | -0.180 |
ramp | -0.179 |
block | -0.174 |
Token | � |
Token ID | 250 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ages | +0.800 |
cious | +0.793 |
� | +0.793 |
's | +0.763 |
ience | +0.761 |
Neg logit contributions | |
them | -0.691 |
wreck | -0.634 |
mate | -0.597 |
polar | -0.573 |
ramp | -0.571 |
Token | there |
Token ID | 612 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
them | +0.011 |
wreck | +0.011 |
mate | +0.010 |
polar | +0.010 |
inn | +0.010 |
Neg logit contributions | |
� | -0.010 |
cious | -0.009 |
's | -0.009 |
ages | -0.009 |
ience | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
ages | +0.005 |
cious | +0.005 |
ience | +0.005 |
� | +0.005 |
aul | +0.005 |
Neg logit contributions | |
them | -0.005 |
wreck | -0.004 |
mate | -0.004 |
polar | -0.004 |
tow | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
them | +0.027 |
polar | +0.021 |
wreck | +0.021 |
mate | +0.020 |
his | +0.020 |
Neg logit contributions | |
ages | -0.036 |
cious | -0.035 |
ience | -0.035 |
aul | -0.034 |
� | -0.034 |
Token | big |
Token ID | 1263 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
� | +0.092 |
cious | +0.085 |
's | +0.085 |
ience | +0.082 |
ages | +0.080 |
Neg logit contributions | |
them | -0.075 |
inn | -0.064 |
mate | -0.064 |
wreck | -0.062 |
polar | -0.060 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
them | +0.055 |
wreck | +0.050 |
mate | +0.049 |
polar | +0.048 |
inn | +0.046 |
Neg logit contributions | |
� | -0.067 |
's | -0.063 |
cious | -0.063 |
ages | -0.062 |
ience | -0.062 |
Token | cereal |
Token ID | 33158 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
them | +0.065 |
mate | +0.065 |
inn | +0.064 |
polar | +0.062 |
wreck | +0.061 |
Neg logit contributions | |
's | -0.073 |
� | -0.071 |
ience | -0.058 |
thoughts | -0.058 |
aul | -0.056 |
Token | � |
Token ID | 6184 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
them | +0.003 |
wreck | +0.003 |
mate | +0.003 |
polar | +0.003 |
inn | +0.002 |
Neg logit contributions | |
� | -0.004 |
's | -0.004 |
ages | -0.003 |
cious | -0.003 |
ience | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ages | +0.014 |
's | +0.014 |
� | +0.013 |
cious | +0.013 |
ience | +0.013 |
Neg logit contributions | |
them | -0.010 |
mate | -0.010 |
wreck | -0.010 |
inn | -0.009 |
tow | -0.009 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
mate | +0.011 |
room | +0.010 |
them | +0.010 |
inn | +0.010 |
tow | +0.010 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.009 |
decisions | -0.008 |
cious | -0.008 |
pads | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.226 |
decisions | +0.223 |
persever | +0.211 |
dedication | +0.207 |
List | +0.204 |
Neg logit contributions | |
them | -0.187 |
room | -0.173 |
block | -0.164 |
row | -0.159 |
tow | -0.155 |
Token | � |
Token ID | 251 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ages | +0.869 |
cious | +0.867 |
� | +0.855 |
's | +0.836 |
ience | +0.833 |
Neg logit contributions | |
them | -0.608 |
wreck | -0.545 |
mate | -0.537 |
polar | -0.494 |
inn | -0.491 |
Token | she |
Token ID | 673 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
cious | +0.051 |
ages | +0.051 |
ience | +0.051 |
ccoli | +0.048 |
aul | +0.047 |
Neg logit contributions | |
them | -0.039 |
his | -0.031 |
mate | -0.030 |
polar | -0.029 |
tow | -0.029 |
Token | ate |
Token ID | 15063 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
cious | +0.242 |
� | +0.241 |
ages | +0.239 |
ience | +0.235 |
aul | +0.228 |
Neg logit contributions | |
them | -0.218 |
wreck | -0.195 |
polar | -0.192 |
mate | -0.189 |
inn | -0.178 |
Token | it |
Token ID | 340 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
� | +0.144 |
's | +0.138 |
aul | +0.124 |
ience | +0.123 |
ages | +0.122 |
Neg logit contributions | |
wreck | -0.112 |
polar | -0.106 |
mate | -0.105 |
ramp | -0.100 |
tow | -0.099 |
Token | with |
Token ID | 351 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
them | +0.069 |
mate | +0.057 |
wreck | +0.057 |
inn | +0.053 |
polar | +0.052 |
Neg logit contributions | |
cious | -0.117 |
� | -0.115 |
ience | -0.115 |
ages | -0.114 |
Michelle | -0.109 |
Token | , |
Token ID | 11 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
them | +0.055 |
wreck | +0.050 |
mate | +0.049 |
polar | +0.047 |
inn | +0.046 |
Neg logit contributions | |
� | -0.074 |
's | -0.071 |
cious | -0.070 |
ages | -0.070 |
ience | -0.069 |
Token | pink |
Token ID | 11398 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ages | +0.033 |
cious | +0.032 |
ience | +0.031 |
� | +0.031 |
aul | +0.031 |
Neg logit contributions | |
them | -0.019 |
polar | -0.017 |
snowball | -0.016 |
his | -0.016 |
wreck | -0.016 |
Token | scarf |
Token ID | 36953 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
them | +0.135 |
wreck | +0.128 |
mate | +0.124 |
inn | +0.121 |
polar | +0.118 |
Neg logit contributions | |
� | -0.156 |
's | -0.155 |
ience | -0.147 |
ages | -0.147 |
cious | -0.147 |
Token | â |
Token ID | 22940 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
them | +0.088 |
wreck | +0.079 |
mate | +0.078 |
polar | +0.076 |
inn | +0.072 |
Neg logit contributions | |
� | -0.115 |
cious | -0.109 |
's | -0.109 |
ages | -0.109 |
ience | -0.108 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
cious | +0.051 |
ience | +0.050 |
ages | +0.049 |
� | +0.047 |
Louise | +0.046 |
Neg logit contributions | |
mate | -0.067 |
inn | -0.067 |
them | -0.065 |
room | -0.061 |
wreck | -0.061 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.185 |
decisions | +0.177 |
persever | +0.172 |
� | +0.171 |
List | +0.170 |
Neg logit contributions | |
them | -0.236 |
room | -0.207 |
ramp | -0.207 |
snowball | -0.205 |
mate | -0.202 |
Token | � |
Token ID | 251 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
� | +0.872 |
cious | +0.869 |
ages | +0.851 |
's | +0.834 |
ience | +0.825 |
Neg logit contributions | |
them | -0.621 |
mate | -0.554 |
wreck | -0.550 |
polar | -0.509 |
inn | -0.504 |
Token | she |
Token ID | 7091 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ience | +0.058 |
cious | +0.058 |
ages | +0.057 |
ccoli | +0.054 |
ita | +0.053 |
Neg logit contributions | |
them | -0.033 |
his | -0.027 |
mate | -0.025 |
wreck | -0.024 |
tow | -0.023 |
Token | kept |
Token ID | 4030 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
them | +0.035 |
wreck | +0.032 |
mate | +0.032 |
polar | +0.031 |
inn | +0.030 |
Neg logit contributions | |
� | -0.033 |
cious | -0.031 |
ages | -0.031 |
's | -0.030 |
ience | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
them | +0.008 |
wreck | +0.007 |
mate | +0.007 |
polar | +0.007 |
inn | +0.007 |
Neg logit contributions | |
� | -0.013 |
's | -0.012 |
cious | -0.012 |
ages | -0.012 |
ience | -0.012 |
Token | safe |
Token ID | 3338 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
them | +0.075 |
wreck | +0.066 |
mate | +0.065 |
polar | +0.064 |
inn | +0.060 |
Neg logit contributions | |
� | -0.108 |
cious | -0.107 |
ience | -0.107 |
ages | -0.106 |
aul | -0.102 |
Token | final |
Token ID | 2457 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
them | +0.077 |
wreck | +0.069 |
mate | +0.067 |
polar | +0.066 |
inn | +0.062 |
Neg logit contributions | |
� | -0.112 |
cious | -0.107 |
ages | -0.107 |
's | -0.107 |
ience | -0.105 |
Token | destination |
Token ID | 10965 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
them | +0.011 |
mate | +0.010 |
wreck | +0.010 |
polar | +0.010 |
inn | +0.009 |
Neg logit contributions | |
� | -0.015 |
's | -0.014 |
cious | -0.014 |
ience | -0.013 |
ages | -0.013 |
Token | � |
Token ID | 6184 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
them | +0.236 |
wreck | +0.207 |
mate | +0.204 |
polar | +0.197 |
inn | +0.187 |
Neg logit contributions | |
� | -0.347 |
cious | -0.332 |
ages | -0.330 |
's | -0.330 |
ience | -0.330 |
Token | � |
Token ID | 95 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
� | +0.012 |
ages | +0.012 |
's | +0.012 |
cious | +0.012 |
ience | +0.011 |
Neg logit contributions | |
them | -0.013 |
wreck | -0.012 |
mate | -0.012 |
polar | -0.011 |
inn | -0.011 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
them | +0.011 |
mate | +0.010 |
wreck | +0.010 |
tow | +0.010 |
inn | +0.010 |
Neg logit contributions | |
� | -0.009 |
cious | -0.009 |
ages | -0.009 |
ience | -0.009 |
aul | -0.009 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.195 |
aul | +0.190 |
decisions | +0.182 |
Michelle | +0.181 |
� | +0.180 |
Neg logit contributions | |
them | -0.228 |
wreck | -0.196 |
tow | -0.195 |
room | -0.194 |
ramp | -0.194 |
Token | � |
Token ID | 250 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
cious | +0.792 |
� | +0.791 |
ages | +0.787 |
's | +0.769 |
ience | +0.755 |
Neg logit contributions | |
them | -0.694 |
wreck | -0.633 |
mate | -0.617 |
polar | -0.594 |
tow | -0.575 |
Token | Lilly |
Token ID | 35134 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
them | +0.012 |
mate | +0.011 |
wreck | +0.011 |
polar | +0.010 |
inn | +0.010 |
Neg logit contributions | |
� | -0.010 |
's | -0.010 |
ages | -0.010 |
cious | -0.010 |
ience | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | +9.30e+00 |
Pos logit contributions | |
them | +0.003 |
wreck | +0.003 |
mate | +0.003 |
polar | +0.003 |
rock | +0.002 |
Neg logit contributions | |
cious | -0.007 |
ages | -0.006 |
List | -0.006 |
aul | -0.006 |
Michelle | -0.006 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
� | +0.650 |
ages | +0.642 |
cious | +0.639 |
ience | +0.625 |
's | +0.622 |
Neg logit contributions | |
them | -0.548 |
wreck | -0.496 |
polar | -0.476 |
mate | -0.472 |
tow | -0.447 |
Token | place |
Token ID | 1295 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
them | +0.058 |
inn | +0.054 |
wreck | +0.052 |
mate | +0.052 |
polar | +0.051 |
Neg logit contributions | |
� | -0.081 |
's | -0.078 |
ience | -0.074 |
cious | -0.074 |
ages | -0.073 |
Token | 't |
Token ID | 470 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
cious | +0.033 |
ages | +0.033 |
ience | +0.032 |
aul | +0.031 |
� | +0.031 |
Neg logit contributions | |
them | -0.019 |
wreck | -0.015 |
mate | -0.015 |
inn | -0.014 |
tow | -0.014 |
Token | believe |
Token ID | 1975 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
them | +0.316 |
polar | +0.302 |
mate | +0.294 |
wreck | +0.294 |
snowball | +0.294 |
Neg logit contributions | |
� | -0.234 |
's | -0.207 |
cious | -0.197 |
ience | -0.184 |
ages | -0.180 |
Token | it |
Token ID | 340 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
� | +0.246 |
's | +0.234 |
cious | +0.228 |
ience | +0.225 |
ages | +0.217 |
Neg logit contributions | |
wreck | -0.206 |
them | -0.205 |
polar | -0.204 |
mate | -0.194 |
inn | -0.190 |
Token | â |
Token ID | 22940 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
them | +0.077 |
mate | +0.065 |
wreck | +0.058 |
inn | +0.054 |
match | +0.054 |
Neg logit contributions | |
ages | -0.113 |
cious | -0.109 |
aul | -0.108 |
ience | -0.106 |
� | -0.105 |
Token | € |
Token ID | 26391 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ages | +0.052 |
cious | +0.051 |
ience | +0.049 |
praying | +0.048 |
aul | +0.047 |
Neg logit contributions | |
inn | -0.066 |
mate | -0.065 |
them | -0.064 |
room | -0.059 |
match | -0.058 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.182 |
List | +0.177 |
decisions | +0.176 |
aul | +0.173 |
persever | +0.166 |
Neg logit contributions | |
them | -0.235 |
room | -0.216 |
mate | -0.198 |
ramp | -0.192 |
tow | -0.184 |
Token | � |
Token ID | 251 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
cious | +0.958 |
ages | +0.947 |
� | +0.935 |
's | +0.925 |
ience | +0.917 |
Neg logit contributions | |
them | -0.534 |
mate | -0.464 |
wreck | -0.441 |
inn | -0.427 |
ramp | -0.407 |
Token | this |
Token ID | 5661 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ience | +0.060 |
ages | +0.058 |
cious | +0.058 |
ccoli | +0.058 |
aul | +0.054 |
Neg logit contributions | |
them | -0.035 |
his | -0.024 |
mate | -0.023 |
tow | -0.020 |
control | -0.020 |
Token | one |
Token ID | 530 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ages | +0.153 |
cious | +0.153 |
� | +0.150 |
aul | +0.144 |
's | +0.142 |
Neg logit contributions | |
them | -0.113 |
mate | -0.097 |
wreck | -0.097 |
polar | -0.091 |
inn | -0.090 |
Token | feather |
Token ID | 17972 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ages | +0.078 |
cious | +0.077 |
� | +0.074 |
ience | +0.072 |
aul | +0.072 |
Neg logit contributions | |
them | -0.055 |
wreck | -0.050 |
mate | -0.049 |
polar | -0.046 |
inn | -0.045 |
Token | seemed |
Token ID | 3947 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
� | +0.097 |
cious | +0.093 |
ages | +0.093 |
ience | +0.091 |
's | +0.090 |
Neg logit contributions | |
them | -0.088 |
mate | -0.077 |
wreck | -0.077 |
polar | -0.075 |
inn | -0.071 |
Token | he |
Token ID | 339 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
� | +0.334 |
's | +0.315 |
cious | +0.300 |
ages | +0.290 |
ience | +0.287 |
Neg logit contributions | |
them | -0.237 |
mate | -0.226 |
wreck | -0.213 |
polar | -0.209 |
inn | -0.205 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
� | +0.032 |
's | +0.030 |
cious | +0.028 |
ience | +0.027 |
ages | +0.026 |
Neg logit contributions | |
them | -0.037 |
mate | -0.036 |
wreck | -0.035 |
inn | -0.034 |
polar | -0.033 |
Token | � |
Token ID | 6184 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
them | +0.064 |
wreck | +0.058 |
mate | +0.057 |
polar | +0.056 |
inn | +0.054 |
Neg logit contributions | |
� | -0.086 |
's | -0.082 |
cious | -0.081 |
ages | -0.080 |
ience | -0.079 |
Token | � |
Token ID | 95 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ages | +0.012 |
� | +0.012 |
's | +0.012 |
ience | +0.011 |
cious | +0.011 |
Neg logit contributions | |
them | -0.012 |
wreck | -0.011 |
mate | -0.011 |
inn | -0.011 |
polar | -0.011 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
them | +0.011 |
wreck | +0.011 |
mate | +0.011 |
inn | +0.011 |
ramp | +0.010 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.009 |
� | -0.008 |
's | -0.008 |
cious | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.205 |
� | +0.194 |
decisions | +0.188 |
Michelle | +0.188 |
aul | +0.187 |
Neg logit contributions | |
them | -0.224 |
wreck | -0.204 |
polar | -0.194 |
ramp | -0.194 |
mate | -0.193 |
Token | � |
Token ID | 250 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ages | +0.763 |
� | +0.763 |
cious | +0.750 |
ience | +0.731 |
's | +0.729 |
Neg logit contributions | |
them | -0.724 |
wreck | -0.673 |
mate | -0.623 |
polar | -0.622 |
inn | -0.608 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
them | +0.012 |
wreck | +0.011 |
mate | +0.011 |
polar | +0.011 |
ramp | +0.010 |
Neg logit contributions | |
� | -0.011 |
's | -0.010 |
cious | -0.010 |
ages | -0.010 |
ience | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
� | +0.096 |
cious | +0.091 |
's | +0.091 |
ience | +0.089 |
ages | +0.088 |
Neg logit contributions | |
them | -0.069 |
mate | -0.060 |
wreck | -0.059 |
inn | -0.057 |
polar | -0.056 |
Token | soft |
Token ID | 2705 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
them | +0.076 |
mate | +0.067 |
inn | +0.065 |
wreck | +0.064 |
polar | +0.061 |
Neg logit contributions | |
� | -0.102 |
's | -0.098 |
cious | -0.095 |
ience | -0.094 |
ages | -0.091 |
Token | swing |
Token ID | 9628 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
� | +0.084 |
's | +0.081 |
cious | +0.080 |
ages | +0.078 |
ience | +0.078 |
Neg logit contributions | |
them | -0.065 |
wreck | -0.058 |
mate | -0.057 |
inn | -0.054 |
polar | -0.054 |
Token | special |
Token ID | 2041 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
them | +0.153 |
wreck | +0.140 |
polar | +0.136 |
mate | +0.134 |
inn | +0.129 |
Neg logit contributions | |
� | -0.188 |
's | -0.176 |
cious | -0.175 |
ience | -0.175 |
ages | -0.174 |
Token | thing |
Token ID | 1517 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
� | +0.173 |
's | +0.166 |
cious | +0.164 |
ages | +0.163 |
ience | +0.160 |
Neg logit contributions | |
them | -0.143 |
wreck | -0.126 |
mate | -0.125 |
polar | -0.122 |
inn | -0.120 |
Token | � |
Token ID | 6184 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
them | +0.010 |
wreck | +0.009 |
mate | +0.009 |
polar | +0.009 |
inn | +0.008 |
Neg logit contributions | |
� | -0.011 |
's | -0.011 |
cious | -0.011 |
ages | -0.011 |
ience | -0.010 |
Token | � |
Token ID | 95 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
� | +0.013 |
ages | +0.013 |
's | +0.013 |
ience | +0.012 |
cious | +0.012 |
Neg logit contributions | |
them | -0.011 |
wreck | -0.010 |
mate | -0.010 |
inn | -0.009 |
polar | -0.009 |
Token | € |
Token ID | 26391 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
them | +0.010 |
wreck | +0.010 |
mate | +0.010 |
inn | +0.010 |
tow | +0.009 |
Neg logit contributions | |
ience | -0.010 |
ages | -0.010 |
� | -0.010 |
's | -0.009 |
cious | -0.009 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.213 |
decisions | +0.209 |
� | +0.203 |
dedication | +0.201 |
List | +0.194 |
Neg logit contributions | |
them | -0.204 |
wreck | -0.183 |
room | -0.181 |
block | -0.180 |
tow | -0.177 |
Token | � |
Token ID | 250 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
� | +0.686 |
ages | +0.656 |
cious | +0.652 |
's | +0.644 |
ience | +0.640 |
Neg logit contributions | |
them | -0.815 |
wreck | -0.763 |
mate | -0.735 |
polar | -0.733 |
inn | -0.700 |
Token | wings |
Token ID | 12098 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
them | +0.012 |
wreck | +0.011 |
mate | +0.011 |
polar | +0.011 |
ramp | +0.010 |
Neg logit contributions | |
� | -0.011 |
cious | -0.010 |
's | -0.010 |
ages | -0.010 |
aul | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
� | +0.318 |
's | +0.303 |
ience | +0.272 |
ages | +0.270 |
cious | +0.265 |
Neg logit contributions | |
them | -0.281 |
mate | -0.259 |
polar | -0.254 |
inn | -0.252 |
wreck | -0.247 |
Token | Every |
Token ID | 3887 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ages | +0.008 |
cious | +0.007 |
ience | +0.007 |
's | +0.007 |
� | +0.007 |
Neg logit contributions | |
them | -0.008 |
polar | -0.007 |
mate | -0.007 |
wreck | -0.007 |
tow | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
them | +0.074 |
mate | +0.067 |
wreck | +0.067 |
polar | +0.064 |
rock | +0.061 |
Neg logit contributions | |
cious | -0.072 |
� | -0.072 |
ages | -0.071 |
ience | -0.070 |
aul | -0.067 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
ages | +0.030 |
cious | +0.029 |
ience | +0.028 |
� | +0.027 |
aul | +0.026 |
Neg logit contributions | |
wreck | -0.017 |
them | -0.016 |
polar | -0.015 |
rock | -0.015 |
tow | -0.015 |
Token | today |
Token ID | 1909 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
� | +0.148 |
cious | +0.143 |
ages | +0.143 |
ience | +0.143 |
's | +0.140 |
Neg logit contributions | |
them | -0.100 |
wreck | -0.086 |
mate | -0.084 |
polar | -0.081 |
tow | -0.076 |
Token | � |
Token ID | 6184 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
them | +0.003 |
mate | +0.003 |
wreck | +0.003 |
polar | +0.002 |
tow | +0.002 |
Neg logit contributions | |
ages | -0.005 |
� | -0.005 |
ience | -0.005 |
cious | -0.005 |
's | -0.005 |
Token | � |
Token ID | 95 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ages | +0.012 |
's | +0.011 |
pads | +0.011 |
ience | +0.011 |
cious | +0.011 |
Neg logit contributions | |
them | -0.012 |
mate | -0.011 |
wreck | -0.011 |
tow | -0.011 |
inn | -0.011 |
Token | € |
Token ID | 26391 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
mate | +0.011 |
them | +0.011 |
room | +0.010 |
tow | +0.010 |
wreck | +0.010 |
Neg logit contributions | |
ience | -0.009 |
ages | -0.009 |
cious | -0.009 |
aul | -0.008 |
bey | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.248 |
decisions | +0.240 |
aul | +0.233 |
persever | +0.226 |
night | +0.226 |
Neg logit contributions | |
them | -0.166 |
room | -0.145 |
tow | -0.143 |
mate | -0.137 |
block | -0.136 |
Token | � |
Token ID | 250 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ages | +0.791 |
cious | +0.788 |
� | +0.783 |
's | +0.758 |
ience | +0.749 |
Neg logit contributions | |
them | -0.688 |
wreck | -0.637 |
mate | -0.622 |
polar | -0.588 |
tow | -0.574 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
them | +0.012 |
mate | +0.011 |
wreck | +0.011 |
polar | +0.011 |
inn | +0.010 |
Neg logit contributions | |
� | -0.011 |
's | -0.010 |
cious | -0.010 |
ages | -0.010 |
ience | -0.010 |
Token | small |
Token ID | 1402 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
� | +0.082 |
ages | +0.081 |
cious | +0.080 |
's | +0.079 |
ience | +0.078 |
Neg logit contributions | |
them | -0.077 |
wreck | -0.071 |
mate | -0.070 |
polar | -0.070 |
tow | -0.065 |
Token | fairy |
Token ID | 25607 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
� | +0.004 |
ages | +0.004 |
cious | +0.004 |
's | +0.004 |
ience | +0.004 |
Neg logit contributions | |
them | -0.003 |
wreck | -0.003 |
mate | -0.003 |
polar | -0.003 |
tow | -0.003 |
Token | who |
Token ID | 508 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
ages | +0.028 |
cious | +0.028 |
� | +0.027 |
aul | +0.026 |
ience | +0.026 |
Neg logit contributions | |
them | -0.022 |
mate | -0.020 |
polar | -0.019 |
wreck | -0.019 |
tow | -0.018 |
Token | other |
Token ID | 584 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
them | +0.079 |
wreck | +0.071 |
polar | +0.069 |
mate | +0.068 |
tow | +0.064 |
Neg logit contributions | |
� | -0.103 |
cious | -0.099 |
ages | -0.098 |
ience | -0.097 |
's | -0.096 |
Token | family |
Token ID | 1641 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
them | +0.088 |
polar | +0.072 |
wreck | +0.072 |
tow | +0.062 |
cubes | +0.062 |
Neg logit contributions | |
� | -0.134 |
ages | -0.129 |
ience | -0.129 |
cious | -0.127 |
aul | -0.124 |
Token | � |
Token ID | 6184 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ience | +0.161 |
� | +0.157 |
cious | +0.156 |
ages | +0.155 |
Michelle | +0.151 |
Neg logit contributions | |
them | -0.107 |
wreck | -0.089 |
mate | -0.083 |
polar | -0.083 |
tow | -0.079 |
Token | � |
Token ID | 95 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
� | +0.012 |
ages | +0.012 |
's | +0.011 |
ience | +0.011 |
cious | +0.011 |
Neg logit contributions | |
them | -0.012 |
wreck | -0.011 |
mate | -0.011 |
inn | -0.011 |
polar | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
them | +0.011 |
wreck | +0.010 |
mate | +0.010 |
inn | +0.010 |
tow | +0.010 |
Neg logit contributions | |
ience | -0.010 |
� | -0.009 |
ages | -0.009 |
's | -0.009 |
Louise | -0.009 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ience | +0.190 |
� | +0.182 |
decisions | +0.178 |
Michelle | +0.175 |
persever | +0.171 |
Neg logit contributions | |
them | -0.236 |
room | -0.205 |
wreck | -0.203 |
tow | -0.200 |
row | -0.199 |
Token | � |
Token ID | 250 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
� | +0.627 |
cious | +0.583 |
's | +0.582 |
ages | +0.581 |
ience | +0.574 |
Neg logit contributions | |
them | -0.898 |
wreck | -0.833 |
mate | -0.816 |
polar | -0.806 |
inn | -0.779 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
them | +0.012 |
wreck | +0.011 |
mate | +0.011 |
polar | +0.011 |
ramp | +0.010 |
Neg logit contributions | |
� | -0.011 |
cious | -0.010 |
's | -0.010 |
ages | -0.009 |
ience | -0.009 |
Token | dad |
Token ID | 9955 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
� | +0.086 |
's | +0.082 |
cious | +0.081 |
ages | +0.079 |
ience | +0.079 |
Neg logit contributions | |
them | -0.077 |
mate | -0.069 |
wreck | -0.068 |
inn | -0.067 |
polar | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
� | +0.117 |
cious | +0.116 |
ages | +0.115 |
ience | +0.114 |
's | +0.110 |
Neg logit contributions | |
them | -0.080 |
wreck | -0.071 |
mate | -0.069 |
polar | -0.068 |
tow | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
� | +0.026 |
cious | +0.025 |
ages | +0.025 |
's | +0.025 |
ience | +0.025 |
Neg logit contributions | |
them | -0.023 |
wreck | -0.021 |
mate | -0.021 |
polar | -0.020 |
inn | -0.019 |
Token | pieces |
Token ID | 5207 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
� | +0.011 |
's | +0.010 |
ience | +0.010 |
cious | +0.010 |
ages | +0.010 |
Neg logit contributions | |
them | -0.009 |
wreck | -0.008 |
mate | -0.008 |
polar | -0.008 |
inn | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
them | +0.048 |
wreck | +0.043 |
mate | +0.042 |
polar | +0.042 |
inn | +0.040 |
Neg logit contributions | |
� | -0.065 |
's | -0.062 |
cious | -0.061 |
ages | -0.061 |
ience | -0.061 |
Token | try |
Token ID | 1949 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
� | +0.029 |
's | +0.026 |
cious | +0.022 |
ience | +0.021 |
dedication | +0.021 |
Neg logit contributions | |
polar | -0.023 |
inn | -0.023 |
mate | -0.022 |
snowball | -0.022 |
tant | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
them | +0.120 |
wreck | +0.114 |
mate | +0.112 |
polar | +0.112 |
inn | +0.105 |
Neg logit contributions | |
� | -0.203 |
's | -0.197 |
cious | -0.190 |
ages | -0.189 |
ience | -0.188 |
Token | check |
Token ID | 2198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
� | +0.027 |
cious | +0.026 |
's | +0.026 |
ages | +0.026 |
ience | +0.025 |
Neg logit contributions | |
them | -0.015 |
wreck | -0.014 |
mate | -0.013 |
polar | -0.013 |
inn | -0.012 |
Token | mate |
Token ID | 9830 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
wreck | +0.043 |
polar | +0.042 |
them | +0.042 |
mate | +0.039 |
inn | +0.037 |
Neg logit contributions | |
� | -0.090 |
's | -0.087 |
ience | -0.085 |
ages | -0.084 |
cious | -0.084 |
Token | your |
Token ID | 534 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
them | +0.620 |
mate | +0.530 |
wreck | +0.523 |
polar | +0.494 |
inn | +0.474 |
Neg logit contributions | |
� | -0.879 |
cious | -0.842 |
ages | -0.833 |
's | -0.826 |
ience | -0.825 |
Token | opponent |
Token ID | 6125 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
them | +0.066 |
wreck | +0.061 |
mate | +0.059 |
polar | +0.058 |
inn | +0.055 |
Neg logit contributions | |
� | -0.065 |
cious | -0.062 |
ages | -0.061 |
ience | -0.061 |
's | -0.060 |
Token | ." |
Token ID | 526 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
� | +0.220 |
cious | +0.219 |
ience | +0.212 |
ages | +0.210 |
Michelle | +0.208 |
Neg logit contributions | |
them | -0.155 |
wreck | -0.130 |
mate | -0.128 |
polar | -0.115 |
match | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
them | +0.138 |
wreck | +0.121 |
mate | +0.119 |
polar | +0.116 |
inn | +0.113 |
Neg logit contributions | |
� | -0.170 |
cious | -0.165 |
ience | -0.164 |
ages | -0.162 |
's | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
� | +0.004 |
's | +0.004 |
ages | +0.004 |
cious | +0.004 |
aul | +0.003 |
Neg logit contributions | |
them | -0.005 |
wreck | -0.005 |
polar | -0.005 |
mate | -0.005 |
captain | -0.004 |
Token | ™ |
Token ID | 8151 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
Michelle | +0.134 |
ience | +0.133 |
aul | +0.133 |
Denise | +0.119 |
Louise | +0.119 |
Neg logit contributions | |
them | -0.273 |
wreck | -0.253 |
ramp | -0.253 |
mate | -0.252 |
room | -0.247 |
Token | s |
Token ID | 82 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
cious | +0.395 |
ience | +0.390 |
listens | +0.384 |
ages | +0.383 |
� | +0.382 |
Neg logit contributions | |
them | -0.334 |
mate | -0.294 |
wreck | -0.288 |
inn | -0.282 |
polar | -0.264 |
Token | King |
Token ID | 2677 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
� | +0.016 |
cious | +0.015 |
ages | +0.015 |
ience | +0.015 |
's | +0.015 |
Neg logit contributions | |
them | -0.014 |
wreck | -0.012 |
mate | -0.012 |
polar | -0.011 |
inn | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
cious | +0.133 |
ience | +0.131 |
Michelle | +0.128 |
List | +0.128 |
aul | +0.127 |
Neg logit contributions | |
them | -0.254 |
mate | -0.237 |
wreck | -0.234 |
polar | -0.219 |
match | -0.218 |
Token | check |
Token ID | 2198 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
� | +0.024 |
's | +0.022 |
pays | +0.020 |
ience | +0.019 |
ages | +0.019 |
Neg logit contributions | |
polar | -0.019 |
them | -0.019 |
wreck | -0.018 |
inn | -0.018 |
mate | -0.018 |
Token | mate |
Token ID | 9830 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
them | +0.051 |
wreck | +0.047 |
mate | +0.046 |
polar | +0.045 |
inn | +0.043 |
Neg logit contributions | |
� | -0.074 |
's | -0.070 |
cious | -0.069 |
ages | -0.069 |
ience | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-03 |
Pos logit contributions | |
them | +0.633 |
wreck | +0.563 |
mate | +0.558 |
polar | +0.540 |
inn | +0.517 |
Neg logit contributions | |
� | -0.840 |
cious | -0.799 |
's | -0.798 |
ages | -0.793 |
ience | -0.787 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
� | +0.000 |
's | +0.000 |
ages | +0.000 |
cious | +0.000 |
ience | +0.000 |
Neg logit contributions | |
them | -0.000 |
mate | -0.000 |
wreck | -0.000 |
polar | -0.000 |
inn | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
� | +0.008 |
's | +0.007 |
ages | +0.006 |
cious | +0.005 |
aul | +0.005 |
Neg logit contributions | |
wreck | -0.014 |
captain | -0.013 |
polar | -0.013 |
mate | -0.013 |
them | -0.013 |
Token | The |
Token ID | 464 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
� | +0.013 |
's | +0.011 |
ages | +0.010 |
cious | +0.009 |
appointed | +0.009 |
Neg logit contributions | |
them | -0.009 |
polar | -0.009 |
mate | -0.008 |
wreck | -0.008 |
detector | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
cious | +0.071 |
ages | +0.071 |
� | +0.070 |
ience | +0.068 |
aul | +0.068 |
Neg logit contributions | |
them | -0.051 |
wreck | -0.049 |
mate | -0.046 |
polar | -0.046 |
tow | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ience | +0.076 |
� | +0.076 |
cious | +0.075 |
ages | +0.075 |
aul | +0.071 |
Neg logit contributions | |
them | -0.048 |
mate | -0.040 |
wreck | -0.039 |
polar | -0.039 |
inn | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ience | +0.001 |
cious | +0.001 |
ages | +0.001 |
� | +0.001 |
aul | +0.001 |
Neg logit contributions | |
them | -0.001 |
inn | -0.001 |
mate | -0.001 |
his | -0.001 |
tow | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
� | +0.011 |
's | +0.010 |
cious | +0.010 |
ages | +0.010 |
ience | +0.010 |
Neg logit contributions | |
them | -0.011 |
wreck | -0.010 |
polar | -0.010 |
mate | -0.010 |
inn | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
ages | +0.012 |
cious | +0.012 |
ience | +0.011 |
aul | +0.011 |
listens | +0.011 |
Neg logit contributions | |
them | -0.010 |
mate | -0.008 |
inn | -0.008 |
wreck | -0.007 |
tow | -0.007 |
Token | Check |
Token ID | 9787 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
them | +0.046 |
mate | +0.040 |
wreck | +0.039 |
polar | +0.038 |
inn | +0.037 |
Neg logit contributions | |
� | -0.069 |
ages | -0.068 |
ience | -0.067 |
cious | -0.067 |
's | -0.067 |
Token | mate |
Token ID | 9830 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
them | +0.062 |
wreck | +0.060 |
polar | +0.058 |
tow | +0.055 |
inn | +0.053 |
Neg logit contributions | |
� | -0.087 |
's | -0.083 |
ages | -0.083 |
cious | -0.082 |
ience | -0.081 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
them | +0.462 |
mate | +0.394 |
wreck | +0.362 |
polar | +0.322 |
control | +0.305 |
Neg logit contributions | |
� | -0.977 |
cious | -0.963 |
aul | -0.941 |
ages | -0.941 |
ience | -0.941 |
Token | declared |
Token ID | 6875 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
them | +0.295 |
his | +0.233 |
match | +0.216 |
inn | +0.215 |
mate | +0.211 |
Neg logit contributions | |
cious | -0.257 |
aul | -0.251 |
ages | -0.248 |
lette | -0.244 |
decisions | -0.241 |
Token | Elsa |
Token ID | 19226 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
them | +0.142 |
his | +0.114 |
mate | +0.109 |
polar | +0.105 |
inn | +0.101 |
Neg logit contributions | |
cious | -0.172 |
ages | -0.172 |
ience | -0.171 |
� | -0.169 |
aul | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | -5.66e-03 |
Pos logit contributions | |
ience | +0.231 |
aul | +0.223 |
Michelle | +0.221 |
listens | +0.219 |
List | +0.218 |
Neg logit contributions | |
them | -0.104 |
wreck | -0.076 |
polar | -0.075 |
mate | -0.075 |
his | -0.075 |
Token | Her |
Token ID | 2332 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
them | +0.000 |
mate | +0.000 |
inn | +0.000 |
tow | +0.000 |
his | +0.000 |
Neg logit contributions | |
ience | -0.000 |
cious | -0.000 |
ages | -0.000 |
� | -0.000 |
listens | -0.000 |
Token | enough |
Token ID | 1576 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
cious | +0.290 |
ages | +0.282 |
� | +0.277 |
ience | +0.274 |
aul | +0.266 |
Neg logit contributions | |
them | -0.186 |
mate | -0.147 |
wreck | -0.146 |
polar | -0.135 |
control | -0.129 |
Token | to |
Token ID | 284 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
them | +0.032 |
wreck | +0.027 |
mate | +0.026 |
polar | +0.025 |
tow | +0.024 |
Neg logit contributions | |
� | -0.047 |
cious | -0.047 |
ages | -0.046 |
's | -0.045 |
ience | -0.045 |
Token | find |
Token ID | 1064 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
� | +0.046 |
's | +0.044 |
cious | +0.044 |
ages | +0.043 |
ience | +0.043 |
Neg logit contributions | |
them | -0.031 |
wreck | -0.028 |
mate | -0.027 |
polar | -0.026 |
inn | -0.025 |
Token | your |
Token ID | 534 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
them | +0.066 |
mate | +0.052 |
wreck | +0.052 |
polar | +0.050 |
his | +0.048 |
Neg logit contributions | |
� | -0.070 |
cious | -0.070 |
ages | -0.069 |
ience | -0.067 |
aul | -0.065 |
Token | soul |
Token ID | 5848 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
them | +0.048 |
wreck | +0.044 |
polar | +0.041 |
mate | +0.041 |
rock | +0.039 |
Neg logit contributions | |
� | -0.055 |
cious | -0.054 |
ages | -0.053 |
ience | -0.052 |
's | -0.051 |
Token | mate |
Token ID | 9830 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
cious | +0.468 |
� | +0.462 |
ages | +0.458 |
ience | +0.452 |
aul | +0.445 |
Neg logit contributions | |
them | -0.319 |
mate | -0.258 |
wreck | -0.254 |
polar | -0.234 |
control | -0.230 |
Token | , |
Token ID | 11 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
them | +0.636 |
mate | +0.538 |
wreck | +0.477 |
his | +0.457 |
control | +0.453 |
Neg logit contributions | |
cious | -0.808 |
ages | -0.799 |
� | -0.794 |
aul | -0.791 |
ience | -0.771 |
Token | don |
Token ID | 836 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
cious | +0.027 |
ages | +0.026 |
ience | +0.025 |
aul | +0.024 |
assy | +0.024 |
Neg logit contributions | |
them | -0.026 |
mate | -0.021 |
wreck | -0.021 |
his | -0.020 |
match | -0.020 |
Token | 't |
Token ID | 470 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
cious | +0.235 |
ages | +0.230 |
� | +0.229 |
ience | +0.226 |
's | +0.223 |
Neg logit contributions | |
them | -0.127 |
wreck | -0.104 |
mate | -0.102 |
polar | -0.093 |
inn | -0.091 |
Token | be |
Token ID | 307 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
them | +0.232 |
wreck | +0.209 |
mate | +0.202 |
polar | +0.198 |
inn | +0.186 |
Neg logit contributions | |
� | -0.309 |
cious | -0.299 |
ages | -0.298 |
ience | -0.295 |
's | -0.294 |
Token | afraid |
Token ID | 7787 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
them | +0.097 |
wreck | +0.088 |
polar | +0.085 |
mate | +0.084 |
inn | +0.080 |
Neg logit contributions | |
� | -0.089 |
cious | -0.085 |
ages | -0.084 |
ience | -0.084 |
's | -0.083 |
Token | popular |
Token ID | 2968 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
� | +0.149 |
cious | +0.141 |
ages | +0.140 |
ience | +0.139 |
's | +0.137 |
Neg logit contributions | |
them | -0.088 |
wreck | -0.081 |
polar | -0.075 |
mate | -0.072 |
tow | -0.069 |
Token | that |
Token ID | 326 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
them | +0.093 |
wreck | +0.083 |
mate | +0.082 |
polar | +0.081 |
inn | +0.080 |
Neg logit contributions | |
� | -0.120 |
's | -0.115 |
cious | -0.113 |
ages | -0.112 |
ience | -0.111 |
Token | everyone |
Token ID | 2506 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
them | +0.070 |
wreck | +0.061 |
mate | +0.060 |
polar | +0.059 |
tow | +0.055 |
Neg logit contributions | |
cious | -0.075 |
� | -0.074 |
ages | -0.074 |
ience | -0.073 |
's | -0.070 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
cious | +0.147 |
ages | +0.145 |
� | +0.144 |
ience | +0.139 |
aul | +0.136 |
Neg logit contributions | |
them | -0.143 |
wreck | -0.128 |
mate | -0.121 |
polar | -0.118 |
match | -0.110 |
Token | a |
Token ID | 257 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
them | +0.044 |
mate | +0.033 |
wreck | +0.033 |
his | +0.031 |
polar | +0.030 |
Neg logit contributions | |
cious | -0.062 |
ience | -0.062 |
ages | -0.061 |
� | -0.061 |
aul | -0.058 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.35e+00 |
Pos logit contributions | |
� | +0.055 |
's | +0.052 |
cious | +0.051 |
ience | +0.050 |
ages | +0.050 |
Neg logit contributions | |
them | -0.043 |
mate | -0.038 |
wreck | -0.038 |
polar | -0.037 |
inn | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
polar | +0.516 |
them | +0.506 |
wreck | +0.495 |
ramp | +0.489 |
snowball | +0.488 |
Neg logit contributions | |
� | -0.740 |
's | -0.682 |
ages | -0.612 |
cious | -0.607 |
ience | -0.578 |
Token | the |
Token ID | 262 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
them | +0.205 |
wreck | +0.201 |
mate | +0.199 |
inn | +0.196 |
polar | +0.192 |
Neg logit contributions | |
� | -0.234 |
's | -0.219 |
cious | -0.209 |
ience | -0.209 |
ages | -0.208 |
Token | same |
Token ID | 976 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
� | +0.002 |
ages | +0.002 |
cious | +0.002 |
's | +0.002 |
ience | +0.002 |
Neg logit contributions | |
them | -0.002 |
wreck | -0.002 |
mate | -0.002 |
polar | -0.002 |
tow | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
them | +0.113 |
wreck | +0.103 |
polar | +0.101 |
mate | +0.101 |
inn | +0.100 |
Neg logit contributions | |
� | -0.148 |
's | -0.141 |
cious | -0.135 |
ience | -0.133 |
ages | -0.133 |
Token | |
Token ID | 220 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
them | +0.007 |
wreck | +0.006 |
mate | +0.006 |
polar | +0.006 |
inn | +0.006 |
Neg logit contributions | |
ages | -0.007 |
cious | -0.007 |
ience | -0.006 |
� | -0.006 |
's | -0.006 |
Token | I |
Token ID | 314 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
them | +0.044 |
wreck | +0.038 |
mate | +0.038 |
polar | +0.038 |
inn | +0.036 |
Neg logit contributions | |
cious | -0.045 |
ages | -0.045 |
ience | -0.045 |
� | -0.044 |
's | -0.043 |
Token | could |
Token ID | 714 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
� | +0.148 |
's | +0.135 |
ience | +0.128 |
ages | +0.122 |
cious | +0.122 |
Neg logit contributions | |
them | -0.134 |
mate | -0.125 |
wreck | -0.123 |
polar | -0.121 |
inn | -0.117 |
Token | use |
Token ID | 779 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
them | +0.079 |
mate | +0.076 |
inn | +0.074 |
polar | +0.073 |
wreck | +0.072 |
Neg logit contributions | |
� | -0.120 |
's | -0.111 |
ages | -0.101 |
cious | -0.100 |
ience | -0.100 |
Token | an |
Token ID | 281 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
mate | +0.186 |
them | +0.185 |
polar | +0.184 |
wreck | +0.183 |
inn | +0.175 |
Neg logit contributions | |
� | -0.252 |
's | -0.237 |
ience | -0.225 |
ages | -0.218 |
cious | -0.214 |
Token | extra |
Token ID | 3131 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
� | +0.122 |
's | +0.112 |
ience | +0.108 |
ages | +0.104 |
cious | +0.102 |
Neg logit contributions | |
them | -0.114 |
mate | -0.103 |
polar | -0.101 |
wreck | -0.100 |
inn | -0.095 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
them | +0.143 |
wreck | +0.128 |
mate | +0.126 |
polar | +0.123 |
inn | +0.118 |
Neg logit contributions | |
� | -0.187 |
's | -0.177 |
cious | -0.177 |
ages | -0.176 |
ience | -0.174 |
Token | of |
Token ID | 286 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
polar | +0.494 |
them | +0.471 |
wreck | +0.467 |
snowball | +0.448 |
ramp | +0.431 |
Neg logit contributions | |
� | -0.770 |
's | -0.710 |
ages | -0.646 |
cious | -0.631 |
ience | -0.629 |
Token | hands |
Token ID | 2832 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
wreck | +0.195 |
mate | +0.190 |
them | +0.184 |
inn | +0.181 |
polar | +0.177 |
Neg logit contributions | |
� | -0.247 |
's | -0.233 |
ience | -0.220 |
cious | -0.219 |
ages | -0.216 |
Token | ." |
Token ID | 526 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
� | +0.204 |
cious | +0.195 |
's | +0.194 |
ages | +0.193 |
ience | +0.192 |
Neg logit contributions | |
them | -0.153 |
wreck | -0.136 |
mate | -0.134 |
polar | -0.131 |
inn | -0.126 |
Token | The |
Token ID | 383 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
them | +0.137 |
mate | +0.110 |
polar | +0.109 |
inn | +0.108 |
wreck | +0.107 |
Neg logit contributions | |
cious | -0.174 |
ience | -0.173 |
ages | -0.170 |
� | -0.163 |
listens | -0.160 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
� | +0.138 |
's | +0.131 |
cious | +0.131 |
ages | +0.130 |
ience | +0.129 |
Neg logit contributions | |
them | -0.107 |
wreck | -0.097 |
mate | -0.095 |
polar | -0.093 |
inn | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ience | +0.183 |
cious | +0.183 |
� | +0.182 |
ages | +0.180 |
aul | +0.178 |
Neg logit contributions | |
them | -0.121 |
mate | -0.102 |
control | -0.084 |
wreck | -0.083 |
tow | -0.080 |
Token | make |
Token ID | 787 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
them | +0.017 |
wreck | +0.015 |
polar | +0.014 |
mate | +0.014 |
tow | +0.013 |
Neg logit contributions | |
� | -0.020 |
cious | -0.020 |
ages | -0.019 |
ience | -0.019 |
's | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
them | +0.188 |
wreck | +0.170 |
mate | +0.169 |
polar | +0.164 |
inn | +0.158 |
Neg logit contributions | |
� | -0.260 |
's | -0.248 |
cious | -0.246 |
ages | -0.245 |
ience | -0.242 |
Token | go |
Token ID | 467 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
them | +0.119 |
mate | +0.108 |
wreck | +0.106 |
polar | +0.104 |
inn | +0.101 |
Neg logit contributions | |
� | -0.166 |
's | -0.159 |
ages | -0.153 |
cious | -0.153 |
ience | -0.151 |
Token | v |
Token ID | 410 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
� | +0.056 |
's | +0.053 |
ience | +0.049 |
ages | +0.048 |
cious | +0.047 |
Neg logit contributions | |
mate | -0.040 |
polar | -0.039 |
them | -0.038 |
wreck | -0.037 |
tow | -0.036 |
Token | room |
Token ID | 3823 |
Feature activation | -9.24e+00 |
Pos logit contributions | |
them | +0.186 |
polar | +0.161 |
wreck | +0.152 |
mate | +0.138 |
tow | +0.137 |
Neg logit contributions | |
ages | -0.449 |
� | -0.446 |
's | -0.437 |
cious | -0.418 |
aul | -0.414 |
Token | v |
Token ID | 410 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
them | +0.503 |
wreck | +0.455 |
mate | +0.449 |
polar | +0.442 |
inn | +0.423 |
Neg logit contributions | |
� | -0.697 |
's | -0.667 |
ages | -0.653 |
cious | -0.649 |
ience | -0.644 |
Token | room |
Token ID | 3823 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
them | +0.208 |
polar | +0.187 |
wreck | +0.173 |
tow | +0.163 |
mate | +0.159 |
Neg logit contributions | |
ages | -0.409 |
� | -0.400 |
's | -0.397 |
cious | -0.370 |
aul | -0.367 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
them | +0.502 |
wreck | +0.458 |
polar | +0.451 |
mate | +0.451 |
inn | +0.429 |
Neg logit contributions | |
� | -0.686 |
's | -0.661 |
ages | -0.641 |
cious | -0.629 |
ience | -0.626 |
Token | When |
Token ID | 1649 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
them | +0.009 |
wreck | +0.008 |
mate | +0.008 |
polar | +0.007 |
inn | +0.007 |
Neg logit contributions | |
� | -0.009 |
's | -0.009 |
cious | -0.009 |
ages | -0.009 |
ience | -0.009 |
Token | they |
Token ID | 484 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
� | +0.091 |
cious | +0.087 |
's | +0.087 |
ages | +0.086 |
ience | +0.086 |
Neg logit contributions | |
them | -0.069 |
wreck | -0.062 |
mate | -0.061 |
polar | -0.059 |
inn | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
cious | +0.018 |
ience | +0.018 |
ages | +0.017 |
� | +0.017 |
ita | +0.017 |
Neg logit contributions | |
them | -0.012 |
his | -0.010 |
wreck | -0.009 |
splash | -0.009 |
polar | -0.009 |
Token | v |
Token ID | 410 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
them | +0.025 |
wreck | +0.022 |
mate | +0.022 |
polar | +0.021 |
inn | +0.020 |
Neg logit contributions | |
� | -0.030 |
cious | -0.029 |
's | -0.029 |
ages | -0.029 |
ience | -0.028 |
Token | room |
Token ID | 3823 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
them | +0.286 |
polar | +0.261 |
wreck | +0.250 |
mate | +0.237 |
tow | +0.237 |
Neg logit contributions | |
ages | -0.399 |
's | -0.386 |
� | -0.381 |
cious | -0.367 |
aul | -0.361 |
Token | , |
Token ID | 11 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
them | +0.542 |
mate | +0.502 |
wreck | +0.500 |
polar | +0.488 |
inn | +0.481 |
Neg logit contributions | |
� | -0.695 |
's | -0.682 |
ages | -0.651 |
cious | -0.641 |
ience | -0.636 |
Token | v |
Token ID | 410 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
them | +0.011 |
mate | +0.011 |
inn | +0.010 |
wreck | +0.010 |
polar | +0.010 |
Neg logit contributions | |
� | -0.019 |
's | -0.018 |
cious | -0.017 |
ages | -0.017 |
ience | -0.017 |
Token | room |
Token ID | 3823 |
Feature activation | -9.24e+00 |
Pos logit contributions | |
them | +0.205 |
polar | +0.194 |
wreck | +0.174 |
tow | +0.170 |
paddle | +0.164 |
Neg logit contributions | |
ages | -0.436 |
's | -0.416 |
� | -0.397 |
cious | -0.392 |
aul | -0.387 |
Token | ! |
Token ID | 0 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
them | +0.533 |
wreck | +0.508 |
mate | +0.507 |
polar | +0.494 |
inn | +0.488 |
Neg logit contributions | |
� | -0.657 |
's | -0.653 |
ages | -0.617 |
cious | -0.599 |
ience | -0.589 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
them | +0.102 |
wreck | +0.095 |
mate | +0.093 |
polar | +0.091 |
inn | +0.088 |
Neg logit contributions | |
� | -0.096 |
's | -0.089 |
cious | -0.085 |
ages | -0.085 |
ience | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
wreck | +0.002 |
mate | +0.002 |
polar | +0.002 |
them | +0.002 |
captain | +0.002 |
Neg logit contributions | |
� | -0.001 |
's | -0.001 |
Louise | -0.001 |
List | -0.001 |
cious | -0.001 |
Token | They |
Token ID | 2990 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
� | +0.002 |
's | +0.002 |
cious | +0.002 |
ages | +0.002 |
ience | +0.002 |
Neg logit contributions | |
them | -0.002 |
wreck | -0.002 |
polar | -0.002 |
mate | -0.002 |
inn | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
them | +0.085 |
mate | +0.084 |
inn | +0.080 |
polar | +0.079 |
wreck | +0.079 |
Neg logit contributions | |
� | -0.099 |
's | -0.093 |
ience | -0.085 |
cious | -0.084 |
listens | -0.081 |
Token | makes |
Token ID | 1838 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
cious | +0.025 |
ages | +0.024 |
� | +0.023 |
ience | +0.022 |
Michelle | +0.022 |
Neg logit contributions | |
them | -0.031 |
wreck | -0.027 |
polar | -0.026 |
mate | -0.025 |
tow | -0.025 |
Token | v |
Token ID | 410 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
� | +0.202 |
cious | +0.198 |
ages | +0.193 |
ience | +0.193 |
's | +0.190 |
Neg logit contributions | |
them | -0.140 |
wreck | -0.119 |
mate | -0.115 |
polar | -0.112 |
inn | -0.103 |
Token | room |
Token ID | 3823 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
them | +0.237 |
polar | +0.215 |
wreck | +0.209 |
mate | +0.200 |
tow | +0.191 |
Neg logit contributions | |
ages | -0.439 |
� | -0.435 |
's | -0.429 |
cious | -0.410 |
aul | -0.398 |
Token | - |
Token ID | 12 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
them | +0.502 |
wreck | +0.451 |
mate | +0.446 |
polar | +0.435 |
inn | +0.416 |
Neg logit contributions | |
� | -0.736 |
's | -0.706 |
ages | -0.696 |
cious | -0.694 |
ience | -0.685 |
Token | v |
Token ID | 85 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
� | +0.026 |
ages | +0.025 |
's | +0.025 |
cious | +0.024 |
ience | +0.023 |
Neg logit contributions | |
them | -0.022 |
mate | -0.020 |
polar | -0.020 |
wreck | -0.020 |
inn | -0.019 |
Token | room |
Token ID | 3823 |
Feature activation | -9.24e+00 |
Pos logit contributions | |
polar | +0.187 |
them | +0.176 |
wreck | +0.174 |
paddle | +0.166 |
tow | +0.162 |
Neg logit contributions | |
's | -0.470 |
ages | -0.459 |
� | -0.432 |
ups | -0.409 |
thoughts | -0.395 |
Token | sounds |
Token ID | 5238 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
them | +0.479 |
wreck | +0.430 |
mate | +0.428 |
polar | +0.416 |
inn | +0.400 |
Neg logit contributions | |
� | -0.718 |
's | -0.691 |
ages | -0.680 |
cious | -0.676 |
ience | -0.665 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
� | +0.390 |
's | +0.373 |
ages | +0.355 |
cious | +0.350 |
ience | +0.339 |
Neg logit contributions | |
them | -0.308 |
mate | -0.294 |
wreck | -0.291 |
polar | -0.289 |
tow | -0.275 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
them | +0.012 |
wreck | +0.011 |
mate | +0.011 |
polar | +0.011 |
inn | +0.010 |
Neg logit contributions | |
� | -0.013 |
cious | -0.012 |
's | -0.012 |
ages | -0.012 |
ience | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
� | +0.002 |
's | +0.001 |
List | +0.001 |
ages | +0.001 |
Louise | +0.001 |
Neg logit contributions | |
wreck | -0.002 |
mate | -0.002 |
polar | -0.002 |
them | -0.002 |
captain | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
� | +0.005 |
's | +0.004 |
cious | +0.004 |
ages | +0.004 |
ience | +0.004 |
Neg logit contributions | |
them | -0.004 |
wreck | -0.003 |
polar | -0.003 |
mate | -0.003 |
inn | -0.003 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
mate | +0.178 |
inn | +0.178 |
them | +0.171 |
polar | +0.162 |
Mike | +0.152 |
Neg logit contributions | |
's | -0.306 |
� | -0.277 |
thoughts | -0.232 |
listens | -0.229 |
aul | -0.221 |
Token | back |
Token ID | 736 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
them | +0.175 |
mate | +0.148 |
wreck | +0.147 |
polar | +0.146 |
inn | +0.136 |
Neg logit contributions | |
cious | -0.197 |
� | -0.197 |
ience | -0.192 |
ages | -0.191 |
aul | -0.185 |
Token | to |
Token ID | 284 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
them | +0.059 |
wreck | +0.054 |
mate | +0.053 |
polar | +0.052 |
inn | +0.050 |
Neg logit contributions | |
� | -0.080 |
's | -0.076 |
cious | -0.075 |
ages | -0.075 |
ience | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
them | +0.006 |
wreck | +0.006 |
mate | +0.006 |
polar | +0.005 |
inn | +0.005 |
Neg logit contributions | |
� | -0.011 |
's | -0.011 |
cious | -0.011 |
ages | -0.010 |
ience | -0.010 |
Token | play |
Token ID | 711 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
them | +0.016 |
mate | +0.014 |
wreck | +0.014 |
inn | +0.014 |
polar | +0.014 |
Neg logit contributions | |
� | -0.021 |
's | -0.020 |
cious | -0.020 |
ages | -0.019 |
ience | -0.019 |
Token | room |
Token ID | 3823 |
Feature activation | -9.24e+00 |
Pos logit contributions | |
wreck | +0.183 |
polar | +0.182 |
them | +0.166 |
tow | +0.161 |
paddle | +0.160 |
Neg logit contributions | |
's | -0.244 |
� | -0.235 |
ages | -0.191 |
cious | -0.187 |
ience | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
them | +0.516 |
wreck | +0.470 |
mate | +0.465 |
polar | +0.457 |
inn | +0.444 |
Neg logit contributions | |
� | -0.681 |
's | -0.659 |
ages | -0.631 |
ience | -0.628 |
cious | -0.626 |
Token | She |
Token ID | 1375 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
them | +0.016 |
wreck | +0.014 |
mate | +0.014 |
polar | +0.014 |
inn | +0.013 |
Neg logit contributions | |
� | -0.014 |
cious | -0.013 |
ages | -0.013 |
ience | -0.013 |
's | -0.013 |
Token | made |
Token ID | 925 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
� | +0.026 |
's | +0.024 |
cious | +0.024 |
ages | +0.024 |
ience | +0.024 |
Neg logit contributions | |
them | -0.028 |
wreck | -0.026 |
mate | -0.025 |
polar | -0.025 |
inn | -0.024 |
Token | Ben |
Token ID | 3932 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
mate | +0.046 |
wreck | +0.045 |
them | +0.044 |
polar | +0.043 |
inn | +0.043 |
Neg logit contributions | |
� | -0.051 |
's | -0.050 |
ages | -0.047 |
cious | -0.045 |
ience | -0.044 |
Token | look |
Token ID | 804 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
� | +0.062 |
cious | +0.059 |
ience | +0.059 |
's | +0.059 |
ages | +0.059 |
Neg logit contributions | |
them | -0.054 |
wreck | -0.049 |
mate | -0.048 |
polar | -0.048 |
inn | -0.045 |
Token | Now |
Token ID | 2735 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
them | +0.005 |
wreck | +0.004 |
mate | +0.004 |
tow | +0.004 |
polar | +0.004 |
Neg logit contributions | |
cious | -0.012 |
ience | -0.012 |
� | -0.012 |
ages | -0.012 |
's | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
them | +0.050 |
wreck | +0.044 |
mate | +0.043 |
polar | +0.042 |
inn | +0.039 |
Neg logit contributions | |
� | -0.078 |
cious | -0.075 |
ages | -0.075 |
ience | -0.075 |
's | -0.074 |
Token | had |
Token ID | 550 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
� | +0.016 |
cious | +0.015 |
ages | +0.015 |
's | +0.015 |
ience | +0.015 |
Neg logit contributions | |
them | -0.017 |
wreck | -0.015 |
mate | -0.015 |
polar | -0.015 |
inn | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
� | +0.108 |
cious | +0.103 |
ages | +0.103 |
ience | +0.102 |
's | +0.102 |
Neg logit contributions | |
them | -0.083 |
wreck | -0.072 |
mate | -0.070 |
polar | -0.070 |
inn | -0.066 |
Token | great |
Token ID | 1049 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
� | +0.067 |
's | +0.063 |
ience | +0.057 |
cious | +0.056 |
pays | +0.053 |
Neg logit contributions | |
them | -0.065 |
mate | -0.060 |
inn | -0.057 |
wreck | -0.056 |
polar | -0.055 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
them | +0.108 |
mate | +0.099 |
wreck | +0.097 |
polar | +0.094 |
inn | +0.090 |
Neg logit contributions | |
� | -0.105 |
's | -0.100 |
ages | -0.094 |
cious | -0.093 |
ience | -0.089 |
Token | of |
Token ID | 286 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
them | +0.494 |
polar | +0.469 |
wreck | +0.467 |
snowball | +0.447 |
ramp | +0.442 |
Neg logit contributions | |
� | -0.741 |
's | -0.698 |
cious | -0.627 |
ages | -0.625 |
ience | -0.592 |
Token | pants |
Token ID | 12581 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
mate | +0.218 |
wreck | +0.206 |
them | +0.195 |
inn | +0.195 |
ramp | +0.193 |
Neg logit contributions | |
� | -0.218 |
's | -0.208 |
ages | -0.185 |
thoughts | -0.184 |
ience | -0.176 |
Token | to |
Token ID | 284 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
them | +0.062 |
wreck | +0.057 |
polar | +0.056 |
mate | +0.056 |
inn | +0.053 |
Neg logit contributions | |
� | -0.077 |
's | -0.073 |
ages | -0.072 |
cious | -0.071 |
ience | -0.069 |
Token | show |
Token ID | 905 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
� | +0.022 |
's | +0.020 |
cious | +0.017 |
ages | +0.016 |
Michelle | +0.016 |
Neg logit contributions | |
snowball | -0.018 |
wreck | -0.018 |
inn | -0.018 |
tant | -0.018 |
mate | -0.018 |
Token | off |
Token ID | 572 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
them | +0.129 |
wreck | +0.118 |
mate | +0.112 |
polar | +0.111 |
inn | +0.105 |
Neg logit contributions | |
� | -0.349 |
's | -0.338 |
ages | -0.332 |
cious | -0.331 |
ience | -0.327 |
Token | sure |
Token ID | 1654 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
them | +0.040 |
wreck | +0.031 |
polar | +0.031 |
mate | +0.031 |
inn | +0.028 |
Neg logit contributions | |
� | -0.062 |
cious | -0.061 |
ience | -0.060 |
ages | -0.060 |
's | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
� | +0.164 |
cious | +0.163 |
ages | +0.159 |
ience | +0.159 |
's | +0.154 |
Neg logit contributions | |
them | -0.129 |
wreck | -0.110 |
mate | -0.107 |
polar | -0.102 |
tow | -0.099 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
� | +0.025 |
's | +0.022 |
Michelle | +0.021 |
cious | +0.020 |
ages | +0.020 |
Neg logit contributions | |
them | -0.019 |
inn | -0.018 |
mate | -0.018 |
wreck | -0.017 |
polar | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
them | +0.074 |
wreck | +0.060 |
mate | +0.058 |
polar | +0.057 |
inn | +0.053 |
Neg logit contributions | |
� | -0.140 |
cious | -0.135 |
ages | -0.135 |
ience | -0.134 |
's | -0.134 |
Token | extra |
Token ID | 3131 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
� | +0.006 |
cious | +0.006 |
ages | +0.006 |
's | +0.006 |
ience | +0.006 |
Neg logit contributions | |
them | -0.004 |
wreck | -0.004 |
mate | -0.003 |
polar | -0.003 |
inn | -0.003 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
them | +0.130 |
wreck | +0.119 |
polar | +0.113 |
mate | +0.112 |
inn | +0.105 |
Neg logit contributions | |
� | -0.178 |
cious | -0.172 |
ience | -0.171 |
's | -0.169 |
ages | -0.168 |
Token | of |
Token ID | 286 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
them | +0.444 |
wreck | +0.388 |
mate | +0.384 |
polar | +0.368 |
inn | +0.351 |
Neg logit contributions | |
� | -0.744 |
cious | -0.715 |
's | -0.711 |
ages | -0.711 |
ience | -0.706 |
Token | pants |
Token ID | 12581 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
mate | +0.192 |
wreck | +0.182 |
inn | +0.182 |
them | +0.182 |
polar | +0.170 |
Neg logit contributions | |
� | -0.235 |
's | -0.221 |
ience | -0.216 |
ages | -0.210 |
cious | -0.209 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
them | +0.059 |
wreck | +0.052 |
mate | +0.051 |
polar | +0.049 |
inn | +0.047 |
Neg logit contributions | |
� | -0.079 |
cious | -0.076 |
ience | -0.075 |
ages | -0.075 |
's | -0.075 |
Token | just |
Token ID | 655 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
cious | +0.008 |
� | +0.008 |
ages | +0.008 |
ience | +0.008 |
aul | +0.008 |
Neg logit contributions | |
them | -0.006 |
wreck | -0.005 |
polar | -0.005 |
mate | -0.005 |
tow | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
them | +0.032 |
wreck | +0.025 |
his | +0.024 |
polar | +0.024 |
control | +0.023 |
Neg logit contributions | |
ages | -0.055 |
cious | -0.054 |
ience | -0.053 |
� | -0.053 |
aul | -0.052 |
Token | explore |
Token ID | 7301 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
� | +0.029 |
's | +0.027 |
cious | +0.027 |
ages | +0.027 |
ience | +0.025 |
Neg logit contributions | |
them | -0.016 |
mate | -0.014 |
wreck | -0.014 |
inn | -0.013 |
polar | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
� | +0.252 |
's | +0.241 |
cious | +0.236 |
ages | +0.234 |
ience | +0.233 |
Neg logit contributions | |
them | -0.176 |
wreck | -0.160 |
mate | -0.159 |
polar | -0.155 |
inn | -0.149 |
Token | She |
Token ID | 1375 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
them | +0.008 |
wreck | +0.007 |
mate | +0.007 |
tow | +0.007 |
inn | +0.007 |
Neg logit contributions | |
ience | -0.011 |
ages | -0.011 |
cious | -0.011 |
� | -0.011 |
's | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
� | +0.031 |
ages | +0.030 |
cious | +0.030 |
ience | +0.029 |
's | +0.029 |
Neg logit contributions | |
them | -0.028 |
wreck | -0.025 |
polar | -0.025 |
mate | -0.024 |
inn | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
ience | +0.144 |
aul | +0.129 |
ccoli | +0.128 |
ages | +0.127 |
ica | +0.127 |
Neg logit contributions | |
them | -0.064 |
his | -0.047 |
block | -0.039 |
snowball | -0.037 |
lot | -0.037 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
� | +0.076 |
's | +0.073 |
cious | +0.072 |
ages | +0.070 |
ience | +0.070 |
Neg logit contributions | |
them | -0.053 |
mate | -0.046 |
wreck | -0.045 |
polar | -0.043 |
inn | -0.043 |
Token | of |
Token ID | 286 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
them | +0.457 |
polar | +0.441 |
wreck | +0.435 |
ramp | +0.406 |
snowball | +0.403 |
Neg logit contributions | |
� | -0.768 |
's | -0.734 |
cious | -0.681 |
ages | -0.678 |
ience | -0.627 |
Token | sunglasses |
Token ID | 36251 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
wreck | +0.214 |
them | +0.207 |
mate | +0.207 |
polar | +0.198 |
ramp | +0.193 |
Neg logit contributions | |
� | -0.213 |
's | -0.210 |
ages | -0.198 |
cious | -0.196 |
thoughts | -0.186 |
Token | with |
Token ID | 351 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
� | +0.202 |
cious | +0.197 |
ience | +0.197 |
ages | +0.193 |
's | +0.189 |
Neg logit contributions | |
them | -0.138 |
wreck | -0.119 |
mate | -0.118 |
polar | -0.110 |
inn | -0.109 |
Token | her |
Token ID | 607 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
� | +0.072 |
's | +0.069 |
cious | +0.065 |
ages | +0.062 |
ience | +0.058 |
Neg logit contributions | |
wreck | -0.066 |
mate | -0.063 |
ramp | -0.063 |
polar | -0.060 |
inn | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
them | +0.077 |
wreck | +0.072 |
mate | +0.070 |
polar | +0.070 |
inn | +0.067 |
Neg logit contributions | |
� | -0.083 |
's | -0.081 |
cious | -0.078 |
ages | -0.078 |
ience | -0.075 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
� | +0.005 |
's | +0.005 |
cious | +0.005 |
ages | +0.005 |
ience | +0.005 |
Neg logit contributions | |
them | -0.005 |
wreck | -0.005 |
mate | -0.005 |
polar | -0.005 |
inn | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
them | +0.042 |
row | +0.031 |
block | +0.028 |
load | +0.025 |
stuffed | +0.025 |
Neg logit contributions | |
decisions | -0.158 |
ience | -0.148 |
ages | -0.147 |
List | -0.146 |
prayers | -0.145 |
Token | a |
Token ID | 257 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
them | +0.240 |
wreck | +0.227 |
mate | +0.227 |
polar | +0.218 |
inn | +0.216 |
Neg logit contributions | |
� | -0.251 |
's | -0.240 |
cious | -0.234 |
ages | -0.233 |
ience | -0.229 |
Token | bright |
Token ID | 6016 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
� | +0.069 |
's | +0.065 |
cious | +0.061 |
ience | +0.059 |
poem | +0.056 |
Neg logit contributions | |
them | -0.063 |
inn | -0.056 |
mate | -0.054 |
control | -0.050 |
polar | -0.049 |
Token | orange |
Token ID | 10912 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
� | +0.093 |
's | +0.091 |
ience | +0.079 |
Michelle | +0.078 |
cious | +0.076 |
Neg logit contributions | |
them | -0.082 |
mate | -0.078 |
inn | -0.072 |
wreck | -0.067 |
polar | -0.067 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
them | +0.019 |
inn | +0.016 |
polar | +0.016 |
mate | +0.016 |
wreck | +0.016 |
Neg logit contributions | |
� | -0.023 |
's | -0.022 |
cious | -0.020 |
ages | -0.020 |
ience | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
them | +0.498 |
polar | +0.492 |
snowball | +0.470 |
wreck | +0.468 |
ramp | +0.455 |
Neg logit contributions | |
� | -0.759 |
's | -0.711 |
cious | -0.622 |
ages | -0.581 |
ience | -0.568 |
Token | shoes |
Token ID | 10012 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
mate | +0.233 |
wreck | +0.221 |
inn | +0.215 |
ramp | +0.208 |
them | +0.203 |
Neg logit contributions | |
� | -0.209 |
's | -0.200 |
cious | -0.181 |
ience | -0.177 |
thoughts | -0.166 |
Token | that |
Token ID | 326 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
them | +0.086 |
mate | +0.084 |
polar | +0.083 |
wreck | +0.081 |
snowball | +0.078 |
Neg logit contributions | |
� | -0.103 |
's | -0.099 |
cious | -0.091 |
ages | -0.090 |
ience | -0.088 |
Token | she |
Token ID | 673 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
them | +0.033 |
wreck | +0.026 |
mate | +0.026 |
his | +0.026 |
match | +0.026 |
Neg logit contributions | |
ience | -0.039 |
ages | -0.037 |
cious | -0.037 |
� | -0.037 |
decisions | -0.036 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
� | +0.203 |
's | +0.192 |
cious | +0.184 |
ience | +0.180 |
ages | +0.179 |
Neg logit contributions | |
them | -0.241 |
mate | -0.225 |
wreck | -0.225 |
polar | -0.220 |
tow | -0.208 |
Token | around |
Token ID | 1088 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
� | +0.009 |
's | +0.009 |
cious | +0.009 |
ages | +0.008 |
ience | +0.008 |
Neg logit contributions | |
them | -0.009 |
wreck | -0.008 |
mate | -0.008 |
polar | -0.008 |
inn | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
� | +0.146 |
's | +0.141 |
Louise | +0.118 |
thoughts | +0.116 |
Michelle | +0.116 |
Neg logit contributions | |
wreck | -0.189 |
polar | -0.188 |
mate | -0.182 |
ramp | -0.180 |
tow | -0.173 |
Token | They |
Token ID | 1119 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
them | +0.008 |
wreck | +0.007 |
mate | +0.007 |
polar | +0.007 |
inn | +0.007 |
Neg logit contributions | |
� | -0.010 |
's | -0.009 |
cious | -0.009 |
ages | -0.009 |
ience | -0.009 |
Token | see |
Token ID | 766 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
them | +0.026 |
mate | +0.024 |
polar | +0.023 |
wreck | +0.023 |
inn | +0.022 |
Neg logit contributions | |
� | -0.040 |
's | -0.038 |
cious | -0.037 |
ience | -0.036 |
ages | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
them | +0.212 |
mate | +0.199 |
wreck | +0.197 |
polar | +0.192 |
inn | +0.191 |
Neg logit contributions | |
� | -0.223 |
's | -0.212 |
cious | -0.205 |
ages | -0.205 |
ience | -0.202 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.19e+00 |
Pos logit contributions | |
� | +0.063 |
's | +0.062 |
cious | +0.049 |
poem | +0.048 |
praying | +0.048 |
Neg logit contributions | |
inn | -0.069 |
them | -0.064 |
mate | -0.059 |
ases | -0.059 |
ir | -0.056 |
Token | of |
Token ID | 286 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
polar | +0.601 |
snowball | +0.534 |
wreck | +0.514 |
ramp | +0.505 |
Ar | +0.505 |
Neg logit contributions | |
� | -0.753 |
's | -0.683 |
cious | -0.501 |
ience | -0.487 |
listens | -0.486 |
Token | scissors |
Token ID | 41786 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
mate | +0.201 |
inn | +0.197 |
wreck | +0.170 |
them | +0.167 |
polar | +0.163 |
Neg logit contributions | |
's | -0.225 |
� | -0.224 |
ages | -0.196 |
ience | -0.196 |
thoughts | -0.192 |
Token | on |
Token ID | 319 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
polar | +0.206 |
them | +0.205 |
wreck | +0.199 |
mate | +0.199 |
inn | +0.189 |
Neg logit contributions | |
� | -0.237 |
's | -0.231 |
cious | -0.207 |
ages | -0.206 |
ience | -0.201 |
Token | the |
Token ID | 262 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
polar | +0.037 |
wreck | +0.036 |
mate | +0.035 |
inn | +0.033 |
splash | +0.031 |
Neg logit contributions | |
� | -0.033 |
's | -0.031 |
Michelle | -0.028 |
Denise | -0.026 |
Louise | -0.026 |
Token | table |
Token ID | 3084 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
� | +0.004 |
's | +0.004 |
cious | +0.004 |
ages | +0.003 |
ience | +0.003 |
Neg logit contributions | |
them | -0.004 |
inn | -0.003 |
mate | -0.003 |
polar | -0.003 |
wreck | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
wreck | +0.053 |
polar | +0.046 |
mate | +0.043 |
tow | +0.037 |
captain | +0.036 |
Neg logit contributions | |
� | -0.139 |
's | -0.137 |
ience | -0.123 |
cious | -0.122 |
pays | -0.122 |
Token | shirt |
Token ID | 10147 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
� | +0.075 |
's | +0.073 |
cious | +0.065 |
ages | +0.063 |
ience | +0.062 |
Neg logit contributions | |
them | -0.058 |
mate | -0.054 |
wreck | -0.053 |
polar | -0.052 |
inn | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
them | +0.253 |
wreck | +0.241 |
polar | +0.237 |
mate | +0.230 |
tow | +0.214 |
Neg logit contributions | |
� | -0.304 |
's | -0.292 |
ages | -0.276 |
cious | -0.273 |
ience | -0.265 |
Token | then |
Token ID | 788 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ience | +0.011 |
� | +0.010 |
ages | +0.010 |
cious | +0.010 |
aul | +0.010 |
Neg logit contributions | |
them | -0.007 |
polar | -0.006 |
his | -0.005 |
match | -0.005 |
wreck | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
them | +0.088 |
wreck | +0.071 |
mate | +0.068 |
polar | +0.066 |
match | +0.066 |
Neg logit contributions | |
cious | -0.133 |
ages | -0.131 |
ience | -0.130 |
� | -0.130 |
aul | -0.128 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.19e+00 |
Pos logit contributions | |
� | +0.077 |
's | +0.072 |
cious | +0.067 |
ience | +0.065 |
ages | +0.064 |
Neg logit contributions | |
them | -0.058 |
inn | -0.049 |
mate | -0.049 |
wreck | -0.048 |
polar | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
polar | +0.612 |
wreck | +0.578 |
snowball | +0.538 |
them | +0.534 |
ramp | +0.513 |
Neg logit contributions | |
� | -0.739 |
's | -0.648 |
cious | -0.499 |
ience | -0.489 |
ages | -0.484 |
Token | pants |
Token ID | 12581 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
mate | +0.191 |
them | +0.186 |
wreck | +0.186 |
inn | +0.177 |
polar | +0.171 |
Neg logit contributions | |
� | -0.242 |
's | -0.228 |
ages | -0.213 |
ience | -0.213 |
cious | -0.213 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
them | +0.062 |
wreck | +0.057 |
polar | +0.056 |
mate | +0.056 |
inn | +0.052 |
Neg logit contributions | |
� | -0.077 |
's | -0.074 |
ages | -0.071 |
cious | -0.071 |
ience | -0.070 |
Token | then |
Token ID | 788 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
cious | +0.010 |
ages | +0.010 |
ience | +0.010 |
� | +0.010 |
aul | +0.009 |
Neg logit contributions | |
them | -0.007 |
polar | -0.005 |
wreck | -0.005 |
mate | -0.005 |
his | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
them | +0.093 |
wreck | +0.079 |
mate | +0.077 |
polar | +0.075 |
tow | +0.072 |
Neg logit contributions | |
cious | -0.127 |
� | -0.127 |
ages | -0.124 |
ience | -0.124 |
aul | -0.121 |
Token | sque |
Token ID | 35776 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
� | +0.067 |
's | +0.064 |
cious | +0.058 |
listens | +0.055 |
ience | +0.055 |
Neg logit contributions | |
inn | -0.064 |
them | -0.062 |
mate | -0.061 |
cubes | -0.055 |
wreck | -0.054 |
Token | ak |
Token ID | 461 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
them | +0.129 |
wreck | +0.117 |
polar | +0.117 |
mate | +0.117 |
tow | +0.114 |
Neg logit contributions | |
� | -0.101 |
's | -0.098 |
ages | -0.091 |
ita | -0.088 |
listens | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
them | +0.012 |
mate | +0.012 |
inn | +0.011 |
wreck | +0.011 |
polar | +0.011 |
Neg logit contributions | |
� | -0.013 |
's | -0.013 |
cious | -0.011 |
ages | -0.011 |
listens | -0.011 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
� | +0.019 |
's | +0.018 |
cious | +0.018 |
ages | +0.018 |
ience | +0.017 |
Neg logit contributions | |
them | -0.016 |
mate | -0.015 |
wreck | -0.015 |
inn | -0.014 |
polar | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
them | +0.220 |
mate | +0.214 |
wreck | +0.211 |
inn | +0.207 |
polar | +0.202 |
Neg logit contributions | |
� | -0.258 |
's | -0.253 |
cious | -0.245 |
ages | -0.243 |
ience | -0.239 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.19e+00 |
Pos logit contributions | |
� | +0.065 |
's | +0.062 |
cious | +0.058 |
poem | +0.054 |
praying | +0.054 |
Neg logit contributions | |
them | -0.065 |
inn | -0.065 |
mate | -0.056 |
ases | -0.054 |
room | -0.050 |
Token | of |
Token ID | 286 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
polar | +0.566 |
Ar | +0.558 |
tant | +0.548 |
them | +0.546 |
snowball | +0.545 |
Neg logit contributions | |
� | -0.692 |
's | -0.634 |
cious | -0.474 |
adow | -0.405 |
ience | -0.401 |
Token | bright |
Token ID | 6016 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
mate | +0.199 |
inn | +0.197 |
them | +0.192 |
wreck | +0.182 |
tow | +0.171 |
Neg logit contributions | |
� | -0.224 |
's | -0.213 |
cious | -0.197 |
ages | -0.196 |
ience | -0.196 |
Token | eyes |
Token ID | 2951 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
's | +0.083 |
� | +0.079 |
thoughts | +0.071 |
Michelle | +0.066 |
decisions | +0.065 |
Neg logit contributions | |
mate | -0.089 |
inn | -0.082 |
them | -0.077 |
wreck | -0.071 |
Ar | -0.069 |
Token | staring |
Token ID | 16143 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
them | +0.013 |
mate | +0.012 |
wreck | +0.012 |
polar | +0.012 |
inn | +0.011 |
Neg logit contributions | |
� | -0.019 |
's | -0.018 |
cious | -0.017 |
ages | -0.017 |
ience | -0.017 |
Token | at |
Token ID | 379 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
� | +0.152 |
ages | +0.144 |
cious | +0.144 |
ience | +0.143 |
's | +0.143 |
Neg logit contributions | |
them | -0.134 |
wreck | -0.119 |
mate | -0.116 |
polar | -0.116 |
inn | -0.111 |
Token | wardrobe |
Token ID | 35593 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
� | +0.671 |
ience | +0.643 |
cious | +0.635 |
ages | +0.633 |
's | +0.614 |
Neg logit contributions | |
them | -0.513 |
wreck | -0.469 |
polar | -0.447 |
mate | -0.439 |
tow | -0.416 |
Token | and |
Token ID | 290 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
them | +0.047 |
wreck | +0.042 |
mate | +0.041 |
load | +0.037 |
polar | +0.037 |
Neg logit contributions | |
� | -0.080 |
ience | -0.079 |
cious | -0.078 |
ages | -0.075 |
Michelle | -0.073 |
Token | she |
Token ID | 673 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
ience | +0.017 |
� | +0.017 |
cious | +0.017 |
ages | +0.017 |
aul | +0.016 |
Neg logit contributions | |
them | -0.019 |
wreck | -0.017 |
polar | -0.016 |
his | -0.016 |
mate | -0.016 |
Token | found |
Token ID | 1043 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
� | +0.246 |
cious | +0.242 |
ages | +0.241 |
ience | +0.239 |
aul | +0.232 |
Neg logit contributions | |
them | -0.190 |
wreck | -0.169 |
polar | -0.163 |
mate | -0.159 |
tow | -0.148 |
Token | a |
Token ID | 257 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
them | +0.135 |
wreck | +0.121 |
mate | +0.120 |
polar | +0.118 |
inn | +0.112 |
Neg logit contributions | |
� | -0.148 |
cious | -0.140 |
's | -0.139 |
ages | -0.139 |
ience | -0.138 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
� | +0.071 |
's | +0.067 |
cious | +0.063 |
ience | +0.060 |
ages | +0.060 |
Neg logit contributions | |
them | -0.062 |
inn | -0.055 |
mate | -0.053 |
polar | -0.049 |
wreck | -0.049 |
Token | of |
Token ID | 286 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
them | +0.499 |
polar | +0.492 |
snowball | +0.482 |
wreck | +0.472 |
ramp | +0.470 |
Neg logit contributions | |
� | -0.755 |
's | -0.699 |
cious | -0.608 |
ages | -0.584 |
ience | -0.549 |
Token | sunglasses |
Token ID | 36251 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
wreck | +0.208 |
mate | +0.201 |
them | +0.196 |
inn | +0.190 |
tow | +0.186 |
Neg logit contributions | |
� | -0.227 |
's | -0.219 |
ience | -0.198 |
cious | -0.196 |
ages | -0.192 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
� | +0.198 |
's | +0.189 |
cious | +0.185 |
ages | +0.185 |
ience | +0.182 |
Neg logit contributions | |
them | -0.147 |
wreck | -0.133 |
mate | -0.131 |
polar | -0.129 |
inn | -0.122 |
Token | She |
Token ID | 1375 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
them | +0.010 |
polar | +0.009 |
wreck | +0.009 |
mate | +0.009 |
inn | +0.009 |
Neg logit contributions | |
� | -0.009 |
ience | -0.009 |
cious | -0.008 |
ages | -0.008 |
's | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
� | +0.029 |
's | +0.028 |
cious | +0.026 |
ages | +0.026 |
ience | +0.026 |
Neg logit contributions | |
them | -0.031 |
mate | -0.029 |
wreck | -0.029 |
polar | -0.028 |
inn | -0.027 |
Token | day |
Token ID | 1110 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
them | +0.076 |
wreck | +0.072 |
polar | +0.069 |
rock | +0.066 |
snowball | +0.063 |
Neg logit contributions | |
ages | -0.093 |
cious | -0.093 |
ience | -0.092 |
� | -0.088 |
Michelle | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
� | +0.127 |
ience | +0.124 |
cious | +0.124 |
ages | +0.124 |
's | +0.122 |
Neg logit contributions | |
them | -0.088 |
mate | -0.075 |
wreck | -0.074 |
polar | -0.073 |
inn | -0.069 |
Token | Alice |
Token ID | 14862 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
them | +0.007 |
wreck | +0.007 |
mate | +0.007 |
polar | +0.006 |
inn | +0.006 |
Neg logit contributions | |
� | -0.008 |
's | -0.007 |
cious | -0.007 |
ages | -0.007 |
ience | -0.007 |
Token | designed |
Token ID | 3562 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ages | +0.174 |
cious | +0.169 |
List | +0.168 |
decisions | +0.167 |
ience | +0.166 |
Neg logit contributions | |
them | -0.116 |
polar | -0.096 |
wreck | -0.093 |
rock | -0.086 |
row | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
them | +0.166 |
wreck | +0.144 |
mate | +0.141 |
polar | +0.138 |
inn | +0.133 |
Neg logit contributions | |
� | -0.181 |
cious | -0.175 |
ages | -0.174 |
ience | -0.174 |
's | -0.171 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
� | +0.066 |
's | +0.063 |
cious | +0.058 |
ience | +0.057 |
ages | +0.056 |
Neg logit contributions | |
them | -0.059 |
inn | -0.052 |
mate | -0.052 |
polar | -0.049 |
wreck | -0.048 |
Token | of |
Token ID | 286 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
polar | +0.594 |
snowball | +0.556 |
them | +0.552 |
ramp | +0.549 |
wreck | +0.528 |
Neg logit contributions | |
� | -0.718 |
's | -0.651 |
ages | -0.520 |
cious | -0.506 |
grand | -0.468 |
Token | wings |
Token ID | 12098 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
them | +0.188 |
wreck | +0.186 |
mate | +0.182 |
inn | +0.178 |
polar | +0.173 |
Neg logit contributions | |
� | -0.233 |
's | -0.223 |
cious | -0.213 |
ages | -0.211 |
ience | -0.206 |
Token | for |
Token ID | 329 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
� | +0.311 |
's | +0.298 |
ages | +0.288 |
cious | +0.285 |
ience | +0.281 |
Neg logit contributions | |
them | -0.246 |
wreck | -0.229 |
mate | -0.225 |
polar | -0.223 |
inn | -0.210 |
Token | Bob |
Token ID | 5811 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
them | +0.150 |
wreck | +0.144 |
mate | +0.141 |
polar | +0.138 |
inn | +0.134 |
Neg logit contributions | |
� | -0.182 |
's | -0.173 |
cious | -0.173 |
ages | -0.170 |
ience | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
ience | +0.200 |
� | +0.196 |
List | +0.194 |
cious | +0.191 |
listens | +0.190 |
Neg logit contributions | |
them | -0.169 |
polar | -0.140 |
wreck | -0.137 |
mate | -0.137 |
his | -0.128 |
Token | They |
Token ID | 1119 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
them | +0.008 |
wreck | +0.006 |
mate | +0.006 |
tow | +0.006 |
inn | +0.006 |
Neg logit contributions | |
cious | -0.008 |
ience | -0.008 |
ages | -0.008 |
� | -0.008 |
's | -0.008 |
Token | were |
Token ID | 547 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
them | +0.030 |
wreck | +0.027 |
mate | +0.027 |
polar | +0.026 |
inn | +0.025 |
Neg logit contributions | |
� | -0.032 |
's | -0.031 |
cious | -0.030 |
ages | -0.030 |
ience | -0.030 |
Token | quite |
Token ID | 2407 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
them | +0.207 |
polar | +0.176 |
wreck | +0.174 |
mate | +0.170 |
tow | +0.162 |
Neg logit contributions | |
� | -0.262 |
cious | -0.256 |
ience | -0.256 |
ages | -0.256 |
's | -0.246 |
Token | a |
Token ID | 257 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
them | +0.178 |
polar | +0.161 |
wreck | +0.157 |
tow | +0.146 |
his | +0.145 |
Neg logit contributions | |
ages | -0.173 |
ience | -0.172 |
� | -0.171 |
cious | -0.169 |
aul | -0.168 |
Token | charming |
Token ID | 23332 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
� | +0.070 |
ages | +0.067 |
cious | +0.067 |
's | +0.066 |
ience | +0.065 |
Neg logit contributions | |
them | -0.058 |
wreck | -0.053 |
mate | -0.052 |
polar | -0.051 |
inn | -0.048 |
Token | pair |
Token ID | 5166 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
them | +0.034 |
mate | +0.030 |
wreck | +0.029 |
inn | +0.028 |
polar | +0.027 |
Neg logit contributions | |
� | -0.055 |
's | -0.053 |
cious | -0.052 |
ience | -0.051 |
ages | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
them | +0.398 |
wreck | +0.352 |
polar | +0.333 |
mate | +0.330 |
inn | +0.310 |
Neg logit contributions | |
� | -0.807 |
's | -0.773 |
cious | -0.756 |
ages | -0.749 |
ience | -0.740 |
Token | they |
Token ID | 484 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
� | +0.018 |
ience | +0.018 |
aul | +0.018 |
ages | +0.018 |
cious | +0.018 |
Neg logit contributions | |
them | -0.017 |
polar | -0.014 |
mate | -0.014 |
wreck | -0.014 |
his | -0.013 |
Token | always |
Token ID | 1464 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
� | +0.102 |
's | +0.097 |
ience | +0.092 |
cious | +0.092 |
ages | +0.091 |
Neg logit contributions | |
them | -0.100 |
wreck | -0.094 |
mate | -0.093 |
polar | -0.090 |
inn | -0.090 |
Token | made |
Token ID | 925 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
them | +0.070 |
wreck | +0.064 |
polar | +0.063 |
mate | +0.061 |
tow | +0.057 |
Neg logit contributions | |
� | -0.067 |
ages | -0.063 |
ience | -0.063 |
cious | -0.063 |
aul | -0.062 |
Token | everyone |
Token ID | 2506 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
them | +0.050 |
wreck | +0.038 |
mate | +0.038 |
polar | +0.038 |
his | +0.037 |
Neg logit contributions | |
� | -0.055 |
cious | -0.053 |
ience | -0.053 |
ages | -0.051 |
aul | -0.051 |
Token | joy |
Token ID | 2633 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
� | +0.211 |
's | +0.198 |
cious | +0.191 |
ience | +0.188 |
ages | +0.188 |
Neg logit contributions | |
them | -0.193 |
wreck | -0.184 |
mate | -0.180 |
polar | -0.177 |
inn | -0.171 |
Token | ed |
Token ID | 276 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
them | +0.041 |
mate | +0.038 |
inn | +0.036 |
his | +0.035 |
control | +0.033 |
Neg logit contributions | |
ience | -0.033 |
cious | -0.032 |
Michelle | -0.032 |
� | -0.030 |
Louise | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
cious | +0.241 |
� | +0.238 |
ages | +0.235 |
ience | +0.235 |
's | +0.229 |
Neg logit contributions | |
them | -0.155 |
mate | -0.127 |
wreck | -0.124 |
polar | -0.121 |
inn | -0.115 |
Token | He |
Token ID | 679 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
cious | +0.011 |
� | +0.011 |
ages | +0.010 |
ience | +0.010 |
's | +0.010 |
Neg logit contributions | |
them | -0.005 |
wreck | -0.004 |
polar | -0.004 |
mate | -0.004 |
inn | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
them | +0.126 |
wreck | +0.113 |
polar | +0.111 |
mate | +0.109 |
inn | +0.105 |
Neg logit contributions | |
cious | -0.126 |
� | -0.125 |
ages | -0.124 |
ience | -0.119 |
's | -0.119 |
Token | conquered |
Token ID | 29346 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
� | +0.108 |
cious | +0.108 |
ages | +0.107 |
ience | +0.107 |
aul | +0.103 |
Neg logit contributions | |
them | -0.113 |
wreck | -0.100 |
mate | -0.096 |
polar | -0.094 |
tow | -0.091 |
Token | something |
Token ID | 1223 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
� | +0.683 |
's | +0.653 |
cious | +0.625 |
ience | +0.622 |
ages | +0.619 |
Neg logit contributions | |
wreck | -0.294 |
them | -0.288 |
mate | -0.278 |
polar | -0.271 |
inn | -0.258 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
� | +0.307 |
cious | +0.299 |
ages | +0.298 |
's | +0.293 |
ience | +0.292 |
Neg logit contributions | |
them | -0.255 |
wreck | -0.228 |
mate | -0.221 |
polar | -0.216 |
inn | -0.207 |
Token | and |
Token ID | 290 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
� | +0.193 |
cious | +0.189 |
ience | +0.187 |
ages | +0.186 |
's | +0.183 |
Neg logit contributions | |
them | -0.136 |
wreck | -0.117 |
mate | -0.117 |
polar | -0.109 |
inn | -0.104 |
Token | he |
Token ID | 339 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
cious | +0.041 |
aul | +0.040 |
ages | +0.040 |
ience | +0.039 |
ita | +0.039 |
Neg logit contributions | |
them | -0.028 |
wreck | -0.024 |
his | -0.023 |
polar | -0.022 |
mate | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
cious | +0.033 |
� | +0.032 |
ages | +0.032 |
aul | +0.031 |
Michelle | +0.031 |
Neg logit contributions | |
them | -0.033 |
wreck | -0.030 |
polar | -0.028 |
mate | -0.028 |
tow | -0.026 |
Token | One |
Token ID | 1881 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
� | +0.006 |
's | +0.006 |
aul | +0.005 |
List | +0.005 |
ages | +0.005 |
Neg logit contributions | |
mate | -0.007 |
them | -0.007 |
wreck | -0.006 |
polar | -0.006 |
control | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
them | +0.041 |
wreck | +0.038 |
polar | +0.037 |
mate | +0.037 |
inn | +0.035 |
Neg logit contributions | |
� | -0.036 |
cious | -0.035 |
ience | -0.035 |
ages | -0.034 |
's | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
� | +0.149 |
's | +0.145 |
ages | +0.137 |
cious | +0.135 |
ience | +0.131 |
Neg logit contributions | |
them | -0.142 |
mate | -0.131 |
wreck | -0.131 |
polar | -0.128 |
inn | -0.122 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
's | +0.023 |
� | +0.023 |
Michelle | +0.019 |
ages | +0.019 |
thoughts | +0.019 |
Neg logit contributions | |
mate | -0.021 |
inn | -0.020 |
detector | -0.019 |
polar | -0.019 |
them | -0.019 |
Token | my |
Token ID | 1820 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
them | +0.147 |
wreck | +0.136 |
mate | +0.135 |
polar | +0.132 |
inn | +0.128 |
Neg logit contributions | |
� | -0.109 |
's | -0.103 |
cious | -0.101 |
ages | -0.101 |
ience | -0.099 |
Token | 's |
Token ID | 338 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
cious | +0.156 |
ience | +0.152 |
� | +0.145 |
aul | +0.142 |
ages | +0.142 |
Neg logit contributions | |
them | -0.264 |
wreck | -0.256 |
polar | -0.251 |
rock | -0.233 |
his | -0.231 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
's | +0.570 |
ages | +0.504 |
� | +0.485 |
thoughts | +0.457 |
ama | +0.455 |
Neg logit contributions | |
them | -0.612 |
mate | -0.595 |
inn | -0.582 |
Nick | -0.524 |
Mike | -0.523 |
Token | made |
Token ID | 925 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
� | +0.030 |
cious | +0.028 |
's | +0.028 |
ages | +0.028 |
ience | +0.027 |
Neg logit contributions | |
them | -0.031 |
wreck | -0.028 |
mate | -0.028 |
polar | -0.027 |
inn | -0.026 |
Token | him |
Token ID | 683 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
mate | +0.029 |
wreck | +0.027 |
polar | +0.027 |
them | +0.026 |
ramp | +0.026 |
Neg logit contributions | |
� | -0.041 |
's | -0.041 |
ages | -0.039 |
aul | -0.035 |
cious | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
them | +0.241 |
wreck | +0.219 |
polar | +0.209 |
mate | +0.206 |
inn | +0.195 |
Neg logit contributions | |
� | -0.305 |
cious | -0.295 |
ience | -0.294 |
ages | -0.286 |
's | -0.286 |
Token | y |
Token ID | 331 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
's | +0.076 |
� | +0.074 |
ience | +0.062 |
poem | +0.062 |
cious | +0.061 |
Neg logit contributions | |
them | -0.084 |
mate | -0.077 |
inn | -0.075 |
Mike | -0.068 |
control | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
them | +0.016 |
mate | +0.014 |
wreck | +0.014 |
polar | +0.013 |
inn | +0.013 |
Neg logit contributions | |
� | -0.023 |
ages | -0.023 |
cious | -0.022 |
ience | -0.022 |
's | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ience | +0.030 |
� | +0.030 |
ages | +0.030 |
cious | +0.030 |
's | +0.029 |
Neg logit contributions | |
them | -0.021 |
wreck | -0.017 |
polar | -0.017 |
mate | -0.017 |
inn | -0.017 |
Token | Yes |
Token ID | 5297 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
them | +0.081 |
wreck | +0.074 |
mate | +0.072 |
polar | +0.071 |
inn | +0.067 |
Neg logit contributions | |
� | -0.107 |
's | -0.100 |
cious | -0.100 |
ages | -0.099 |
ience | -0.098 |
Token | ! |
Token ID | 0 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
wreck | +0.141 |
them | +0.137 |
polar | +0.133 |
inn | +0.129 |
ramp | +0.127 |
Neg logit contributions | |
� | -0.139 |
's | -0.130 |
ience | -0.120 |
cious | -0.112 |
Louise | -0.105 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
them | +0.077 |
mate | +0.075 |
polar | +0.072 |
tow | +0.070 |
inn | +0.069 |
Neg logit contributions | |
cious | -0.067 |
ages | -0.065 |
ience | -0.064 |
aul | -0.062 |
's | -0.061 |
Token | 's |
Token ID | 338 |
Feature activation | +9.30e+00 |
Pos logit contributions | |
ages | +0.059 |
cious | +0.055 |
aul | +0.051 |
ccoli | +0.048 |
List | +0.048 |
Neg logit contributions | |
them | -0.194 |
mate | -0.156 |
his | -0.154 |
row | -0.153 |
rock | -0.152 |
Token | play |
Token ID | 711 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
� | +0.784 |
's | +0.739 |
ages | +0.633 |
cious | +0.627 |
ience | +0.607 |
Neg logit contributions | |
them | -0.445 |
inn | -0.429 |
mate | -0.423 |
polar | -0.402 |
tant | -0.396 |
Token | before |
Token ID | 878 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
tow | +0.157 |
polar | +0.153 |
inn | +0.153 |
wreck | +0.152 |
them | +0.147 |
Neg logit contributions | |
� | -0.201 |
's | -0.198 |
ience | -0.167 |
ages | -0.166 |
cious | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
� | +0.246 |
cious | +0.242 |
ages | +0.241 |
ience | +0.235 |
's | +0.232 |
Neg logit contributions | |
them | -0.304 |
wreck | -0.271 |
mate | -0.264 |
polar | -0.263 |
tow | -0.247 |
Token | sunrise |
Token ID | 40048 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
� | +0.026 |
's | +0.025 |
cious | +0.024 |
ience | +0.024 |
ages | +0.024 |
Neg logit contributions | |
them | -0.019 |
mate | -0.017 |
inn | -0.017 |
wreck | -0.017 |
polar | -0.016 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
cious | +0.296 |
� | +0.296 |
ience | +0.289 |
ages | +0.288 |
Michelle | +0.281 |
Neg logit contributions | |
them | -0.167 |
wreck | -0.139 |
mate | -0.137 |
polar | -0.129 |
match | -0.122 |
Token | um |
Token ID | 388 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
them | +0.219 |
wreck | +0.200 |
mate | +0.198 |
polar | +0.193 |
inn | +0.188 |
Neg logit contributions | |
� | -0.223 |
's | -0.210 |
cious | -0.209 |
ages | -0.207 |
ience | -0.205 |
Token | ma |
Token ID | 2611 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
� | +0.178 |
cious | +0.178 |
ages | +0.173 |
ience | +0.171 |
Michelle | +0.165 |
Neg logit contributions | |
them | -0.122 |
polar | -0.095 |
wreck | -0.094 |
mate | -0.091 |
inn | -0.088 |
Token | kissed |
Token ID | 27946 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
them | +0.027 |
polar | +0.022 |
wreck | +0.022 |
mate | +0.021 |
tow | +0.020 |
Neg logit contributions | |
cious | -0.030 |
ages | -0.030 |
� | -0.030 |
ience | -0.029 |
List | -0.028 |
Token | him |
Token ID | 683 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
� | +0.264 |
's | +0.251 |
cious | +0.248 |
ages | +0.247 |
ience | +0.243 |
Neg logit contributions | |
them | -0.182 |
wreck | -0.169 |
mate | -0.164 |
polar | -0.160 |
inn | -0.153 |
Token | good |
Token ID | 922 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
them | +0.227 |
his | +0.178 |
polar | +0.178 |
wreck | +0.170 |
mate | +0.167 |
Neg logit contributions | |
cious | -0.394 |
ience | -0.383 |
aul | -0.377 |
ages | -0.371 |
� | -0.369 |
Token | night |
Token ID | 3847 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
them | +0.016 |
wreck | +0.014 |
mate | +0.014 |
polar | +0.014 |
inn | +0.013 |
Neg logit contributions | |
� | -0.016 |
cious | -0.015 |
's | -0.015 |
ience | -0.014 |
ages | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
� | +0.519 |
ience | +0.502 |
cious | +0.502 |
ages | +0.489 |
's | +0.483 |
Neg logit contributions | |
them | -0.335 |
polar | -0.273 |
mate | -0.273 |
wreck | -0.270 |
inn | -0.248 |
Token | urged |
Token ID | 11643 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
cious | +0.013 |
ages | +0.012 |
aul | +0.012 |
ience | +0.012 |
� | +0.012 |
Neg logit contributions | |
them | -0.011 |
his | -0.009 |
polar | -0.009 |
wreck | -0.009 |
mate | -0.008 |
Token | him |
Token ID | 683 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
them | +0.112 |
mate | +0.093 |
wreck | +0.092 |
polar | +0.090 |
inn | +0.086 |
Neg logit contributions | |
� | -0.156 |
cious | -0.151 |
ience | -0.149 |
ages | -0.149 |
's | -0.148 |
Token | to |
Token ID | 284 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
them | +0.207 |
his | +0.166 |
mate | +0.155 |
polar | +0.134 |
load | +0.133 |
Neg logit contributions | |
ience | -0.372 |
aul | -0.368 |
cious | -0.365 |
Michelle | -0.359 |
ita | -0.357 |
Token | go |
Token ID | 467 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
� | +0.029 |
cious | +0.029 |
ience | +0.028 |
ages | +0.028 |
's | +0.028 |
Neg logit contributions | |
them | -0.020 |
wreck | -0.017 |
mate | -0.017 |
polar | -0.017 |
tow | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
cious | +0.195 |
� | +0.193 |
ages | +0.192 |
ience | +0.192 |
aul | +0.185 |
Neg logit contributions | |
them | -0.120 |
mate | -0.099 |
wreck | -0.096 |
inn | -0.093 |
polar | -0.091 |
Token | talk |
Token ID | 1561 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
cious | +0.021 |
ages | +0.021 |
ience | +0.020 |
� | +0.020 |
ita | +0.020 |
Neg logit contributions | |
them | -0.016 |
wreck | -0.014 |
polar | -0.013 |
mate | -0.013 |
his | -0.012 |
Token | about |
Token ID | 546 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
� | +0.037 |
cious | +0.036 |
ages | +0.036 |
's | +0.035 |
ience | +0.035 |
Neg logit contributions | |
them | -0.030 |
mate | -0.026 |
wreck | -0.026 |
polar | -0.025 |
inn | -0.024 |
Token | why |
Token ID | 1521 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
� | +0.146 |
's | +0.138 |
cious | +0.138 |
ages | +0.137 |
ience | +0.136 |
Neg logit contributions | |
them | -0.112 |
wreck | -0.101 |
mate | -0.099 |
polar | -0.097 |
inn | -0.093 |
Token | it |
Token ID | 340 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
cious | +0.294 |
� | +0.289 |
ages | +0.284 |
ita | +0.273 |
ience | +0.272 |
Neg logit contributions | |
them | -0.220 |
wreck | -0.180 |
mate | -0.166 |
polar | -0.162 |
his | -0.162 |
Token | 's |
Token ID | 338 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
them | +0.137 |
wreck | +0.130 |
rock | +0.125 |
match | +0.123 |
tank | +0.123 |
Neg logit contributions | |
cious | -0.082 |
enna | -0.077 |
Michelle | -0.075 |
Nik | -0.072 |
Jennifer | -0.071 |
Token | important |
Token ID | 1593 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
� | +0.628 |
cious | +0.613 |
ience | +0.599 |
ages | +0.594 |
's | +0.588 |
Neg logit contributions | |
them | -0.561 |
wreck | -0.502 |
polar | -0.480 |
mate | -0.471 |
inn | -0.446 |
Token | to |
Token ID | 284 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
� | +0.307 |
cious | +0.298 |
ience | +0.293 |
's | +0.284 |
ages | +0.281 |
Neg logit contributions | |
them | -0.206 |
mate | -0.174 |
wreck | -0.169 |
polar | -0.153 |
inn | -0.148 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
� | +0.028 |
's | +0.026 |
cious | +0.026 |
ages | +0.026 |
ience | +0.025 |
Neg logit contributions | |
them | -0.017 |
mate | -0.016 |
wreck | -0.016 |
polar | -0.015 |
inn | -0.015 |
Token | healthy |
Token ID | 5448 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
them | +0.045 |
wreck | +0.036 |
mate | +0.035 |
polar | +0.034 |
his | +0.032 |
Neg logit contributions | |
cious | -0.059 |
� | -0.057 |
ages | -0.057 |
ience | -0.056 |
Michelle | -0.054 |
Token | fish |
Token ID | 5916 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
� | +0.251 |
cious | +0.243 |
ience | +0.240 |
ages | +0.230 |
Michelle | +0.230 |
Neg logit contributions | |
them | -0.183 |
wreck | -0.153 |
mate | -0.149 |
polar | -0.149 |
snowball | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
� | +0.037 |
's | +0.036 |
cious | +0.032 |
ages | +0.032 |
ience | +0.031 |
Neg logit contributions | |
them | -0.030 |
wreck | -0.029 |
polar | -0.028 |
mate | -0.028 |
tow | -0.027 |
Token | One |
Token ID | 1881 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
� | +0.000 |
cious | +0.000 |
ages | +0.000 |
's | +0.000 |
ience | +0.000 |
Neg logit contributions | |
them | -0.000 |
wreck | -0.000 |
mate | -0.000 |
polar | -0.000 |
inn | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
them | +0.034 |
polar | +0.032 |
his | +0.031 |
wreck | +0.031 |
snowball | +0.031 |
Neg logit contributions | |
ience | -0.056 |
ages | -0.053 |
cious | -0.052 |
� | -0.050 |
aries | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
� | +0.160 |
's | +0.152 |
cious | +0.151 |
ages | +0.150 |
ience | +0.149 |
Neg logit contributions | |
them | -0.122 |
wreck | -0.109 |
mate | -0.108 |
polar | -0.105 |
inn | -0.101 |
Token | while |
Token ID | 981 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
's | +0.010 |
� | +0.010 |
Michelle | +0.008 |
cious | +0.008 |
ages | +0.008 |
Neg logit contributions | |
wreck | -0.025 |
polar | -0.024 |
them | -0.024 |
mate | -0.024 |
ramp | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
them | +0.166 |
wreck | +0.141 |
polar | +0.141 |
mate | +0.140 |
tow | +0.133 |
Neg logit contributions | |
� | -0.155 |
ience | -0.154 |
ages | -0.154 |
cious | -0.151 |
aul | -0.146 |
Token | was |
Token ID | 373 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
� | +0.240 |
's | +0.229 |
cious | +0.223 |
ages | +0.222 |
ience | +0.219 |
Neg logit contributions | |
them | -0.220 |
wreck | -0.198 |
mate | -0.197 |
polar | -0.192 |
inn | -0.185 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
them | +0.033 |
wreck | +0.028 |
mate | +0.026 |
polar | +0.026 |
inn | +0.025 |
Neg logit contributions | |
� | -0.049 |
ience | -0.049 |
cious | -0.047 |
ages | -0.047 |
aul | -0.046 |
Token | in |
Token ID | 287 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
polar | +0.078 |
them | +0.078 |
wreck | +0.078 |
tow | +0.075 |
inn | +0.074 |
Neg logit contributions | |
's | -0.074 |
� | -0.071 |
ages | -0.062 |
cious | -0.060 |
Louise | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
� | +0.019 |
's | +0.018 |
Louise | +0.016 |
Michelle | +0.016 |
Denise | +0.015 |
Neg logit contributions | |
mate | -0.021 |
inn | -0.020 |
them | -0.020 |
wreck | -0.019 |
captain | -0.019 |
Token | park |
Token ID | 3952 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ience | +0.017 |
� | +0.017 |
ages | +0.017 |
cious | +0.017 |
's | +0.016 |
Neg logit contributions | |
them | -0.011 |
wreck | -0.010 |
polar | -0.009 |
mate | -0.009 |
snowball | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
them | +0.165 |
wreck | +0.149 |
mate | +0.147 |
polar | +0.144 |
inn | +0.138 |
Neg logit contributions | |
� | -0.221 |
's | -0.210 |
cious | -0.207 |
ages | -0.207 |
ience | -0.205 |
Token | magic |
Token ID | 5536 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
� | +0.085 |
's | +0.081 |
cious | +0.080 |
ages | +0.080 |
ience | +0.079 |
Neg logit contributions | |
them | -0.059 |
wreck | -0.052 |
mate | -0.052 |
polar | -0.051 |
inn | -0.049 |
Token | stone |
Token ID | 7815 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
them | +0.036 |
wreck | +0.032 |
polar | +0.032 |
mate | +0.031 |
inn | +0.031 |
Neg logit contributions | |
� | -0.043 |
's | -0.041 |
ages | -0.040 |
cious | -0.039 |
ience | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
� | +0.108 |
cious | +0.104 |
ience | +0.103 |
ages | +0.102 |
's | +0.101 |
Neg logit contributions | |
them | -0.077 |
wreck | -0.067 |
mate | -0.067 |
polar | -0.063 |
inn | -0.061 |
Token | The |
Token ID | 383 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
them | +0.002 |
his | +0.002 |
load | +0.002 |
wreck | +0.002 |
tow | +0.002 |
Neg logit contributions | |
cious | -0.002 |
ages | -0.002 |
ience | -0.002 |
� | -0.002 |
ita | -0.002 |
Token | human |
Token ID | 1692 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
� | +0.151 |
ages | +0.149 |
ience | +0.142 |
aul | +0.142 |
cious | +0.142 |
Neg logit contributions | |
wreck | -0.088 |
polar | -0.088 |
them | -0.087 |
rock | -0.086 |
captain | -0.086 |
Token | did |
Token ID | 750 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
cious | +0.121 |
ages | +0.113 |
aul | +0.113 |
Michelle | +0.113 |
� | +0.111 |
Neg logit contributions | |
them | -0.096 |
wreck | -0.086 |
polar | -0.082 |
captain | -0.081 |
rock | -0.081 |
Token | as |
Token ID | 355 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
them | +0.120 |
wreck | +0.110 |
mate | +0.109 |
polar | +0.107 |
inn | +0.103 |
Neg logit contributions | |
� | -0.104 |
's | -0.098 |
cious | -0.097 |
ages | -0.096 |
ience | -0.096 |
Token | he |
Token ID | 339 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
them | +0.027 |
his | +0.022 |
wreck | +0.021 |
polar | +0.021 |
mate | +0.020 |
Neg logit contributions | |
ages | -0.050 |
cious | -0.050 |
� | -0.049 |
ience | -0.047 |
's | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
� | +0.021 |
's | +0.020 |
ience | +0.020 |
ages | +0.019 |
cious | +0.019 |
Neg logit contributions | |
them | -0.024 |
mate | -0.021 |
wreck | -0.021 |
polar | -0.021 |
inn | -0.020 |
Token | told |
Token ID | 1297 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
them | +0.043 |
wreck | +0.039 |
mate | +0.038 |
polar | +0.037 |
inn | +0.036 |
Neg logit contributions | |
� | -0.042 |
cious | -0.041 |
ience | -0.040 |
ages | -0.040 |
's | -0.039 |
Token | bread |
Token ID | 8509 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
� | +0.022 |
ages | +0.022 |
cious | +0.021 |
ience | +0.020 |
's | +0.020 |
Neg logit contributions | |
them | -0.018 |
wreck | -0.016 |
polar | -0.015 |
match | -0.015 |
rock | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
� | +0.064 |
cious | +0.062 |
ience | +0.062 |
ages | +0.061 |
's | +0.059 |
Neg logit contributions | |
them | -0.042 |
wreck | -0.034 |
polar | -0.033 |
mate | -0.033 |
match | -0.030 |
Token | cakes |
Token ID | 30849 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
� | +0.043 |
ience | +0.042 |
cious | +0.042 |
ages | +0.041 |
ita | +0.040 |
Neg logit contributions | |
them | -0.023 |
his | -0.017 |
polar | -0.016 |
wreck | -0.016 |
rock | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
� | +0.084 |
cious | +0.080 |
ience | +0.080 |
ages | +0.079 |
's | +0.079 |
Neg logit contributions | |
them | -0.056 |
wreck | -0.048 |
mate | -0.047 |
polar | -0.046 |
inn | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
� | +0.028 |
cious | +0.028 |
ience | +0.027 |
ages | +0.027 |
's | +0.026 |
Neg logit contributions | |
them | -0.017 |
polar | -0.012 |
wreck | -0.012 |
his | -0.011 |
mate | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
cious | +0.037 |
ages | +0.036 |
� | +0.036 |
ience | +0.036 |
ita | +0.034 |
Neg logit contributions | |
them | -0.025 |
wreck | -0.020 |
polar | -0.020 |
his | -0.019 |
match | -0.018 |
Token | love |
Token ID | 1842 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
� | +0.020 |
ages | +0.020 |
cious | +0.019 |
ience | +0.019 |
's | +0.019 |
Neg logit contributions | |
them | -0.016 |
wreck | -0.015 |
polar | -0.014 |
mate | -0.013 |
tow | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
� | +0.025 |
cious | +0.025 |
ages | +0.024 |
ience | +0.024 |
's | +0.024 |
Neg logit contributions | |
them | -0.017 |
mate | -0.014 |
wreck | -0.014 |
polar | -0.013 |
inn | -0.012 |
Token | their |
Token ID | 511 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
them | +0.155 |
wreck | +0.128 |
mate | +0.124 |
polar | +0.122 |
tow | +0.112 |
Neg logit contributions | |
� | -0.267 |
cious | -0.257 |
ages | -0.257 |
's | -0.255 |
ience | -0.254 |
Token | mother |
Token ID | 2802 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
them | +0.205 |
wreck | +0.176 |
polar | +0.170 |
mate | +0.161 |
match | +0.159 |
Neg logit contributions | |
� | -0.225 |
ages | -0.211 |
cious | -0.209 |
ience | -0.203 |
's | -0.201 |
Token | and |
Token ID | 290 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
cious | +0.229 |
ages | +0.228 |
ience | +0.224 |
List | +0.220 |
� | +0.220 |
Neg logit contributions | |
them | -0.123 |
polar | -0.091 |
wreck | -0.089 |
mate | -0.084 |
his | -0.081 |
Token | John |
Token ID | 1757 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
them | +0.134 |
wreck | +0.117 |
mate | +0.114 |
polar | +0.112 |
inn | +0.105 |
Neg logit contributions | |
� | -0.246 |
's | -0.235 |
cious | -0.235 |
ages | -0.234 |
ience | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
's | +0.142 |
� | +0.139 |
ages | +0.122 |
cious | +0.122 |
aul | +0.116 |
Neg logit contributions | |
mate | -0.138 |
them | -0.136 |
ramp | -0.131 |
wreck | -0.129 |
inn | -0.128 |
Token | John |
Token ID | 1757 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
them | +0.003 |
wreck | +0.003 |
mate | +0.003 |
polar | +0.002 |
inn | +0.002 |
Neg logit contributions | |
� | -0.003 |
cious | -0.003 |
's | -0.003 |
ages | -0.003 |
ience | -0.003 |
Token | loved |
Token ID | 6151 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
� | +0.136 |
cious | +0.132 |
ience | +0.132 |
ages | +0.130 |
's | +0.126 |
Neg logit contributions | |
them | -0.135 |
wreck | -0.124 |
polar | -0.121 |
mate | -0.116 |
inn | -0.112 |
Token | to |
Token ID | 284 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
� | +0.066 |
's | +0.063 |
cious | +0.063 |
ages | +0.062 |
ience | +0.062 |
Neg logit contributions | |
them | -0.057 |
wreck | -0.051 |
mate | -0.051 |
polar | -0.050 |
inn | -0.048 |
Token | explore |
Token ID | 7301 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
� | +0.035 |
's | +0.033 |
cious | +0.032 |
ages | +0.032 |
ience | +0.030 |
Neg logit contributions | |
them | -0.021 |
mate | -0.019 |
wreck | -0.019 |
inn | -0.019 |
polar | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
� | +0.252 |
's | +0.249 |
cious | +0.225 |
ience | +0.224 |
ages | +0.222 |
Neg logit contributions | |
mate | -0.176 |
them | -0.171 |
wreck | -0.168 |
inn | -0.166 |
polar | -0.163 |
Token | outdoors |
Token ID | 24349 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
� | +0.011 |
ience | +0.011 |
ages | +0.011 |
cious | +0.010 |
's | +0.010 |
Neg logit contributions | |
them | -0.010 |
wreck | -0.009 |
polar | -0.009 |
mate | -0.009 |
rock | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
� | +0.116 |
ience | +0.115 |
cious | +0.114 |
ages | +0.112 |
's | +0.108 |
Neg logit contributions | |
them | -0.072 |
wreck | -0.062 |
mate | -0.059 |
polar | -0.058 |
inn | -0.052 |
Token | he |
Token ID | 339 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ience | +0.028 |
� | +0.028 |
ages | +0.028 |
cious | +0.028 |
aul | +0.027 |
Neg logit contributions | |
them | -0.018 |
wreck | -0.015 |
mate | -0.014 |
polar | -0.014 |
rock | -0.013 |
Token | often |
Token ID | 1690 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
� | +0.021 |
cious | +0.021 |
ages | +0.020 |
ience | +0.020 |
's | +0.020 |
Neg logit contributions | |
them | -0.022 |
wreck | -0.019 |
mate | -0.019 |
polar | -0.019 |
inn | -0.018 |
Token | field |
Token ID | 2214 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
� | +0.022 |
cious | +0.021 |
's | +0.021 |
ages | +0.020 |
ience | +0.020 |
Neg logit contributions | |
them | -0.016 |
wreck | -0.015 |
mate | -0.014 |
polar | -0.014 |
inn | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
them | +0.003 |
wreck | +0.003 |
mate | +0.003 |
polar | +0.003 |
inn | +0.003 |
Neg logit contributions | |
� | -0.005 |
's | -0.004 |
cious | -0.004 |
ages | -0.004 |
ience | -0.004 |
Token | eating |
Token ID | 6600 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ages | +0.026 |
� | +0.025 |
ience | +0.025 |
cious | +0.025 |
aul | +0.025 |
Neg logit contributions | |
them | -0.021 |
wreck | -0.018 |
polar | -0.018 |
mate | -0.017 |
ramp | -0.016 |
Token | grass |
Token ID | 8701 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
� | +0.101 |
's | +0.097 |
cious | +0.093 |
ages | +0.092 |
aul | +0.090 |
Neg logit contributions | |
wreck | -0.078 |
them | -0.078 |
mate | -0.078 |
inn | -0.075 |
polar | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
� | +0.385 |
cious | +0.369 |
ience | +0.367 |
ages | +0.365 |
's | +0.363 |
Neg logit contributions | |
them | -0.266 |
wreck | -0.229 |
mate | -0.225 |
polar | -0.220 |
inn | -0.209 |
Token | feeling |
Token ID | 4203 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
ience | +0.037 |
� | +0.036 |
cious | +0.036 |
ages | +0.036 |
aul | +0.035 |
Neg logit contributions | |
them | -0.030 |
polar | -0.027 |
wreck | -0.026 |
his | -0.025 |
rock | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
� | +0.050 |
cious | +0.049 |
ages | +0.048 |
ience | +0.048 |
's | +0.047 |
Neg logit contributions | |
them | -0.044 |
wreck | -0.038 |
polar | -0.038 |
mate | -0.037 |
tow | -0.034 |
Token | wind |
Token ID | 2344 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
ages | +0.025 |
ience | +0.024 |
cious | +0.024 |
� | +0.023 |
Michelle | +0.023 |
Neg logit contributions | |
them | -0.018 |
polar | -0.017 |
wreck | -0.017 |
rock | -0.017 |
snowball | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
� | +0.331 |
cious | +0.323 |
ience | +0.320 |
ages | +0.319 |
's | +0.312 |
Neg logit contributions | |
them | -0.230 |
wreck | -0.202 |
mate | -0.196 |
polar | -0.192 |
inn | -0.181 |
Token | his |
Token ID | 465 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
� | +0.036 |
's | +0.032 |
Michelle | +0.032 |
Louise | +0.030 |
Denise | +0.030 |
Neg logit contributions | |
ramp | -0.022 |
wreck | -0.021 |
mate | -0.020 |
inn | -0.019 |
cubes | -0.019 |
Token | fur |
Token ID | 9230 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
them | +0.229 |
wreck | +0.207 |
polar | +0.205 |
rock | +0.201 |
his | +0.198 |
Neg logit contributions | |
� | -0.282 |
ience | -0.280 |
Michelle | -0.274 |
List | -0.257 |
cious | -0.256 |
Token | in |
Token ID | 287 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
� | +0.181 |
's | +0.175 |
cious | +0.151 |
ience | +0.148 |
Louise | +0.146 |
Neg logit contributions | |
polar | -0.160 |
wreck | -0.158 |
them | -0.157 |
mate | -0.156 |
inn | -0.156 |
Token | circles |
Token ID | 13332 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
� | +0.017 |
's | +0.015 |
decisions | +0.013 |
pays | +0.013 |
dedication | +0.012 |
Neg logit contributions | |
inn | -0.019 |
mate | -0.018 |
polar | -0.017 |
ramp | -0.017 |
wreck | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
them | +0.045 |
wreck | +0.041 |
mate | +0.040 |
polar | +0.039 |
inn | +0.037 |
Neg logit contributions | |
� | -0.063 |
's | -0.060 |
cious | -0.060 |
ages | -0.059 |
ience | -0.059 |
Token | cl |
Token ID | 537 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
� | +0.016 |
cious | +0.015 |
ages | +0.015 |
ience | +0.015 |
's | +0.015 |
Neg logit contributions | |
them | -0.014 |
wreck | -0.012 |
polar | -0.012 |
mate | -0.012 |
inn | -0.011 |
Token | apping |
Token ID | 5912 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
them | +0.218 |
wreck | +0.200 |
mate | +0.198 |
polar | +0.196 |
inn | +0.192 |
Neg logit contributions | |
� | -0.167 |
cious | -0.156 |
's | -0.155 |
ience | -0.155 |
ages | -0.154 |
Token | his |
Token ID | 465 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
wreck | +0.006 |
them | +0.006 |
mate | +0.005 |
polar | +0.005 |
inn | +0.005 |
Neg logit contributions | |
� | -0.014 |
's | -0.014 |
ages | -0.013 |
cious | -0.013 |
ience | -0.013 |
Token | fins |
Token ID | 42080 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
them | +0.269 |
wreck | +0.251 |
polar | +0.242 |
row | +0.237 |
match | +0.236 |
Neg logit contributions | |
� | -0.263 |
Michelle | -0.262 |
assy | -0.255 |
ience | -0.254 |
aul | -0.251 |
Token | together |
Token ID | 1978 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
� | +0.184 |
's | +0.176 |
cious | +0.173 |
ages | +0.172 |
ience | +0.170 |
Neg logit contributions | |
them | -0.136 |
wreck | -0.122 |
mate | -0.122 |
polar | -0.118 |
inn | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
them | +0.166 |
wreck | +0.153 |
mate | +0.150 |
polar | +0.149 |
inn | +0.142 |
Neg logit contributions | |
� | -0.222 |
's | -0.212 |
cious | -0.207 |
ages | -0.205 |
ience | -0.203 |
Token |
|
Token ID | 198 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
them | +0.004 |
inn | +0.003 |
polar | +0.003 |
tow | +0.003 |
wreck | +0.003 |
Neg logit contributions | |
cious | -0.005 |
ience | -0.005 |
ages | -0.005 |
� | -0.005 |
ita | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
� | +0.006 |
's | +0.005 |
ages | +0.004 |
cious | +0.004 |
aul | +0.004 |
Neg logit contributions | |
wreck | -0.008 |
mate | -0.007 |
them | -0.007 |
polar | -0.007 |
captain | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
them | +0.002 |
wreck | +0.001 |
mate | +0.001 |
polar | +0.001 |
inn | +0.001 |
Neg logit contributions | |
� | -0.002 |
's | -0.002 |
cious | -0.002 |
ages | -0.002 |
ience | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
them | +0.154 |
mate | +0.148 |
wreck | +0.142 |
polar | +0.141 |
tow | +0.140 |
Neg logit contributions | |
� | -0.125 |
's | -0.123 |
ience | -0.115 |
cious | -0.112 |
ages | -0.112 |
Token | always |
Token ID | 1464 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
them | +0.042 |
mate | +0.042 |
wreck | +0.040 |
polar | +0.039 |
ramp | +0.038 |
Neg logit contributions | |
� | -0.038 |
's | -0.037 |
cious | -0.034 |
ages | -0.034 |
ience | -0.033 |
Token | pushing |
Token ID | 7796 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
them | +0.064 |
wreck | +0.059 |
mate | +0.059 |
polar | +0.057 |
inn | +0.055 |
Neg logit contributions | |
� | -0.059 |
's | -0.056 |
cious | -0.055 |
ages | -0.055 |
ience | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
wreck | +0.110 |
polar | +0.109 |
tow | +0.107 |
mate | +0.106 |
ramp | +0.101 |
Neg logit contributions | |
� | -0.262 |
's | -0.259 |
cious | -0.234 |
ience | -0.234 |
ages | -0.234 |
Token | other |
Token ID | 584 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
's | +0.015 |
� | +0.015 |
cious | +0.014 |
ages | +0.013 |
ience | +0.013 |
Neg logit contributions | |
them | -0.010 |
mate | -0.010 |
tow | -0.009 |
inn | -0.009 |
wreck | -0.009 |
Token | fishes |
Token ID | 49765 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
them | +0.101 |
wreck | +0.092 |
mate | +0.091 |
polar | +0.087 |
inn | +0.085 |
Neg logit contributions | |
� | -0.134 |
's | -0.131 |
cious | -0.125 |
ages | -0.124 |
ience | -0.121 |
Token | away |
Token ID | 1497 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
� | +0.023 |
's | +0.023 |
ages | +0.020 |
cious | +0.020 |
ience | +0.020 |
Neg logit contributions | |
them | -0.020 |
polar | -0.020 |
tow | -0.019 |
mate | -0.019 |
wreck | -0.019 |
Token | when |
Token ID | 618 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
them | +0.196 |
polar | +0.185 |
wreck | +0.184 |
mate | +0.180 |
tow | +0.174 |
Neg logit contributions | |
� | -0.220 |
's | -0.214 |
ages | -0.201 |
cious | -0.199 |
ience | -0.194 |
Token | they |
Token ID | 484 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
� | +0.353 |
's | +0.337 |
cious | +0.335 |
ages | +0.333 |
ience | +0.330 |
Neg logit contributions | |
them | -0.224 |
wreck | -0.199 |
mate | -0.196 |
polar | -0.191 |
inn | -0.182 |
Token | tried |
Token ID | 3088 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
� | +0.107 |
's | +0.107 |
ience | +0.097 |
cious | +0.093 |
ages | +0.092 |
Neg logit contributions | |
them | -0.100 |
mate | -0.100 |
inn | -0.096 |
polar | -0.095 |
snowball | -0.093 |
Token | day |
Token ID | 1110 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
them | +0.036 |
wreck | +0.034 |
polar | +0.033 |
his | +0.032 |
inn | +0.032 |
Neg logit contributions | |
ience | -0.058 |
ages | -0.055 |
cious | -0.055 |
� | -0.052 |
Michelle | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
� | +0.168 |
cious | +0.163 |
ience | +0.162 |
ages | +0.162 |
's | +0.157 |
Neg logit contributions | |
them | -0.110 |
mate | -0.094 |
wreck | -0.092 |
polar | -0.088 |
inn | -0.087 |
Token | her |
Token ID | 607 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
's | +0.010 |
� | +0.010 |
Michelle | +0.009 |
cious | +0.008 |
ages | +0.008 |
Neg logit contributions | |
wreck | -0.022 |
polar | -0.021 |
them | -0.021 |
mate | -0.020 |
ramp | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
them | +0.055 |
wreck | +0.049 |
mate | +0.047 |
polar | +0.047 |
tow | +0.044 |
Neg logit contributions | |
� | -0.089 |
ience | -0.086 |
cious | -0.085 |
ages | -0.084 |
's | -0.081 |
Token | gave |
Token ID | 2921 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
� | +0.021 |
cious | +0.020 |
ages | +0.020 |
ience | +0.019 |
's | +0.019 |
Neg logit contributions | |
them | -0.022 |
wreck | -0.020 |
mate | -0.019 |
polar | -0.019 |
inn | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
� | +0.192 |
's | +0.185 |
ages | +0.175 |
cious | +0.174 |
ience | +0.174 |
Neg logit contributions | |
them | -0.172 |
wreck | -0.166 |
mate | -0.162 |
polar | -0.161 |
tow | -0.152 |
Token | an |
Token ID | 281 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
them | +0.062 |
wreck | +0.050 |
mate | +0.049 |
polar | +0.049 |
his | +0.047 |
Neg logit contributions | |
� | -0.085 |
cious | -0.084 |
ience | -0.082 |
ages | -0.082 |
's | -0.078 |
Token | ancient |
Token ID | 6156 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
� | +0.121 |
's | +0.115 |
ience | +0.104 |
ages | +0.100 |
cious | +0.100 |
Neg logit contributions | |
them | -0.157 |
mate | -0.146 |
wreck | -0.137 |
polar | -0.136 |
inn | -0.136 |
Token | card |
Token ID | 2657 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
� | +0.048 |
's | +0.047 |
cious | +0.045 |
ience | +0.044 |
ages | +0.044 |
Neg logit contributions | |
them | -0.045 |
mate | -0.039 |
inn | -0.039 |
wreck | -0.038 |
polar | -0.037 |
Token | that |
Token ID | 326 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
them | +0.111 |
mate | +0.100 |
wreck | +0.096 |
polar | +0.093 |
inn | +0.089 |
Neg logit contributions | |
� | -0.163 |
ience | -0.160 |
cious | -0.157 |
's | -0.151 |
ages | -0.151 |
Token | was |
Token ID | 373 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
them | +0.024 |
mate | +0.019 |
match | +0.019 |
wreck | +0.019 |
his | +0.018 |
Neg logit contributions | |
cious | -0.032 |
ience | -0.032 |
ages | -0.032 |
ita | -0.031 |
� | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
them | +0.098 |
mate | +0.093 |
polar | +0.091 |
wreck | +0.089 |
inn | +0.088 |
Neg logit contributions | |
's | -0.106 |
� | -0.105 |
cious | -0.096 |
ages | -0.093 |
ience | -0.090 |
Token | They |
Token ID | 1119 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
them | +0.003 |
wreck | +0.003 |
mate | +0.003 |
polar | +0.003 |
inn | +0.003 |
Neg logit contributions | |
� | -0.003 |
's | -0.003 |
cious | -0.003 |
ages | -0.003 |
ience | -0.003 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
mate | +0.030 |
inn | +0.029 |
them | +0.027 |
wreck | +0.027 |
ramp | +0.026 |
Neg logit contributions | |
's | -0.025 |
� | -0.024 |
cious | -0.021 |
ience | -0.020 |
listens | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
's | +0.129 |
� | +0.127 |
Michelle | +0.114 |
ages | +0.114 |
listens | +0.110 |
Neg logit contributions | |
wreck | -0.109 |
mate | -0.106 |
inn | -0.102 |
polar | -0.100 |
ramp | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
them | +0.060 |
wreck | +0.053 |
mate | +0.052 |
polar | +0.051 |
inn | +0.048 |
Neg logit contributions | |
� | -0.087 |
cious | -0.083 |
ages | -0.082 |
ience | -0.082 |
's | -0.082 |
Token | told |
Token ID | 1297 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
� | +0.024 |
cious | +0.022 |
ience | +0.022 |
ages | +0.022 |
aul | +0.021 |
Neg logit contributions | |
them | -0.023 |
wreck | -0.020 |
polar | -0.020 |
his | -0.019 |
mate | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
wreck | +0.006 |
mate | +0.006 |
ramp | +0.005 |
inn | +0.005 |
polar | +0.005 |
Neg logit contributions | |
� | -0.005 |
's | -0.005 |
ages | -0.005 |
Michelle | -0.005 |
listens | -0.005 |
Token | what |
Token ID | 644 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
them | +0.066 |
wreck | +0.054 |
polar | +0.052 |
mate | +0.050 |
his | +0.050 |
Neg logit contributions | |
� | -0.085 |
cious | -0.083 |
ience | -0.082 |
ages | -0.081 |
aul | -0.078 |
Token | happened |
Token ID | 3022 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ience | +0.100 |
ages | +0.096 |
cious | +0.094 |
� | +0.093 |
ita | +0.089 |
Neg logit contributions | |
them | -0.133 |
wreck | -0.117 |
polar | -0.113 |
mate | -0.113 |
his | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
� | +0.248 |
ience | +0.248 |
cious | +0.245 |
ages | +0.243 |
aul | +0.239 |
Neg logit contributions | |
them | -0.141 |
wreck | -0.112 |
mate | -0.108 |
polar | -0.101 |
inn | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
them | +0.004 |
wreck | +0.004 |
mate | +0.004 |
polar | +0.004 |
inn | +0.004 |
Neg logit contributions | |
� | -0.006 |
cious | -0.005 |
's | -0.005 |
ience | -0.005 |
ages | -0.005 |
Token | getting |
Token ID | 1972 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
them | +0.213 |
wreck | +0.187 |
polar | +0.184 |
mate | +0.179 |
inn | +0.170 |
Neg logit contributions | |
� | -0.244 |
ience | -0.238 |
cious | -0.236 |
ages | -0.233 |
's | -0.227 |
Token | ready |
Token ID | 3492 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
them | +0.024 |
wreck | +0.021 |
polar | +0.021 |
mate | +0.020 |
inn | +0.020 |
Neg logit contributions | |
� | -0.021 |
cious | -0.021 |
ience | -0.020 |
ages | -0.020 |
's | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
� | +0.103 |
cious | +0.098 |
's | +0.098 |
ages | +0.097 |
ience | +0.097 |
Neg logit contributions | |
them | -0.076 |
wreck | -0.067 |
mate | -0.066 |
polar | -0.064 |
inn | -0.062 |
Token | make |
Token ID | 787 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
� | +0.036 |
's | +0.035 |
cious | +0.034 |
ages | +0.034 |
ience | +0.033 |
Neg logit contributions | |
them | -0.024 |
mate | -0.022 |
wreck | -0.022 |
polar | -0.021 |
inn | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
them | +0.167 |
wreck | +0.129 |
polar | +0.126 |
his | +0.120 |
snowball | +0.118 |
Neg logit contributions | |
ience | -0.205 |
� | -0.205 |
cious | -0.203 |
ages | -0.192 |
listens | -0.188 |
Token | cup |
Token ID | 6508 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
� | +0.080 |
's | +0.077 |
cious | +0.072 |
ages | +0.072 |
ience | +0.071 |
Neg logit contributions | |
them | -0.066 |
mate | -0.061 |
inn | -0.059 |
wreck | -0.056 |
polar | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
them | +0.106 |
wreck | +0.095 |
mate | +0.094 |
polar | +0.093 |
inn | +0.088 |
Neg logit contributions | |
� | -0.163 |
's | -0.158 |
ages | -0.153 |
cious | -0.150 |
ience | -0.146 |
Token | hot |
Token ID | 3024 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
mate | +0.208 |
them | +0.196 |
wreck | +0.194 |
inn | +0.189 |
polar | +0.177 |
Neg logit contributions | |
� | -0.215 |
's | -0.207 |
ages | -0.190 |
cious | -0.187 |
aul | -0.182 |
Token | chocolate |
Token ID | 11311 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
� | +0.202 |
cious | +0.193 |
ience | +0.193 |
ages | +0.189 |
's | +0.188 |
Neg logit contributions | |
them | -0.181 |
wreck | -0.161 |
polar | -0.157 |
mate | -0.156 |
inn | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
them | +0.015 |
mate | +0.014 |
wreck | +0.014 |
polar | +0.014 |
inn | +0.013 |
Neg logit contributions | |
� | -0.020 |
's | -0.020 |
ages | -0.019 |
cious | -0.019 |
ience | -0.018 |
Token | The |
Token ID | 383 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
them | +0.002 |
tow | +0.001 |
wreck | +0.001 |
polar | +0.001 |
inn | +0.001 |
Neg logit contributions | |
ience | -0.002 |
cious | -0.002 |
ages | -0.002 |
� | -0.002 |
aul | -0.002 |
Token | watched |
Token ID | 7342 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
� | +0.229 |
cious | +0.224 |
ages | +0.219 |
ience | +0.216 |
's | +0.213 |
Neg logit contributions | |
them | -0.241 |
wreck | -0.217 |
mate | -0.211 |
polar | -0.210 |
inn | -0.198 |
Token | as |
Token ID | 355 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
� | +0.271 |
's | +0.258 |
cious | +0.254 |
ages | +0.253 |
ience | +0.251 |
Neg logit contributions | |
them | -0.154 |
wreck | -0.142 |
mate | -0.139 |
polar | -0.135 |
inn | -0.128 |
Token | everyone |
Token ID | 2506 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
them | +0.021 |
wreck | +0.016 |
mate | +0.016 |
polar | +0.016 |
tow | +0.015 |
Neg logit contributions | |
� | -0.033 |
ages | -0.032 |
cious | -0.032 |
's | -0.032 |
ience | -0.032 |
Token | took |
Token ID | 1718 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
� | +0.205 |
cious | +0.201 |
ages | +0.200 |
ience | +0.195 |
's | +0.193 |
Neg logit contributions | |
them | -0.183 |
wreck | -0.162 |
mate | -0.156 |
polar | -0.155 |
inn | -0.147 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
cious | +0.180 |
� | +0.180 |
ience | +0.178 |
ages | +0.177 |
's | +0.171 |
Neg logit contributions | |
them | -0.101 |
mate | -0.071 |
wreck | -0.069 |
polar | -0.066 |
tow | -0.063 |
Token | few |
Token ID | 1178 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
� | +0.103 |
's | +0.097 |
cious | +0.095 |
ience | +0.094 |
ages | +0.093 |
Neg logit contributions | |
them | -0.064 |
mate | -0.056 |
wreck | -0.055 |
polar | -0.054 |
inn | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
them | +0.361 |
wreck | +0.334 |
mate | +0.332 |
polar | +0.324 |
inn | +0.310 |
Neg logit contributions | |
� | -0.401 |
's | -0.378 |
ience | -0.373 |
cious | -0.372 |
ages | -0.371 |
Token |
|
Token ID | 198 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ience | +0.008 |
ages | +0.008 |
cious | +0.008 |
's | +0.008 |
� | +0.007 |
Neg logit contributions | |
them | -0.007 |
inn | -0.006 |
tow | -0.006 |
mate | -0.006 |
polar | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
� | +0.018 |
's | +0.016 |
cious | +0.015 |
ages | +0.015 |
aul | +0.014 |
Neg logit contributions | |
wreck | -0.020 |
them | -0.019 |
polar | -0.019 |
mate | -0.019 |
ramp | -0.018 |
Token | When |
Token ID | 2215 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
� | +0.017 |
's | +0.015 |
cious | +0.015 |
ages | +0.015 |
ience | +0.015 |
Neg logit contributions | |
them | -0.021 |
wreck | -0.019 |
polar | -0.019 |
mate | -0.019 |
inn | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
them | +0.064 |
mate | +0.048 |
wreck | +0.046 |
his | +0.045 |
polar | +0.045 |
Neg logit contributions | |
ages | -0.095 |
cious | -0.092 |
ience | -0.091 |
� | -0.090 |
aul | -0.088 |
Token | having |
Token ID | 1719 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
� | +0.019 |
cious | +0.017 |
's | +0.017 |
ages | +0.017 |
ience | +0.017 |
Neg logit contributions | |
them | -0.021 |
wreck | -0.019 |
mate | -0.018 |
polar | -0.018 |
inn | -0.017 |
Token | fun |
Token ID | 1257 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
them | +0.114 |
wreck | +0.104 |
mate | +0.103 |
polar | +0.100 |
inn | +0.097 |
Neg logit contributions | |
� | -0.138 |
's | -0.130 |
cious | -0.130 |
ages | -0.129 |
ience | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
them | +0.020 |
wreck | +0.019 |
mate | +0.019 |
polar | +0.018 |
inn | +0.018 |
Neg logit contributions | |
� | -0.027 |
's | -0.026 |
ages | -0.025 |
cious | -0.025 |
ience | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
them | +0.009 |
polar | +0.007 |
wreck | +0.007 |
his | +0.007 |
mate | +0.007 |
Neg logit contributions | |
ience | -0.008 |
ages | -0.008 |
cious | -0.008 |
� | -0.008 |
's | -0.007 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
� | +0.029 |
's | +0.027 |
cious | +0.027 |
ages | +0.026 |
ience | +0.026 |
Neg logit contributions | |
them | -0.033 |
wreck | -0.031 |
mate | -0.030 |
polar | -0.030 |
inn | -0.029 |
Token | them |
Token ID | 606 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
them | +0.205 |
wreck | +0.197 |
mate | +0.194 |
polar | +0.188 |
inn | +0.183 |
Neg logit contributions | |
� | -0.279 |
's | -0.269 |
cious | -0.260 |
ience | -0.259 |
ages | -0.258 |
Token | in |
Token ID | 287 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
them | +0.427 |
wreck | +0.381 |
mate | +0.370 |
polar | +0.365 |
inn | +0.345 |
Neg logit contributions | |
� | -0.505 |
cious | -0.487 |
ages | -0.484 |
ience | -0.479 |
's | -0.476 |
Token | their |
Token ID | 511 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
� | +0.012 |
's | +0.011 |
Michelle | +0.011 |
Louise | +0.010 |
Denise | +0.010 |
Neg logit contributions | |
inn | -0.013 |
wreck | -0.013 |
mate | -0.013 |
polar | -0.012 |
ramp | -0.012 |
Token | old |
Token ID | 1468 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
them | +0.191 |
wreck | +0.167 |
polar | +0.158 |
mate | +0.154 |
tow | +0.151 |
Neg logit contributions | |
� | -0.259 |
ages | -0.246 |
cious | -0.243 |
ience | -0.241 |
aul | -0.233 |
Token | house |
Token ID | 2156 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
� | +0.074 |
cious | +0.069 |
ience | +0.069 |
ages | +0.068 |
aul | +0.066 |
Neg logit contributions | |
them | -0.059 |
wreck | -0.053 |
mate | -0.051 |
polar | -0.050 |
ramp | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
them | +0.090 |
wreck | +0.080 |
mate | +0.078 |
polar | +0.076 |
inn | +0.072 |
Neg logit contributions | |
� | -0.123 |
cious | -0.117 |
's | -0.117 |
ages | -0.116 |
ience | -0.116 |
Token | lost |
Token ID | 2626 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
them | +0.002 |
wreck | +0.002 |
mate | +0.002 |
polar | +0.002 |
inn | +0.002 |
Neg logit contributions | |
� | -0.002 |
's | -0.002 |
cious | -0.002 |
ages | -0.002 |
ience | -0.002 |
Token | my |
Token ID | 616 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
them | +0.063 |
wreck | +0.060 |
inn | +0.060 |
mate | +0.060 |
polar | +0.058 |
Neg logit contributions | |
� | -0.078 |
's | -0.075 |
cious | -0.070 |
ience | -0.070 |
ages | -0.070 |
Token | way |
Token ID | 835 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
them | +0.115 |
mate | +0.101 |
inn | +0.101 |
wreck | +0.098 |
polar | +0.094 |
Neg logit contributions | |
� | -0.157 |
's | -0.152 |
ages | -0.146 |
cious | -0.146 |
ience | -0.144 |
Token | home |
Token ID | 1363 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
� | +0.201 |
's | +0.187 |
cious | +0.159 |
ience | +0.157 |
ages | +0.154 |
Neg logit contributions | |
them | -0.172 |
wreck | -0.166 |
mate | -0.164 |
polar | -0.164 |
inn | -0.160 |
Token | and |
Token ID | 290 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
them | +0.125 |
mate | +0.107 |
wreck | +0.106 |
polar | +0.098 |
control | +0.092 |
Neg logit contributions | |
cious | -0.211 |
� | -0.210 |
ience | -0.208 |
ages | -0.206 |
's | -0.199 |
Token | now |
Token ID | 783 |
Feature activation | -6.74e+00 |
Pos logit contributions | |
cious | +0.031 |
ages | +0.030 |
� | +0.029 |
aul | +0.029 |
ience | +0.029 |
Neg logit contributions | |
them | -0.034 |
wreck | -0.031 |
mate | -0.029 |
polar | -0.029 |
his | -0.027 |
Token | I |
Token ID | 314 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
them | +0.431 |
wreck | +0.364 |
his | +0.349 |
rock | +0.345 |
mate | +0.343 |
Neg logit contributions | |
ages | -0.478 |
cious | -0.475 |
aul | -0.463 |
ita | -0.444 |
assy | -0.439 |
Token | don |
Token ID | 836 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
� | +0.212 |
's | +0.199 |
ience | +0.191 |
ages | +0.188 |
cious | +0.187 |
Neg logit contributions | |
them | -0.181 |
mate | -0.164 |
wreck | -0.161 |
polar | -0.157 |
inn | -0.155 |
Token | 't |
Token ID | 470 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
� | +0.222 |
's | +0.210 |
cious | +0.205 |
ages | +0.205 |
ience | +0.204 |
Neg logit contributions | |
them | -0.139 |
wreck | -0.125 |
mate | -0.122 |
polar | -0.121 |
inn | -0.113 |
Token | own |
Token ID | 898 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
them | +0.256 |
mate | +0.234 |
wreck | +0.229 |
polar | +0.225 |
inn | +0.222 |
Neg logit contributions | |
� | -0.302 |
's | -0.281 |
cious | -0.266 |
ience | -0.262 |
ages | -0.262 |
Token | a |
Token ID | 257 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
them | +0.128 |
wreck | +0.109 |
polar | +0.101 |
mate | +0.097 |
his | +0.096 |
Neg logit contributions | |
ages | -0.184 |
cious | -0.180 |
aul | -0.180 |
� | -0.179 |
ience | -0.179 |
Token | measured |
Token ID | 8630 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
them | +0.015 |
wreck | +0.013 |
mate | +0.013 |
polar | +0.012 |
inn | +0.012 |
Neg logit contributions | |
� | -0.022 |
cious | -0.021 |
ages | -0.021 |
's | -0.021 |
ience | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
wreck | +0.027 |
polar | +0.026 |
them | +0.026 |
mate | +0.025 |
tow | +0.023 |
Neg logit contributions | |
� | -0.033 |
's | -0.033 |
ages | -0.030 |
cious | -0.030 |
aul | -0.029 |
Token | ingredients |
Token ID | 9391 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
ages | +0.029 |
cious | +0.029 |
ience | +0.028 |
� | +0.028 |
Michelle | +0.027 |
Neg logit contributions | |
them | -0.015 |
wreck | -0.015 |
mate | -0.013 |
ramp | -0.013 |
rock | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
� | +0.324 |
's | +0.308 |
cious | +0.297 |
ages | +0.297 |
ience | +0.289 |
Neg logit contributions | |
them | -0.245 |
wreck | -0.231 |
polar | -0.228 |
mate | -0.227 |
inn | -0.209 |
Token | blended |
Token ID | 32063 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
� | +0.039 |
cious | +0.039 |
ages | +0.038 |
ience | +0.038 |
's | +0.036 |
Neg logit contributions | |
them | -0.031 |
wreck | -0.026 |
mate | -0.025 |
polar | -0.024 |
inn | -0.023 |
Token | them |
Token ID | 606 |
Feature activation | -6.92e+00 |
Pos logit contributions | |
wreck | +0.132 |
mate | +0.131 |
polar | +0.131 |
tow | +0.115 |
them | +0.115 |
Neg logit contributions | |
� | -0.284 |
's | -0.275 |
ages | -0.263 |
cious | -0.258 |
aul | -0.256 |
Token | all |
Token ID | 477 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
them | +0.353 |
inn | +0.260 |
wreck | +0.260 |
mate | +0.257 |
his | +0.245 |
Neg logit contributions | |
ience | -0.561 |
cious | -0.547 |
� | -0.544 |
Michelle | -0.538 |
ages | -0.532 |
Token | together |
Token ID | 1978 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
them | +0.135 |
wreck | +0.117 |
mate | +0.115 |
polar | +0.111 |
inn | +0.111 |
Neg logit contributions | |
� | -0.172 |
cious | -0.168 |
ages | -0.166 |
ience | -0.165 |
's | -0.162 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
them | +0.148 |
wreck | +0.131 |
mate | +0.129 |
polar | +0.125 |
inn | +0.120 |
Neg logit contributions | |
� | -0.217 |
's | -0.206 |
cious | -0.206 |
ages | -0.205 |
ience | -0.203 |
Token | Finally |
Token ID | 9461 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
ience | +0.008 |
cious | +0.008 |
ages | +0.008 |
's | +0.008 |
� | +0.007 |
Neg logit contributions | |
them | -0.009 |
inn | -0.007 |
tow | -0.007 |
mate | -0.007 |
his | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
them | +0.055 |
wreck | +0.051 |
mate | +0.050 |
polar | +0.049 |
inn | +0.047 |
Neg logit contributions | |
� | -0.066 |
's | -0.062 |
cious | -0.061 |
ages | -0.061 |
ience | -0.060 |
Token | Pat |
Token ID | 3208 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
� | +0.018 |
's | +0.017 |
cious | +0.017 |
ages | +0.016 |
ience | +0.016 |
Neg logit contributions | |
them | -0.019 |
wreck | -0.018 |
mate | -0.017 |
polar | -0.017 |
inn | -0.017 |
Token | ches |
Token ID | 2052 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
� | +0.114 |
cious | +0.107 |
ages | +0.107 |
's | +0.106 |
ience | +0.104 |
Neg logit contributions | |
them | -0.142 |
wreck | -0.129 |
mate | -0.129 |
polar | -0.127 |
inn | -0.122 |
Token | got |
Token ID | 1392 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
� | +0.065 |
ages | +0.063 |
cious | +0.063 |
ience | +0.063 |
's | +0.061 |
Neg logit contributions | |
them | -0.059 |
wreck | -0.052 |
mate | -0.051 |
polar | -0.050 |
inn | -0.047 |
Token | an |
Token ID | 281 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
cious | +0.034 |
ience | +0.033 |
ages | +0.031 |
� | +0.031 |
aul | +0.031 |
Neg logit contributions | |
them | -0.027 |
wreck | -0.023 |
polar | -0.022 |
his | -0.022 |
inn | -0.021 |
Token | exciting |
Token ID | 7895 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
� | +0.168 |
's | +0.160 |
ages | +0.155 |
ience | +0.153 |
cious | +0.152 |
Neg logit contributions | |
them | -0.116 |
mate | -0.103 |
wreck | -0.097 |
polar | -0.094 |
tow | -0.093 |
Token | idea |
Token ID | 2126 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
� | +0.147 |
's | +0.143 |
cious | +0.139 |
ages | +0.138 |
ience | +0.136 |
Neg logit contributions | |
them | -0.099 |
mate | -0.086 |
wreck | -0.084 |
polar | -0.083 |
inn | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-03 |
Pos logit contributions | |
them | +0.336 |
wreck | +0.312 |
polar | +0.302 |
mate | +0.297 |
inn | +0.286 |
Neg logit contributions | |
� | -0.429 |
's | -0.412 |
cious | -0.396 |
ages | -0.395 |
ience | -0.381 |
Token | She |
Token ID | 1375 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ience | +0.000 |
� | +0.000 |
cious | +0.000 |
ages | +0.000 |
's | +0.000 |
Neg logit contributions | |
them | -0.000 |
polar | -0.000 |
mate | -0.000 |
wreck | -0.000 |
inn | -0.000 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
� | +0.041 |
's | +0.039 |
cious | +0.039 |
ages | +0.038 |
ience | +0.038 |
Neg logit contributions | |
them | -0.038 |
wreck | -0.034 |
mate | -0.034 |
polar | -0.033 |
inn | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
� | +0.106 |
ages | +0.106 |
ience | +0.106 |
cious | +0.105 |
aul | +0.105 |
Neg logit contributions | |
them | -0.059 |
his | -0.042 |
wreck | -0.041 |
mate | -0.039 |
rock | -0.037 |
Token | put |
Token ID | 1234 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
� | +0.039 |
's | +0.037 |
cious | +0.034 |
ages | +0.034 |
ience | +0.034 |
Neg logit contributions | |
them | -0.023 |
polar | -0.021 |
mate | -0.021 |
wreck | -0.021 |
inn | -0.020 |