TOP ACTIVATIONS
MAX = 3.762

leave your things behind . Someone might take them or use
they cannot find it . Someone else took their ship and
Look , a coin ! Someone put it there . Maybe
. That is bad . Someone will be mad . We
It is a bomb . Someone left it in the hut
is a fake one . Someone put it here for Halloween
It is a fire . Someone made it to cook food
" Help ! Help ! Someone help Tom !"
, but be careful . Someone might take it ." Tom
" Look , Mia . Someone was here before us ."
are making a mess . Someone can trip and fall .
was a prank balloon . Someone gave it to me as
the slide was wet . Someone had poured water on it
It is a statue . Someone made it for fun .
should go down soon . Someone might see us ."
floating in the air . Someone had let it go .
never played with the or nam ents again . They still
the box was gone . Someone had taken it away .
. This is candy . Someone left it in the park
and play with your or nam ents . Maybe you can

MIN ACTIVATIONS
MIN = -4.711

a little girl named Kay la . She was 3 years
was a girl named Kay la . She was very happy
was a girl named Car la who loved to rest .
a little girl named Mar la . She was walking in
the way home , Kay la started to imagine all the
knew it was her own fault . The girl
big ! Kay la wondered what was inside ,
far from home . Kay la told him she was just
a little girl named Is la . She loved basketball .
When Kay la got on the train ,
a little girl named Kay la . She woke up one
awn â s fault . The
â Kay la put the bell and the
family . Kay la was very happy that she
One day , Kay la decided to take the subway
a little girl named Car la . She was three years
was a girl named Kay la . Kay la went out
spraying all around . Mar la was so excited - she
year old girl named Kay la . Every day , Kay
her . He asked Kay la what she was doing so

INTERVAL 1.644 - 3.762
CONTAINS 1.516%

that day on , she saved every penny she got and
Ben say , " You too , lady ! Bye !"
perfect place to learn and explore new things .
not listen . They were too playful . They kept playing
said . " We can fix it together ."

INTERVAL -0.474 - 1.644
CONTAINS 77.695%

and said , " Good luck , little one . I
important to not let others tease you into doing something that
they were done , they put the toys back in the
of a sudden , the bunny noticed a strange crack in
, Anna and Ben ," the bird says . " I

INTERVAL -2.593 - -0.474
CONTAINS 20.695%

of the sport . After that day , she went back
The end . <|endoftext|> Once upon a time there was a
the castle and took the princess away . The king and
. It was green and yellow and had a lightning bolt
a poor girl . She wanted very much to have a

INTERVAL -4.711 - -2.593
CONTAINS 0.095%

parents said no . Id a felt very sad . So
Once there was a fle a who wanted to quit .
and not be too nos y . And they all lived
it and sees the smile y face and the heart .
He saw a large tr amp oline . It was round
Token leave
Token ID2666
Feature activation+2.57e-01

Pos logit contributions
lights+0.058
 forth+0.047
bel+0.045
kins+0.045
ized+0.045
Neg logit contributions
 nine-0.029
-0.027
 thirteen-0.027
ching-0.025
upid-0.025
Token your
Token ID534
Feature activation-1.54e+00

Pos logit contributions
lights+0.036
 forth+0.029
kins+0.029
ized+0.028
nam+0.028
Neg logit contributions
 nine-0.015
 thirteen-0.014
-0.014
ching-0.013
upid-0.013
Token things
Token ID1243
Feature activation+3.63e-01

Pos logit contributions
 nine+0.122
+0.118
 a+0.115
 like+0.112
ching+0.111
Neg logit contributions
lights-0.179
bel-0.137
ized-0.134
ths-0.133
apy-0.133
Token behind
Token ID2157
Feature activation+1.58e+00

Pos logit contributions
lights+0.045
 forth+0.037
ized+0.036
kins+0.036
bel+0.034
Neg logit contributions
 nine-0.027
 thirteen-0.025
upid-0.024
ching-0.022
-0.022
Token.
Token ID13
Feature activation+8.50e-01

Pos logit contributions
lights+0.213
 forth+0.171
kins+0.169
ized+0.167
bel+0.159
Neg logit contributions
 nine-0.096
 thirteen-0.095
ching-0.084
-0.081
upid-0.079
Token Someone
Token ID17877
Feature activation+3.56e+00

Pos logit contributions
lights+0.105
Really+0.079
apy+0.077
kins+0.076
nam+0.076
Neg logit contributions
 nine-0.059
ching-0.056
 thirteen-0.054
 enough-0.052
-0.051
Token might
Token ID1244
Feature activation+1.20e-01

Pos logit contributions
lights+0.445
 forth+0.374
kins+0.366
ized+0.366
bel+0.365
Neg logit contributions
 thirteen-0.223
 nine-0.222
upid-0.192
-0.174
ching-0.169
Token take
Token ID1011
Feature activation-5.25e-01

Pos logit contributions
lights+0.012
 forth+0.010
bel+0.010
kins+0.010
ized+0.010
Neg logit contributions
 nine-0.009
 thirteen-0.009
one-0.008
-0.008
ff-0.008
Token them
Token ID606
Feature activation-6.26e-01

Pos logit contributions
 thirteen+0.040
 nine+0.040
+0.038
upid+0.035
ching+0.034
Neg logit contributions
lights-0.060
 forth-0.048
kins-0.045
bel-0.045
ized-0.045
Token or
Token ID393
Feature activation-4.65e-01

Pos logit contributions
 thirteen+0.045
 nine+0.044
ching+0.037
upid+0.037
 knows+0.037
Neg logit contributions
lights-0.077
 forth-0.064
ized-0.061
bel-0.060
uddle-0.059
Token use
Token ID779
Feature activation-3.26e-01

Pos logit contributions
 nine+0.031
+0.030
 thirteen+0.027
 like+0.027
 a+0.027
Neg logit contributions
lights-0.063
kins-0.049
ized-0.048
uddle-0.048
 forth-0.048
Token they
Token ID484
Feature activation+1.01e+00

Pos logit contributions
lights+0.206
 forth+0.153
bel+0.153
ized+0.151
kins+0.150
Neg logit contributions
 nine-0.157
-0.151
 thirteen-0.144
 like-0.139
ching-0.137
Token cannot
Token ID2314
Feature activation+4.22e-01

Pos logit contributions
lights+0.130
 forth+0.114
kins+0.112
uddle+0.108
ized+0.105
Neg logit contributions
 nine-0.057
ching-0.052
 thirteen-0.051
-0.050
one-0.049
Token find
Token ID1064
Feature activation+1.28e+00

Pos logit contributions
lights+0.065
 forth+0.053
bel+0.052
kins+0.052
ized+0.052
Neg logit contributions
 nine-0.020
-0.019
 thirteen-0.017
ching-0.016
 like-0.016
Token it
Token ID340
Feature activation+6.90e-01

Pos logit contributions
lights+0.178
 forth+0.141
kins+0.139
ized+0.138
bel+0.137
Neg logit contributions
 nine-0.077
-0.075
 thirteen-0.071
ching-0.068
upid-0.066
Token.
Token ID13
Feature activation+7.12e-01

Pos logit contributions
lights+0.087
 forth+0.069
kins+0.068
ized+0.066
bel+0.065
Neg logit contributions
 nine-0.048
 thirteen-0.046
-0.046
upid-0.042
ching-0.042
Token Someone
Token ID17877
Feature activation+3.55e+00

Pos logit contributions
lights+0.092
 forth+0.071
kins+0.070
bel+0.070
ized+0.069
Neg logit contributions
 nine-0.051
-0.047
 thirteen-0.046
ching-0.045
upid-0.043
Token else
Token ID2073
Feature activation+1.62e+00

Pos logit contributions
lights+0.456
 forth+0.376
bel+0.367
kins+0.367
ized+0.359
Neg logit contributions
 nine-0.224
 thirteen-0.218
-0.211
upid-0.201
ching-0.194
Token took
Token ID1718
Feature activation-2.84e-01

Pos logit contributions
lights+0.227
 forth+0.188
kins+0.187
bel+0.186
uddle+0.178
Neg logit contributions
 nine-0.087
 thirteen-0.082
-0.077
ching-0.074
upid-0.071
Token their
Token ID511
Feature activation+1.05e+00

Pos logit contributions
+0.021
 nine+0.020
 thirteen+0.020
ching+0.019
upid+0.019
Neg logit contributions
lights-0.034
 forth-0.027
kins-0.026
ized-0.025
nam-0.025
Token ship
Token ID4074
Feature activation+7.96e-01

Pos logit contributions
lights+0.129
 forth+0.097
ized+0.097
bel+0.095
ths+0.094
Neg logit contributions
 nine-0.086
-0.078
 thirteen-0.077
 like-0.074
 a-0.073
Token and
Token ID290
Feature activation+3.73e-01

Pos logit contributions
lights+0.106
bel+0.083
kins+0.082
 forth+0.082
ized+0.081
Neg logit contributions
 nine-0.053
 thirteen-0.052
-0.052
upid-0.048
ching-0.046
TokenLook
Token ID8567
Feature activation-3.83e-01

Pos logit contributions
lights+0.159
 forth+0.122
kins+0.119
bel+0.119
ized+0.118
Neg logit contributions
 nine-0.102
-0.097
 thirteen-0.093
ching-0.090
upid-0.088
Token,
Token ID11
Feature activation+1.06e-01

Pos logit contributions
 nine+0.013
+0.012
 thirteen+0.011
ching+0.010
upid+0.010
Neg logit contributions
lights-0.063
 forth-0.052
kins-0.052
bel-0.052
ized-0.051
Token a
Token ID257
Feature activation+6.82e-01

Pos logit contributions
lights+0.010
nam+0.008
kins+0.008
 forth+0.008
apy+0.008
Neg logit contributions
ching-0.010
upid-0.009
 thirteen-0.009
 nine-0.009
-0.009
Token coin
Token ID10752
Feature activation+3.82e-01

Pos logit contributions
lights+0.081
 forth+0.062
kins+0.062
uddle+0.061
bel+0.061
Neg logit contributions
 nine-0.053
-0.052
 thirteen-0.049
ching-0.048
upid-0.047
Token!
Token ID0
Feature activation+1.88e-01

Pos logit contributions
lights+0.048
kins+0.041
uddle+0.039
 forth+0.038
bel+0.037
Neg logit contributions
 nine-0.024
 thirteen-0.023
-0.023
ching-0.022
upid-0.022
Token Someone
Token ID17877
Feature activation+3.54e+00

Pos logit contributions
lights+0.023
Really+0.018
bel+0.018
apy+0.018
kins+0.018
Neg logit contributions
 nine-0.012
ching-0.012
 thirteen-0.011
-0.011
upid-0.011
Token put
Token ID1234
Feature activation-4.50e-02

Pos logit contributions
lights+0.364
 forth+0.310
kins+0.309
ized+0.306
uddle+0.305
Neg logit contributions
 thirteen-0.258
 nine-0.255
upid-0.244
ching-0.225
-0.221
Token it
Token ID340
Feature activation+7.03e-01

Pos logit contributions
+0.003
 nine+0.003
ching+0.003
upid+0.003
 thirteen+0.003
Neg logit contributions
lights-0.006
 forth-0.005
kins-0.005
nam-0.005
ized-0.004
Token there
Token ID612
Feature activation+7.09e-01

Pos logit contributions
lights+0.086
 forth+0.068
bel+0.066
kins+0.066
ized+0.064
Neg logit contributions
 nine-0.051
 thirteen-0.050
-0.050
ching-0.048
upid-0.047
Token.
Token ID13
Feature activation+7.69e-01

Pos logit contributions
lights+0.087
kins+0.068
 forth+0.068
bel+0.067
uddle+0.067
Neg logit contributions
 thirteen-0.046
 nine-0.044
ching-0.044
-0.040
upid-0.038
Token Maybe
Token ID6674
Feature activation+4.09e-01

Pos logit contributions
lights+0.094
Really+0.072
bel+0.071
nam+0.071
kins+0.070
Neg logit contributions
 nine-0.055
ching-0.054
 thirteen-0.050
upid-0.050
-0.049
Token.
Token ID13
Feature activation+8.40e-01

Pos logit contributions
 nine+0.019
 thirteen+0.018
ching+0.017
upid+0.016
+0.016
Neg logit contributions
lights-0.043
bel-0.033
 forth-0.033
kins-0.032
ized-0.032
Token That
Token ID1320
Feature activation-4.38e-01

Pos logit contributions
lights+0.111
 forth+0.087
kins+0.085
bel+0.085
ized+0.085
Neg logit contributions
 nine-0.055
-0.050
 thirteen-0.050
ching-0.049
 like-0.046
Token is
Token ID318
Feature activation-1.51e+00

Pos logit contributions
 nine+0.032
 thirteen+0.030
+0.028
upid+0.028
ching+0.027
Neg logit contributions
lights-0.055
 forth-0.044
ized-0.042
bel-0.042
kins-0.042
Token bad
Token ID2089
Feature activation-5.99e-01

Pos logit contributions
 nine+0.072
+0.068
 a+0.061
 thirteen+0.061
 like+0.060
Neg logit contributions
lights-0.236
kins-0.190
ized-0.190
bel-0.189
uddle-0.188
Token.
Token ID13
Feature activation+8.64e-01

Pos logit contributions
 nine+0.033
+0.031
 thirteen+0.029
ching+0.028
upid+0.027
Neg logit contributions
lights-0.087
 forth-0.070
kins-0.069
bel-0.069
ized-0.069
Token Someone
Token ID17877
Feature activation+3.53e+00

Pos logit contributions
lights+0.110
 forth+0.085
kins+0.084
bel+0.083
apy+0.083
Neg logit contributions
 nine-0.060
 thirteen-0.055
-0.054
ching-0.054
upid-0.051
Token will
Token ID481
Feature activation-1.95e+00

Pos logit contributions
lights+0.425
 forth+0.351
bel+0.344
ized+0.341
kins+0.336
Neg logit contributions
 nine-0.248
 thirteen-0.243
-0.228
upid-0.220
ching-0.208
Token be
Token ID307
Feature activation+1.65e+00

Pos logit contributions
 nine+0.153
 thirteen+0.147
+0.140
ching+0.131
upid+0.130
Neg logit contributions
lights-0.224
 forth-0.182
bel-0.174
ized-0.174
kins-0.170
Token mad
Token ID8805
Feature activation-2.65e-01

Pos logit contributions
lights+0.196
 forth+0.155
ized+0.149
bel+0.148
kins+0.148
Neg logit contributions
 nine-0.130
-0.127
 thirteen-0.122
upid-0.117
ching-0.115
Token.
Token ID13
Feature activation+8.82e-01

Pos logit contributions
 nine+0.018
 thirteen+0.017
+0.017
upid+0.016
ching+0.016
Neg logit contributions
lights-0.035
 forth-0.028
ized-0.026
kins-0.026
bel-0.026
Token We
Token ID775
Feature activation+8.14e-01

Pos logit contributions
lights+0.108
 forth+0.082
kins+0.081
bel+0.081
apy+0.080
Neg logit contributions
 nine-0.066
 thirteen-0.061
ching-0.061
-0.060
upid-0.058
Token It
Token ID632
Feature activation+1.02e+00

Pos logit contributions
lights+0.065
bel+0.051
 forth+0.051
kins+0.051
ized+0.051
Neg logit contributions
 nine-0.021
-0.019
 thirteen-0.018
ching-0.018
upid-0.016
Token is
Token ID318
Feature activation-1.60e+00

Pos logit contributions
lights+0.147
uddle+0.121
 forth+0.121
kins+0.115
ized+0.115
Neg logit contributions
 nine-0.048
upid-0.043
ching-0.040
 thirteen-0.039
-0.037
Token a
Token ID257
Feature activation+6.31e-01

Pos logit contributions
 nine+0.085
+0.080
 thirteen+0.075
ching+0.072
upid+0.070
Neg logit contributions
lights-0.234
 forth-0.189
kins-0.186
bel-0.185
ized-0.184
Token bomb
Token ID5194
Feature activation+8.39e-01

Pos logit contributions
lights+0.081
 forth+0.063
kins+0.062
bel+0.062
ized+0.062
Neg logit contributions
 nine-0.045
-0.043
 thirteen-0.041
ching-0.040
 like-0.039
Token.
Token ID13
Feature activation+5.17e-01

Pos logit contributions
lights+0.116
 forth+0.093
kins+0.091
bel+0.090
ized+0.089
Neg logit contributions
 nine-0.052
-0.048
 thirteen-0.047
upid-0.046
ching-0.043
Token Someone
Token ID17877
Feature activation+3.51e+00

Pos logit contributions
lights+0.077
bel+0.060
kins+0.060
apy+0.060
ized+0.060
Neg logit contributions
 nine-0.025
-0.023
 thirteen-0.023
ching-0.023
upid-0.020
Token left
Token ID1364
Feature activation-1.87e-01

Pos logit contributions
lights+0.422
 forth+0.345
bel+0.336
kins+0.334
ized+0.334
Neg logit contributions
 nine-0.238
 thirteen-0.231
-0.223
upid-0.217
ching-0.206
Token it
Token ID340
Feature activation+6.25e-01

Pos logit contributions
+0.013
 nine+0.012
ching+0.012
 thirteen+0.012
upid+0.011
Neg logit contributions
lights-0.024
kins-0.019
 forth-0.019
ized-0.018
nam-0.018
Token in
Token ID287
Feature activation+1.25e+00

Pos logit contributions
lights+0.069
 forth+0.056
ized+0.052
kins+0.052
bel+0.051
Neg logit contributions
 thirteen-0.050
 nine-0.049
-0.048
upid-0.047
ching-0.045
Token the
Token ID262
Feature activation+1.40e-01

Pos logit contributions
lights+0.171
kins+0.140
 forth+0.133
ized+0.131
nam+0.130
Neg logit contributions
 thirteen-0.073
-0.068
 nine-0.068
ching-0.064
upid-0.059
Token hut
Token ID40812
Feature activation+2.01e+00

Pos logit contributions
lights+0.015
 forth+0.011
uddle+0.011
kins+0.011
bel+0.011
Neg logit contributions
 nine-0.013
-0.012
 thirteen-0.012
ching-0.012
upid-0.011
Token is
Token ID318
Feature activation-1.57e+00

Pos logit contributions
lights+0.141
kins+0.116
 forth+0.115
uddle+0.114
ized+0.111
Neg logit contributions
 nine-0.064
upid-0.056
 thirteen-0.054
ching-0.046
 enough-0.046
Token a
Token ID257
Feature activation+6.38e-01

Pos logit contributions
 nine+0.079
upid+0.073
+0.073
ching+0.072
 thirteen+0.070
Neg logit contributions
lights-0.220
nam-0.180
kins-0.179
 forth-0.179
bel-0.168
Token fake
Token ID8390
Feature activation-1.65e+00

Pos logit contributions
lights+0.079
 forth+0.061
kins+0.060
bel+0.060
ized+0.059
Neg logit contributions
 nine-0.048
-0.045
 thirteen-0.044
ching-0.042
upid-0.041
Token one
Token ID530
Feature activation-3.11e-01

Pos logit contributions
 nine+0.131
+0.127
 thirteen+0.123
ching+0.118
upid+0.116
Neg logit contributions
lights-0.194
 forth-0.150
kins-0.146
bel-0.144
ized-0.144
Token.
Token ID13
Feature activation+8.04e-01

Pos logit contributions
 nine+0.021
 thirteen+0.020
upid+0.020
ching+0.019
+0.019
Neg logit contributions
lights-0.038
kins-0.031
 forth-0.030
ized-0.028
bel-0.028
Token Someone
Token ID17877
Feature activation+3.48e+00

Pos logit contributions
lights+0.101
Really+0.079
apy+0.078
 Sorry+0.075
bel+0.073
Neg logit contributions
 nine-0.053
ching-0.051
upid-0.046
 thirteen-0.046
 enough-0.045
Token put
Token ID1234
Feature activation-1.49e-01

Pos logit contributions
lights+0.406
kins+0.333
 forth+0.332
ized+0.328
bel+0.328
Neg logit contributions
 nine-0.239
 thirteen-0.237
upid-0.220
-0.203
ching-0.199
Token it
Token ID340
Feature activation+6.39e-01

Pos logit contributions
 nine+0.009
+0.009
 thirteen+0.009
ching+0.009
upid+0.008
Neg logit contributions
lights-0.019
 forth-0.016
kins-0.015
ized-0.015
nam-0.015
Token here
Token ID994
Feature activation-4.92e-01

Pos logit contributions
lights+0.079
 forth+0.063
bel+0.062
kins+0.062
ized+0.060
Neg logit contributions
 nine-0.045
 thirteen-0.044
-0.044
upid-0.041
ching-0.041
Token for
Token ID329
Feature activation+2.66e-01

Pos logit contributions
 thirteen+0.028
 nine+0.028
ching+0.027
upid+0.026
+0.026
Neg logit contributions
lights-0.066
kins-0.053
 forth-0.053
bel-0.052
ized-0.052
Token Halloween
Token ID16032
Feature activation+5.56e-01

Pos logit contributions
lights+0.036
 forth+0.029
kins+0.029
bel+0.028
ized+0.028
Neg logit contributions
 nine-0.017
-0.016
 thirteen-0.015
ching-0.014
upid-0.014
Token It
Token ID632
Feature activation+1.06e+00

Pos logit contributions
lights+0.102
apy+0.079
Really+0.078
bel+0.077
kins+0.077
Neg logit contributions
 nine-0.038
ching-0.035
 thirteen-0.033
-0.032
upid-0.031
Token is
Token ID318
Feature activation-1.61e+00

Pos logit contributions
lights+0.163
 forth+0.133
kins+0.132
ized+0.130
uddle+0.130
Neg logit contributions
 nine-0.049
upid-0.039
 thirteen-0.039
ching-0.037
-0.035
Token a
Token ID257
Feature activation+5.68e-01

Pos logit contributions
 nine+0.100
ching+0.094
+0.094
upid+0.091
 thirteen+0.090
Neg logit contributions
lights-0.217
 forth-0.172
kins-0.169
nam-0.165
bel-0.163
Token fire
Token ID2046
Feature activation-1.82e-01

Pos logit contributions
lights+0.070
 forth+0.054
kins+0.053
bel+0.053
ized+0.053
Neg logit contributions
 nine-0.043
-0.041
 thirteen-0.039
ching-0.038
upid-0.037
Token.
Token ID13
Feature activation+7.31e-01

Pos logit contributions
 nine+0.012
+0.011
upid+0.011
ching+0.011
 thirteen+0.011
Neg logit contributions
lights-0.025
 forth-0.020
kins-0.019
bel-0.019
uddle-0.018
Token Someone
Token ID17877
Feature activation+3.47e+00

Pos logit contributions
lights+0.101
apy+0.078
kins+0.076
bel+0.076
Really+0.076
Neg logit contributions
 nine-0.042
ching-0.039
 thirteen-0.037
-0.036
upid-0.036
Token made
Token ID925
Feature activation-6.26e-01

Pos logit contributions
lights+0.405
 forth+0.330
kins+0.327
ized+0.323
bel+0.320
Neg logit contributions
 nine-0.238
 thirteen-0.233
upid-0.222
ching-0.205
-0.200
Token it
Token ID340
Feature activation+6.71e-01

Pos logit contributions
 nine+0.042
 thirteen+0.040
+0.040
ching+0.040
ny+0.036
Neg logit contributions
lights-0.076
kins-0.058
apy-0.057
 forth-0.057
ized-0.055
Token to
Token ID284
Feature activation+1.01e-01

Pos logit contributions
lights+0.088
bel+0.070
 forth+0.068
kins+0.066
ized+0.065
Neg logit contributions
 nine-0.045
 thirteen-0.041
-0.039
ching-0.039
upid-0.039
Token cook
Token ID4255
Feature activation+5.54e-01

Pos logit contributions
lights+0.013
 forth+0.011
bel+0.010
kins+0.010
ized+0.010
Neg logit contributions
 nine-0.007
-0.006
 thirteen-0.006
ching-0.006
upid-0.006
Token food
Token ID2057
Feature activation+8.88e-01

Pos logit contributions
lights+0.074
kins+0.061
 forth+0.059
ized+0.057
bel+0.055
Neg logit contributions
 nine-0.036
ching-0.033
upid-0.032
 thirteen-0.032
-0.032
Token"
Token ID1
Feature activation-4.67e-01

Pos logit contributions
lights+0.030
 forth+0.023
kins+0.023
bel+0.023
ized+0.023
Neg logit contributions
 nine-0.014
-0.013
 thirteen-0.012
ching-0.012
upid-0.011
TokenHelp
Token ID22087
Feature activation+1.09e+00

Pos logit contributions
 nine+0.026
+0.025
 a+0.023
ching+0.023
 never+0.022
Neg logit contributions
lights-0.074
uddle-0.057
kins-0.056
nam-0.055
ized-0.055
Token!
Token ID0
Feature activation+2.87e-01

Pos logit contributions
lights+0.142
 forth+0.130
uddle+0.116
ized+0.115
kins+0.115
Neg logit contributions
 thirteen-0.061
 nine-0.059
-0.058
ching-0.056
upid-0.052
Token Help
Token ID10478
Feature activation+1.14e+00

Pos logit contributions
lights+0.037
bel+0.029
 forth+0.029
apy+0.029
uddle+0.029
Neg logit contributions
 nine-0.018
 thirteen-0.017
-0.017
ching-0.017
 like-0.016
Token!
Token ID0
Feature activation+3.12e-01

Pos logit contributions
lights+0.144
 forth+0.126
uddle+0.119
kins+0.110
ths+0.109
Neg logit contributions
 thirteen-0.072
 nine-0.070
ching-0.064
-0.063
upid-0.059
Token Someone
Token ID17877
Feature activation+3.47e+00

Pos logit contributions
lights+0.040
 forth+0.032
bel+0.032
apy+0.031
kins+0.031
Neg logit contributions
 nine-0.020
 thirteen-0.019
-0.018
ching-0.018
 like-0.018
Token help
Token ID1037
Feature activation+9.81e-01

Pos logit contributions
lights+0.420
 forth+0.362
bel+0.350
uddle+0.347
ized+0.345
Neg logit contributions
 thirteen-0.220
 nine-0.219
upid-0.195
-0.195
ching-0.181
Token Tom
Token ID4186
Feature activation-3.12e-02

Pos logit contributions
lights+0.125
 forth+0.109
kins+0.099
ized+0.099
uddle+0.099
Neg logit contributions
 nine-0.061
 thirteen-0.060
-0.056
ching-0.056
upid-0.052
Token!"
Token ID2474
Feature activation-8.39e-01

Pos logit contributions
 thirteen+0.002
 nine+0.002
upid+0.002
+0.002
 fourteen+0.002
Neg logit contributions
lights-0.004
 forth-0.003
uddle-0.003
ized-0.003
bel-0.003
Token
Token ID198
Feature activation+3.35e-01

Pos logit contributions
 nine+0.036
+0.034
 a+0.029
 like+0.029
 thirteen+0.028
Neg logit contributions
lights-0.134
 forth-0.110
kins-0.109
ized-0.108
bel-0.107
Token
Token ID198
Feature activation+2.89e-01

Pos logit contributions
lights+0.054
 forth+0.044
bel+0.044
kins+0.044
ized+0.044
Neg logit contributions
 nine-0.013
-0.011
 thirteen-0.011
ching-0.010
upid-0.010
Token,
Token ID11
Feature activation+1.11e-01

Pos logit contributions
lights+0.008
 forth+0.006
kins+0.006
ized+0.006
bel+0.006
Neg logit contributions
 nine-0.002
-0.002
 thirteen-0.002
ching-0.001
upid-0.001
Token but
Token ID475
Feature activation+1.26e+00

Pos logit contributions
lights+0.015
 forth+0.012
kins+0.012
bel+0.012
ized+0.012
Neg logit contributions
 nine-0.007
-0.006
 thirteen-0.006
ching-0.006
upid-0.006
Token be
Token ID307
Feature activation+1.57e+00

Pos logit contributions
lights+0.164
bel+0.124
ized+0.124
kins+0.122
uddle+0.120
Neg logit contributions
 nine-0.095
-0.092
 like-0.085
 thirteen-0.085
 a-0.083
Token careful
Token ID8161
Feature activation-1.28e-02

Pos logit contributions
lights+0.180
 forth+0.162
kins+0.151
nam+0.148
bel+0.146
Neg logit contributions
-0.112
upid-0.110
 thirteen-0.108
 nine-0.105
ching-0.099
Token.
Token ID13
Feature activation+6.41e-01

Pos logit contributions
 nine+0.001
 thirteen+0.001
upid+0.001
ching+0.001
+0.001
Neg logit contributions
lights-0.002
kins-0.001
 forth-0.001
bel-0.001
we-0.001
Token Someone
Token ID17877
Feature activation+3.45e+00

Pos logit contributions
lights+0.086
 forth+0.068
kins+0.067
bel+0.067
ized+0.067
Neg logit contributions
 nine-0.042
-0.040
 thirteen-0.038
ching-0.036
 like-0.036
Token might
Token ID1244
Feature activation-3.03e-02

Pos logit contributions
lights+0.396
 forth+0.344
uddle+0.338
bel+0.336
ized+0.334
Neg logit contributions
 thirteen-0.230
 nine-0.220
upid-0.204
-0.193
ching-0.186
Token take
Token ID1011
Feature activation-5.73e-01

Pos logit contributions
 thirteen+0.002
 nine+0.002
+0.002
upid+0.002
ching+0.002
Neg logit contributions
lights-0.003
 forth-0.003
bel-0.002
ized-0.002
kins-0.002
Token it
Token ID340
Feature activation+5.77e-01

Pos logit contributions
 thirteen+0.043
 nine+0.041
+0.041
ching+0.040
upid+0.038
Neg logit contributions
lights-0.062
 forth-0.054
nam-0.048
ized-0.047
kins-0.046
Token."
Token ID526
Feature activation-1.01e+00

Pos logit contributions
lights+0.069
 forth+0.054
bel+0.052
kins+0.051
uddle+0.051
Neg logit contributions
 thirteen-0.043
-0.040
 nine-0.039
ching-0.037
 knows-0.037
Token Tom
Token ID4186
Feature activation-8.06e-02

Pos logit contributions
 nine+0.038
+0.034
 a+0.030
 like+0.029
 thirteen+0.026
Neg logit contributions
lights-0.165
ized-0.140
 forth-0.140
kins-0.139
nam-0.137
Token "
Token ID366
Feature activation+1.20e+00

Pos logit contributions
 nine+0.002
upid+0.002
 thirteen+0.002
ching+0.002
+0.002
Neg logit contributions
lights-0.003
kins-0.002
Really-0.002
bel-0.002
apy-0.002
TokenLook
Token ID8567
Feature activation-4.67e-01

Pos logit contributions
lights+0.147
 forth+0.111
kins+0.111
ized+0.108
uddle+0.108
Neg logit contributions
 nine-0.096
-0.093
 thirteen-0.089
ching-0.085
 like-0.084
Token,
Token ID11
Feature activation+2.83e-02

Pos logit contributions
 nine+0.018
+0.016
 thirteen+0.015
ching+0.014
upid+0.013
Neg logit contributions
lights-0.075
 forth-0.063
kins-0.062
ized-0.061
uddle-0.061
Token Mia
Token ID32189
Feature activation+5.37e-01

Pos logit contributions
lights+0.004
 forth+0.003
nam+0.003
kins+0.003
bel+0.003
Neg logit contributions
ching-0.002
 nine-0.002
 thirteen-0.002
upid-0.002
-0.002
Token.
Token ID13
Feature activation+7.68e-01

Pos logit contributions
lights+0.065
kins+0.057
 forth+0.054
uddle+0.051
ies+0.051
Neg logit contributions
 thirteen-0.036
 nine-0.035
upid-0.034
ching-0.032
-0.030
Token Someone
Token ID17877
Feature activation+3.45e+00

Pos logit contributions
lights+0.092
 forth+0.070
bel+0.069
kins+0.068
ized+0.067
Neg logit contributions
 nine-0.060
ching-0.056
-0.056
 thirteen-0.055
upid-0.053
Token was
Token ID373
Feature activation+3.72e-01

Pos logit contributions
lights+0.391
 forth+0.345
uddle+0.335
ized+0.332
kins+0.327
Neg logit contributions
 thirteen-0.223
 nine-0.217
upid-0.202
-0.189
ching-0.183
Token here
Token ID994
Feature activation-5.47e-01

Pos logit contributions
lights+0.042
 forth+0.036
kins+0.035
nam+0.035
ized+0.034
Neg logit contributions
-0.027
 nine-0.026
upid-0.026
 thirteen-0.025
ching-0.024
Token before
Token ID878
Feature activation+1.43e-01

Pos logit contributions
 thirteen+0.039
 nine+0.038
ching+0.037
upid+0.036
+0.033
Neg logit contributions
lights-0.064
kins-0.052
 forth-0.050
bel-0.049
ized-0.048
Token us
Token ID514
Feature activation-1.37e+00

Pos logit contributions
lights+0.019
 forth+0.016
kins+0.015
ized+0.015
bel+0.015
Neg logit contributions
 nine-0.009
 thirteen-0.008
-0.008
ching-0.008
upid-0.008
Token."
Token ID526
Feature activation-9.32e-01

Pos logit contributions
 nine+0.086
 thirteen+0.083
ching+0.074
+0.074
upid+0.068
Neg logit contributions
lights-0.173
 forth-0.147
uddle-0.140
kins-0.139
ized-0.138
Token are
Token ID389
Feature activation-1.79e+00

Pos logit contributions
lights+0.029
 forth+0.025
kins+0.024
bel+0.024
nam+0.024
Neg logit contributions
 nine-0.013
 thirteen-0.012
ching-0.011
-0.011
upid-0.011
Token making
Token ID1642
Feature activation-2.70e-01

Pos logit contributions
 nine+0.107
+0.098
 thirteen+0.094
 like+0.089
ching+0.087
Neg logit contributions
lights-0.256
 forth-0.203
ized-0.202
bel-0.202
kins-0.201
Token a
Token ID257
Feature activation+4.98e-01

Pos logit contributions
 nine+0.017
 thirteen+0.016
+0.015
ching+0.015
upid+0.014
Neg logit contributions
lights-0.037
 forth-0.029
ized-0.029
bel-0.029
kins-0.028
Token mess
Token ID2085
Feature activation-1.04e+00

Pos logit contributions
lights+0.074
ized+0.061
kins+0.060
uddled+0.058
nam+0.058
Neg logit contributions
 nine-0.028
-0.024
 right-0.024
 a-0.024
 like-0.023
Token.
Token ID13
Feature activation+5.01e-01

Pos logit contributions
 nine+0.064
 thirteen+0.062
upid+0.059
+0.059
ching+0.055
Neg logit contributions
lights-0.147
kins-0.116
 forth-0.114
bel-0.109
ized-0.109
Token Someone
Token ID17877
Feature activation+3.44e+00

Pos logit contributions
lights+0.059
nam+0.043
 forth+0.043
Really+0.042
kins+0.042
Neg logit contributions
 nine-0.038
ching-0.038
 thirteen-0.035
upid-0.035
-0.034
Token can
Token ID460
Feature activation-1.40e+00

Pos logit contributions
lights+0.410
 forth+0.347
bel+0.342
kins+0.334
ized+0.333
Neg logit contributions
 thirteen-0.230
 nine-0.220
upid-0.203
-0.193
ching-0.186
Token trip
Token ID5296
Feature activation-6.34e-01

Pos logit contributions
 nine+0.091
+0.085
 thirteen+0.084
ching+0.079
upid+0.077
Neg logit contributions
lights-0.187
 forth-0.148
kins-0.145
bel-0.145
ized-0.145
Token and
Token ID290
Feature activation+2.12e-01

Pos logit contributions
 thirteen+0.036
 nine+0.036
+0.033
ching+0.032
upid+0.032
Neg logit contributions
lights-0.089
bel-0.072
 forth-0.071
ized-0.070
kins-0.069
Token fall
Token ID2121
Feature activation-6.82e-01

Pos logit contributions
lights+0.029
 forth+0.023
kins+0.023
ized+0.023
bel+0.023
Neg logit contributions
 nine-0.013
-0.013
 thirteen-0.012
ching-0.011
 like-0.011
Token.
Token ID13
Feature activation+5.27e-01

Pos logit contributions
 nine+0.043
 thirteen+0.042
+0.042
ching+0.038
upid+0.038
Neg logit contributions
lights-0.094
 forth-0.074
bel-0.071
kins-0.069
ized-0.068
Token was
Token ID373
Feature activation+3.71e-01

Pos logit contributions
 nine+0.033
 thirteen+0.030
upid+0.029
ching+0.027
+0.027
Neg logit contributions
lights-0.063
 forth-0.050
kins-0.049
ized-0.049
uddle-0.049
Token a
Token ID257
Feature activation+6.08e-01

Pos logit contributions
lights+0.057
 forth+0.048
nam+0.048
kins+0.047
ized+0.047
Neg logit contributions
 nine-0.014
upid-0.012
-0.012
ching-0.012
 thirteen-0.011
Token prank
Token ID33401
Feature activation+1.60e-01

Pos logit contributions
lights+0.079
 forth+0.062
kins+0.061
bel+0.061
ized+0.061
Neg logit contributions
 nine-0.042
-0.040
 thirteen-0.038
ching-0.036
upid-0.036
Token balloon
Token ID21190
Feature activation-1.17e+00

Pos logit contributions
lights+0.023
 forth+0.018
kins+0.018
bel+0.018
ized+0.018
Neg logit contributions
 nine-0.009
-0.008
 thirteen-0.008
ching-0.008
upid-0.007
Token.
Token ID13
Feature activation+8.23e-01

Pos logit contributions
 nine+0.065
+0.060
 thirteen+0.058
ching+0.054
upid+0.053
Neg logit contributions
lights-0.169
 forth-0.136
kins-0.134
bel-0.134
ized-0.133
Token Someone
Token ID17877
Feature activation+3.44e+00

Pos logit contributions
lights+0.109
apy+0.084
 forth+0.083
Really+0.083
kins+0.082
Neg logit contributions
 nine-0.053
ching-0.047
 thirteen-0.047
-0.046
upid-0.045
Token gave
Token ID2921
Feature activation+2.09e-01

Pos logit contributions
lights+0.407
 forth+0.322
ized+0.316
bel+0.315
kins+0.313
Neg logit contributions
 nine-0.265
 thirteen-0.250
-0.234
upid-0.233
ching-0.223
Token it
Token ID340
Feature activation+5.69e-01

Pos logit contributions
lights+0.024
 forth+0.021
ized+0.020
nam+0.019
ths+0.019
Neg logit contributions
 nine-0.015
-0.014
 thirteen-0.014
ching-0.014
upid-0.013
Token to
Token ID284
Feature activation+1.02e-01

Pos logit contributions
lights+0.075
bel+0.063
 forth+0.059
ized+0.059
uddle+0.058
Neg logit contributions
 thirteen-0.032
 nine-0.031
ching-0.029
upid-0.028
-0.028
Token me
Token ID502
Feature activation-9.81e-01

Pos logit contributions
lights+0.015
 forth+0.012
bel+0.012
kins+0.012
ized+0.011
Neg logit contributions
 nine-0.006
-0.006
 thirteen-0.005
 like-0.005
ching-0.005
Token as
Token ID355
Feature activation+1.29e+00

Pos logit contributions
 nine+0.058
 thirteen+0.056
+0.053
ching+0.053
upid+0.051
Neg logit contributions
lights-0.134
 forth-0.109
kins-0.108
bel-0.106
ized-0.105
Token the
Token ID262
Feature activation+1.95e-01

Pos logit contributions
 nine+0.039
 thirteen+0.037
upid+0.037
ching+0.037
+0.037
Neg logit contributions
lights-0.079
 forth-0.064
nam-0.063
ized-0.061
kins-0.061
Token slide
Token ID10649
Feature activation+1.67e-01

Pos logit contributions
lights+0.024
 forth+0.018
bel+0.018
ized+0.018
kins+0.018
Neg logit contributions
 nine-0.015
-0.015
 thirteen-0.014
 like-0.014
ching-0.014
Token was
Token ID373
Feature activation+3.16e-01

Pos logit contributions
lights+0.023
bel+0.018
kins+0.018
 forth+0.018
nam+0.018
Neg logit contributions
-0.010
 nine-0.010
 thirteen-0.009
 like-0.009
ching-0.009
Token wet
Token ID9583
Feature activation-2.23e-01

Pos logit contributions
lights+0.041
 forth+0.032
bel+0.031
kins+0.031
ized+0.031
Neg logit contributions
 nine-0.022
-0.021
 thirteen-0.020
ching-0.020
upid-0.020
Token.
Token ID13
Feature activation+4.79e-01

Pos logit contributions
 nine+0.012
upid+0.012
 thirteen+0.011
+0.010
ching+0.010
Neg logit contributions
lights-0.033
 forth-0.027
ized-0.026
kins-0.025
uddle-0.025
Token Someone
Token ID17877
Feature activation+3.44e+00

Pos logit contributions
lights+0.070
apy+0.055
bel+0.055
uddle+0.055
kins+0.054
Neg logit contributions
 nine-0.025
-0.022
 thirteen-0.022
ching-0.022
upid-0.020
Token had
Token ID550
Feature activation+6.42e-01

Pos logit contributions
lights+0.463
 forth+0.353
bel+0.352
kins+0.351
ized+0.347
Neg logit contributions
-0.234
 nine-0.233
ching-0.210
 like-0.209
 thirteen-0.205
Token poured
Token ID19036
Feature activation-9.23e-01

Pos logit contributions
lights+0.079
kins+0.061
 forth+0.061
ized+0.061
bel+0.060
Neg logit contributions
 nine-0.046
-0.046
 thirteen-0.044
ching-0.041
upid-0.041
Token water
Token ID1660
Feature activation-1.22e-01

Pos logit contributions
 nine+0.056
ching+0.051
+0.051
 thirteen+0.051
upid+0.048
Neg logit contributions
lights-0.126
 forth-0.102
kins-0.097
ized-0.097
apy-0.097
Token on
Token ID319
Feature activation+1.57e-01

Pos logit contributions
 nine+0.009
 thirteen+0.008
+0.008
upid+0.007
ching+0.007
Neg logit contributions
lights-0.015
 forth-0.012
bel-0.012
kins-0.012
ized-0.012
Token it
Token ID340
Feature activation+5.28e-01

Pos logit contributions
lights+0.018
 forth+0.014
ized+0.014
apy+0.014
kins+0.014
Neg logit contributions
ching-0.012
 nine-0.012
 thirteen-0.011
upid-0.011
ives-0.011
Token It
Token ID632
Feature activation+9.06e-01

Pos logit contributions
lights+0.073
apy+0.055
Really+0.054
kins+0.053
uddle+0.052
Neg logit contributions
 nine-0.038
ching-0.037
-0.034
 enough-0.034
 thirteen-0.034
Token is
Token ID318
Feature activation-1.68e+00

Pos logit contributions
lights+0.136
 forth+0.112
kins+0.111
ized+0.108
uddle+0.108
Neg logit contributions
 nine-0.043
 thirteen-0.035
upid-0.035
ching-0.032
-0.030
Token a
Token ID257
Feature activation+5.12e-01

Pos logit contributions
 nine+0.089
+0.088
ching+0.087
upid+0.084
 thirteen+0.078
Neg logit contributions
lights-0.232
kins-0.185
nam-0.185
 forth-0.184
ized-0.174
Token statue
Token ID15207
Feature activation-4.80e-01

Pos logit contributions
lights+0.063
 forth+0.049
kins+0.048
bel+0.048
ized+0.048
Neg logit contributions
 nine-0.038
-0.036
 thirteen-0.035
ching-0.034
upid-0.033
Token.
Token ID13
Feature activation+6.40e-01

Pos logit contributions
 nine+0.027
 thirteen+0.025
upid+0.025
+0.024
ching+0.023
Neg logit contributions
lights-0.068
 forth-0.054
bel-0.053
kins-0.053
ized-0.053
Token Someone
Token ID17877
Feature activation+3.43e+00

Pos logit contributions
lights+0.079
Really+0.061
apy+0.059
kins+0.057
 Sorry+0.057
Neg logit contributions
 nine-0.042
ching-0.042
 enough-0.039
 thirteen-0.038
upid-0.037
Token made
Token ID925
Feature activation-6.90e-01

Pos logit contributions
lights+0.428
 forth+0.349
ized+0.347
bel+0.343
kins+0.343
Neg logit contributions
 nine-0.221
 thirteen-0.213
upid-0.199
-0.191
ching-0.188
Token it
Token ID340
Feature activation+5.39e-01

Pos logit contributions
 nine+0.044
+0.042
 thirteen+0.042
ching+0.041
upid+0.037
Neg logit contributions
lights-0.085
kins-0.066
 forth-0.066
ized-0.066
bel-0.064
Token for
Token ID329
Feature activation+2.64e-01

Pos logit contributions
lights+0.073
bel+0.059
 forth+0.058
ized+0.056
kins+0.056
Neg logit contributions
 nine-0.033
 thirteen-0.030
-0.029
ching-0.028
upid-0.028
Token fun
Token ID1257
Feature activation+4.06e-01

Pos logit contributions
lights+0.036
 forth+0.028
bel+0.028
kins+0.028
ized+0.027
Neg logit contributions
 nine-0.017
-0.016
 thirteen-0.016
ching-0.015
 like-0.015
Token.
Token ID13
Feature activation+6.57e-01

Pos logit contributions
lights+0.057
 forth+0.046
kins+0.045
bel+0.044
ized+0.044
Neg logit contributions
 nine-0.024
 thirteen-0.023
-0.022
ching-0.022
upid-0.022
Token should
Token ID815
Feature activation+1.46e-01

Pos logit contributions
lights+0.048
 forth+0.042
kins+0.041
uddle+0.040
ized+0.039
Neg logit contributions
 nine-0.030
 thirteen-0.029
ching-0.028
upid-0.026
una-0.026
Token go
Token ID467
Feature activation-4.16e-01

Pos logit contributions
lights+0.016
 forth+0.014
uddle+0.012
kins+0.012
ths+0.012
Neg logit contributions
ching-0.011
 thirteen-0.011
 nine-0.010
ives-0.009
 aback-0.009
Token down
Token ID866
Feature activation-3.63e-01

Pos logit contributions
 thirteen+0.027
 nine+0.027
+0.026
ching+0.025
upid+0.024
Neg logit contributions
lights-0.054
 forth-0.046
bel-0.043
uddle-0.043
ized-0.042
Token soon
Token ID2582
Feature activation+9.28e-01

Pos logit contributions
ching+0.021
 thirteen+0.021
upid+0.019
+0.019
 nine+0.019
Neg logit contributions
lights-0.050
 forth-0.039
ized-0.039
kins-0.038
bel-0.038
Token.
Token ID13
Feature activation+7.45e-01

Pos logit contributions
lights+0.120
 forth+0.101
kins+0.098
ized+0.092
bel+0.091
Neg logit contributions
 nine-0.056
 thirteen-0.055
ching-0.053
upid-0.053
-0.052
Token Someone
Token ID17877
Feature activation+3.42e+00

Pos logit contributions
lights+0.081
 forth+0.059
bel+0.057
kins+0.057
ized+0.056
Neg logit contributions
 nine-0.067
-0.063
 thirteen-0.063
ching-0.063
upid-0.060
Token might
Token ID1244
Feature activation-2.67e-02

Pos logit contributions
lights+0.399
 forth+0.321
bel+0.315
ized+0.314
kins+0.313
Neg logit contributions
 nine-0.257
 thirteen-0.250
upid-0.234
-0.224
ching-0.221
Token see
Token ID766
Feature activation+9.06e-01

Pos logit contributions
 nine+0.002
 thirteen+0.002
upid+0.002
ont+0.002
ives+0.002
Neg logit contributions
lights-0.003
 forth-0.002
bel-0.002
ized-0.002
har-0.002
Token us
Token ID514
Feature activation-1.39e+00

Pos logit contributions
lights+0.119
 forth+0.095
ized+0.092
kins+0.091
bel+0.089
Neg logit contributions
 nine-0.059
-0.056
 thirteen-0.056
ching-0.053
upid-0.052
Token."
Token ID526
Feature activation-7.66e-01

Pos logit contributions
 nine+0.094
 thirteen+0.091
+0.082
upid+0.082
ching+0.080
Neg logit contributions
lights-0.160
 forth-0.147
ized-0.129
kins-0.128
bel-0.126
Token
Token ID198
Feature activation+3.47e-01

Pos logit contributions
 nine+0.032
 thirteen+0.029
+0.029
ching+0.027
upid+0.025
Neg logit contributions
lights-0.121
 forth-0.098
kins-0.097
bel-0.097
ized-0.097
Token floating
Token ID12462
Feature activation+3.41e-01

Pos logit contributions
lights+0.049
 forth+0.039
kins+0.038
bel+0.038
ized+0.038
Neg logit contributions
 nine-0.022
-0.021
 thirteen-0.020
ching-0.019
upid-0.019
Token in
Token ID287
Feature activation+1.21e+00

Pos logit contributions
lights+0.046
 forth+0.036
kins+0.035
ized+0.035
bel+0.035
Neg logit contributions
 nine-0.023
-0.022
 thirteen-0.021
ching-0.020
upid-0.020
Token the
Token ID262
Feature activation+1.49e-01

Pos logit contributions
lights+0.182
 forth+0.146
kins+0.144
ized+0.143
bel+0.142
Neg logit contributions
 nine-0.056
-0.056
 thirteen-0.054
ching-0.053
upid-0.050
Token air
Token ID1633
Feature activation-8.72e-01

Pos logit contributions
lights+0.019
uddle+0.014
 forth+0.014
bel+0.014
ized+0.013
Neg logit contributions
 nine-0.011
-0.011
 thirteen-0.010
ching-0.010
upid-0.010
Token.
Token ID13
Feature activation+5.38e-01

Pos logit contributions
 nine+0.072
upid+0.071
 thirteen+0.069
+0.068
ching+0.066
Neg logit contributions
lights-0.100
kins-0.075
 forth-0.075
ized-0.074
uddle-0.067
Token Someone
Token ID17877
Feature activation+3.42e+00

Pos logit contributions
lights+0.086
 forth+0.072
kins+0.070
ized+0.070
bel+0.069
Neg logit contributions
 nine-0.023
-0.021
 thirteen-0.019
 like-0.018
 a-0.018
Token had
Token ID550
Feature activation+5.98e-01

Pos logit contributions
lights+0.488
uddle+0.371
 forth+0.369
ized+0.368
bel+0.365
Neg logit contributions
-0.214
 nine-0.213
 like-0.202
 a-0.197
ching-0.193
Token let
Token ID1309
Feature activation-3.40e-01

Pos logit contributions
lights+0.078
 forth+0.061
kins+0.061
bel+0.061
ized+0.060
Neg logit contributions
 nine-0.040
-0.039
 thirteen-0.037
ching-0.035
upid-0.035
Token it
Token ID340
Feature activation+5.42e-01

Pos logit contributions
 nine+0.021
+0.020
 thirteen+0.019
ching+0.018
upid+0.018
Neg logit contributions
lights-0.047
 forth-0.037
kins-0.036
bel-0.036
ized-0.036
Token go
Token ID467
Feature activation-5.18e-01

Pos logit contributions
lights+0.081
kins+0.064
ths+0.064
ized+0.064
 forth+0.064
Neg logit contributions
 nine-0.028
-0.027
 like-0.027
ching-0.025
 a-0.025
Token.
Token ID13
Feature activation+5.24e-01

Pos logit contributions
 nine+0.028
+0.026
 thirteen+0.025
ching+0.024
upid+0.023
Neg logit contributions
lights-0.076
 forth-0.061
kins-0.060
bel-0.060
ized-0.060
Token never
Token ID1239
Feature activation-1.61e+00

Pos logit contributions
lights+0.033
 forth+0.027
kins+0.027
bel+0.027
ized+0.026
Neg logit contributions
 nine-0.013
 thirteen-0.012
-0.012
ching-0.012
upid-0.011
Token played
Token ID2826
Feature activation+1.19e+00

Pos logit contributions
 nine+0.130
+0.123
 thirteen+0.119
ching+0.115
upid+0.114
Neg logit contributions
lights-0.192
 forth-0.149
bel-0.144
kins-0.144
ized-0.143
Token with
Token ID351
Feature activation+8.34e-01

Pos logit contributions
lights+0.152
 forth+0.118
kins+0.117
bel+0.117
ized+0.116
Neg logit contributions
 nine-0.086
-0.082
 thirteen-0.079
upid-0.076
ching-0.074
Token the
Token ID262
Feature activation+2.17e-01

Pos logit contributions
lights+0.110
kins+0.085
 forth+0.085
ized+0.084
bel+0.084
Neg logit contributions
 nine-0.057
-0.055
 thirteen-0.053
ching-0.050
upid-0.050
Token or
Token ID393
Feature activation-6.79e-01

Pos logit contributions
lights+0.026
 forth+0.019
kins+0.019
ized+0.019
bel+0.019
Neg logit contributions
 nine-0.018
-0.017
 thirteen-0.017
ching-0.016
 like-0.016
Tokennam
Token ID7402
Feature activation+3.40e+00

Pos logit contributions
 nine+0.042
+0.039
 thirteen+0.037
 like+0.036
ching+0.035
Neg logit contributions
lights-0.094
 forth-0.074
kins-0.074
ized-0.073
uddle-0.073
Tokenents
Token ID658
Feature activation-6.26e-02

Pos logit contributions
lights+0.407
 forth+0.310
kins+0.304
bel+0.304
ized+0.303
Neg logit contributions
 nine-0.272
-0.260
 thirteen-0.251
ching-0.243
upid-0.238
Token again
Token ID757
Feature activation+5.92e-01

Pos logit contributions
 nine+0.006
+0.006
 thirteen+0.006
upid+0.006
ching+0.005
Neg logit contributions
lights-0.006
 forth-0.005
ized-0.005
kins-0.005
bel-0.005
Token.
Token ID13
Feature activation+2.35e-01

Pos logit contributions
lights+0.089
 forth+0.071
bel+0.070
kins+0.070
ized+0.070
Neg logit contributions
 nine-0.030
-0.029
 thirteen-0.026
 like-0.025
ching-0.025
Token They
Token ID1119
Feature activation+9.79e-02

Pos logit contributions
lights+0.032
Really+0.025
nam+0.024
kins+0.024
bel+0.024
Neg logit contributions
 nine-0.014
 thirteen-0.013
ching-0.013
upid-0.012
-0.012
Token still
Token ID991
Feature activation+1.28e+00

Pos logit contributions
lights+0.014
 forth+0.011
kins+0.011
bel+0.011
ized+0.010
Neg logit contributions
 nine-0.006
-0.006
 thirteen-0.005
ching-0.005
upid-0.005
Token the
Token ID262
Feature activation+1.38e-01

Pos logit contributions
 nine+0.038
+0.036
 thirteen+0.033
 like+0.033
 a+0.033
Neg logit contributions
lights-0.099
 forth-0.080
kins-0.079
ized-0.079
bel-0.078
Token box
Token ID3091
Feature activation+4.26e-01

Pos logit contributions
lights+0.016
ized+0.013
kins+0.013
bel+0.012
 forth+0.012
Neg logit contributions
 nine-0.011
-0.011
 thirteen-0.010
 like-0.010
 a-0.010
Token was
Token ID373
Feature activation+2.28e-01

Pos logit contributions
lights+0.059
nam+0.050
Really+0.049
 forth+0.049
bel+0.048
Neg logit contributions
-0.025
 nine-0.023
 like-0.022
 a-0.022
 never-0.021
Token gone
Token ID3750
Feature activation+5.14e-01

Pos logit contributions
lights+0.031
 forth+0.024
bel+0.024
ized+0.024
kins+0.024
Neg logit contributions
 nine-0.015
-0.014
 thirteen-0.013
 like-0.013
ching-0.013
Token.
Token ID13
Feature activation+3.40e-01

Pos logit contributions
lights+0.071
 forth+0.056
kins+0.055
ized+0.054
bel+0.053
Neg logit contributions
 nine-0.033
 thirteen-0.031
-0.030
upid-0.028
ching-0.028
Token Someone
Token ID17877
Feature activation+3.40e+00

Pos logit contributions
lights+0.050
 forth+0.041
kins+0.040
bel+0.040
ized+0.040
Neg logit contributions
 nine-0.018
-0.017
 thirteen-0.016
ching-0.014
 like-0.014
Token had
Token ID550
Feature activation+5.72e-01

Pos logit contributions
lights+0.489
 forth+0.370
uddle+0.369
kins+0.369
bel+0.369
Neg logit contributions
-0.216
 nine-0.210
 like-0.197
 a-0.190
ching-0.187
Token taken
Token ID2077
Feature activation+4.70e-01

Pos logit contributions
lights+0.075
 forth+0.059
kins+0.059
bel+0.058
ized+0.058
Neg logit contributions
 nine-0.038
-0.037
 thirteen-0.036
ching-0.034
upid-0.033
Token it
Token ID340
Feature activation+5.06e-01

Pos logit contributions
lights+0.060
 forth+0.047
kins+0.046
ized+0.045
bel+0.045
Neg logit contributions
-0.030
 thirteen-0.029
 nine-0.028
ching-0.027
upid-0.025
Token away
Token ID1497
Feature activation-9.20e-01

Pos logit contributions
lights+0.062
 forth+0.051
ized+0.050
bel+0.048
kins+0.047
Neg logit contributions
 thirteen-0.037
 nine-0.035
-0.031
upid-0.030
 knows-0.030
Token.
Token ID13
Feature activation+3.50e-01

Pos logit contributions
 nine+0.055
 thirteen+0.054
upid+0.050
+0.050
ching+0.049
Neg logit contributions
lights-0.129
kins-0.104
ized-0.100
 forth-0.099
bel-0.098
Token.
Token ID13
Feature activation+7.55e-01

Pos logit contributions
lights+0.115
kins+0.095
uddle+0.090
 forth+0.089
ized+0.088
Neg logit contributions
 nine-0.060
-0.055
 thirteen-0.053
upid-0.051
ching-0.050
Token This
Token ID770
Feature activation-7.01e-01

Pos logit contributions
lights+0.098
Really+0.077
kins+0.077
apy+0.076
bel+0.074
Neg logit contributions
 nine-0.048
ching-0.046
upid-0.042
 thirteen-0.042
-0.040
Token is
Token ID318
Feature activation-1.60e+00

Pos logit contributions
 nine+0.041
upid+0.039
ching+0.038
 thirteen+0.036
+0.036
Neg logit contributions
lights-0.085
kins-0.077
uddle-0.071
 creations-0.069
ized-0.066
Token candy
Token ID18550
Feature activation-5.80e-02

Pos logit contributions
 nine+0.080
ching+0.077
+0.074
upid+0.072
 thirteen+0.069
Neg logit contributions
lights-0.229
kins-0.187
 forth-0.185
nam-0.185
ized-0.177
Token.
Token ID13
Feature activation+7.61e-01

Pos logit contributions
 nine+0.004
 thirteen+0.003
upid+0.003
+0.003
ching+0.003
Neg logit contributions
lights-0.008
kins-0.006
 forth-0.006
uddle-0.006
ized-0.006
Token Someone
Token ID17877
Feature activation+3.40e+00

Pos logit contributions
lights+0.095
Really+0.074
kins+0.074
apy+0.072
nam+0.072
Neg logit contributions
 nine-0.052
ching-0.049
upid-0.046
 thirteen-0.046
-0.044
Token left
Token ID1364
Feature activation-2.45e-01

Pos logit contributions
lights+0.396
kins+0.339
 forth+0.331
ized+0.329
bel+0.318
Neg logit contributions
 nine-0.216
 thirteen-0.213
upid-0.207
ching-0.191
-0.181
Token it
Token ID340
Feature activation+5.66e-01

Pos logit contributions
+0.018
ching+0.018
 thirteen+0.017
 nine+0.017
upid+0.016
Neg logit contributions
lights-0.029
kins-0.023
 forth-0.023
nam-0.022
ized-0.022
Token in
Token ID287
Feature activation+1.17e+00

Pos logit contributions
lights+0.064
 forth+0.051
kins+0.050
ized+0.049
bel+0.048
Neg logit contributions
 thirteen-0.043
 nine-0.043
-0.042
upid-0.041
ching-0.041
Token the
Token ID262
Feature activation+1.54e-01

Pos logit contributions
lights+0.153
kins+0.128
 forth+0.122
nam+0.121
ized+0.120
Neg logit contributions
 thirteen-0.072
ching-0.068
 nine-0.066
-0.065
upid-0.061
Token park
Token ID3952
Feature activation-5.51e-01

Pos logit contributions
lights+0.017
 forth+0.014
uddle+0.014
kins+0.013
bel+0.013
Neg logit contributions
 nine-0.012
-0.012
 thirteen-0.012
ching-0.012
upid-0.011
Token and
Token ID290
Feature activation-1.38e-01

Pos logit contributions
 thirteen+0.008
 nine+0.008
upid+0.007
ching+0.007
+0.007
Neg logit contributions
lights-0.019
bel-0.015
 forth-0.015
kins-0.015
ized-0.015
Token play
Token ID711
Feature activation+7.57e-01

Pos logit contributions
 nine+0.010
+0.009
 thirteen+0.009
ching+0.009
upid+0.009
Neg logit contributions
lights-0.018
 forth-0.014
bel-0.013
kins-0.013
ized-0.013
Token with
Token ID351
Feature activation+5.24e-01

Pos logit contributions
lights+0.097
 forth+0.076
kins+0.074
bel+0.074
ized+0.074
Neg logit contributions
 nine-0.055
-0.052
 thirteen-0.051
ching-0.048
upid-0.048
Token your
Token ID534
Feature activation-1.54e+00

Pos logit contributions
lights+0.077
 forth+0.061
kins+0.061
ized+0.060
bel+0.060
Neg logit contributions
 nine-0.028
-0.027
 thirteen-0.026
ching-0.024
upid-0.024
Token or
Token ID393
Feature activation-7.27e-01

Pos logit contributions
 nine+0.115
 a+0.112
+0.105
 right+0.104
 two+0.103
Neg logit contributions
lights-0.189
ized-0.147
bel-0.142
ths-0.142
 forth-0.141
Tokennam
Token ID7402
Feature activation+3.40e+00

Pos logit contributions
 nine+0.040
+0.036
 like+0.035
 a+0.034
 thirteen+0.034
Neg logit contributions
lights-0.108
ized-0.086
kins-0.085
uddle-0.085
bel-0.083
Tokenents
Token ID658
Feature activation-1.40e-01

Pos logit contributions
lights+0.415
 forth+0.319
kins+0.313
bel+0.308
ized+0.307
Neg logit contributions
 nine-0.266
-0.253
 thirteen-0.242
ching-0.232
upid-0.229
Token.
Token ID13
Feature activation+1.14e-01

Pos logit contributions
 nine+0.010
 thirteen+0.010
+0.009
upid+0.009
ching+0.009
Neg logit contributions
lights-0.018
kins-0.014
 forth-0.014
bel-0.014
ized-0.014
Token Maybe
Token ID6674
Feature activation+3.22e-01

Pos logit contributions
lights+0.013
Really+0.010
nam+0.010
 forth+0.009
apy+0.009
Neg logit contributions
ching-0.009
 nine-0.009
upid-0.008
 thirteen-0.008
 enough-0.008
Token you
Token ID345
Feature activation-7.75e-01

Pos logit contributions
lights+0.038
 forth+0.028
uddle+0.028
bel+0.028
kins+0.028
Neg logit contributions
 nine-0.027
-0.026
 thirteen-0.025
 like-0.024
 a-0.024
Token can
Token ID460
Feature activation-1.38e+00

Pos logit contributions
 nine+0.046
 thirteen+0.044
ching+0.040
+0.039
upid+0.038
Neg logit contributions
lights-0.101
 forth-0.083
kins-0.083
bel-0.082
uddle-0.080
Token a
Token ID257
Feature activation-2.96e-01

Pos logit contributions
 thirteen+0.023
upid+0.022
 nine+0.022
ching+0.021
icks+0.017
Neg logit contributions
lights-0.122
apy-0.101
ized-0.101
bel-0.100
 forth-0.100
Token little
Token ID1310
Feature activation-1.67e+00

Pos logit contributions
 nine+0.020
+0.019
 a+0.017
 like+0.017
 thirteen+0.017
Neg logit contributions
lights-0.041
ized-0.032
bel-0.031
kins-0.031
 forth-0.031
Token girl
Token ID2576
Feature activation-1.13e+00

Pos logit contributions
 nine+0.166
+0.160
 thirteen+0.153
 like+0.150
ching+0.149
Neg logit contributions
lights-0.171
bel-0.121
kins-0.121
 forth-0.119
ized-0.119
Token named
Token ID3706
Feature activation+8.19e-01

Pos logit contributions
 nine+0.086
 thirteen+0.083
+0.080
upid+0.080
ching+0.078
Neg logit contributions
lights-0.136
 forth-0.107
bel-0.104
kins-0.104
ized-0.104
Token Kay
Token ID17356
Feature activation-7.74e-01

Pos logit contributions
lights+0.092
 forth+0.069
kins+0.068
bel+0.067
ized+0.067
Neg logit contributions
 nine-0.072
-0.069
 thirteen-0.067
ching-0.065
upid-0.064
Tokenla
Token ID5031
Feature activation-4.51e+00

Pos logit contributions
 nine+0.044
 thirteen+0.042
+0.041
ching+0.040
upid+0.039
Neg logit contributions
lights-0.108
ized-0.087
 forth-0.087
kins-0.086
bel-0.086
Token.
Token ID13
Feature activation-7.21e-01

Pos logit contributions
 nine+0.273
 thirteen+0.257
+0.250
ching+0.240
upid+0.240
Neg logit contributions
lights-0.614
kins-0.494
 forth-0.491
bel-0.487
ized-0.487
Token She
Token ID1375
Feature activation-1.37e+00

Pos logit contributions
ching+0.052
 nine+0.047
 thirteen+0.047
+0.045
upid+0.043
Neg logit contributions
lights-0.091
Really-0.068
ized-0.067
 forth-0.067
bel-0.066
Token was
Token ID373
Feature activation-3.38e-01

Pos logit contributions
 nine+0.099
+0.093
 thirteen+0.091
ching+0.087
upid+0.086
Neg logit contributions
lights-0.175
 forth-0.137
kins-0.134
bel-0.134
ized-0.134
Token 3
Token ID513
Feature activation-1.80e-01

Pos logit contributions
upid+0.024
ching+0.023
ives+0.022
 thirteen+0.021
icks+0.021
Neg logit contributions
lights-0.037
nam-0.034
 forth-0.033
bel-0.032
ths-0.032
Token years
Token ID812
Feature activation-3.90e-01

Pos logit contributions
 nine+0.019
+0.018
 thirteen+0.018
upid+0.018
ching+0.017
Neg logit contributions
lights-0.017
 forth-0.012
ized-0.012
kins-0.012
bel-0.011
Token was
Token ID373
Feature activation-4.51e-01

Pos logit contributions
 nine+0.010
 thirteen+0.010
upid+0.009
+0.009
ching+0.009
Neg logit contributions
lights-0.013
kins-0.009
 forth-0.009
ized-0.009
bel-0.009
Token a
Token ID257
Feature activation-1.66e-01

Pos logit contributions
 thirteen+0.018
upid+0.017
 nine+0.015
 knows+0.015
ching+0.014
Neg logit contributions
lights-0.067
 sudden-0.057
ized-0.057
apy-0.057
nam-0.056
Token girl
Token ID2576
Feature activation-8.19e-01

Pos logit contributions
 nine+0.009
+0.008
 a+0.007
 like+0.007
ching+0.007
Neg logit contributions
lights-0.026
bel-0.020
ized-0.020
 forth-0.020
kins-0.020
Token named
Token ID3706
Feature activation+7.76e-01

Pos logit contributions
 nine+0.063
+0.059
 thirteen+0.058
ching+0.056
upid+0.055
Neg logit contributions
lights-0.101
 forth-0.078
kins-0.077
bel-0.076
ized-0.076
Token Kay
Token ID17356
Feature activation-5.57e-01

Pos logit contributions
lights+0.082
 forth+0.060
kins+0.058
ized+0.058
bel+0.058
Neg logit contributions
 nine-0.071
 thirteen-0.069
-0.068
ching-0.067
upid-0.065
Tokenla
Token ID5031
Feature activation-4.31e+00

Pos logit contributions
 thirteen+0.037
 nine+0.036
ching+0.035
+0.035
upid+0.033
Neg logit contributions
lights-0.072
ized-0.057
kins-0.056
 forth-0.056
bel-0.055
Token.
Token ID13
Feature activation-6.39e-01

Pos logit contributions
 nine+0.259
 thirteen+0.245
+0.238
ching+0.224
upid+0.223
Neg logit contributions
lights-0.592
kins-0.478
 forth-0.473
bel-0.470
ized-0.468
Token She
Token ID1375
Feature activation-1.29e+00

Pos logit contributions
 nine+0.036
+0.035
ching+0.034
 thirteen+0.033
upid+0.031
Neg logit contributions
lights-0.091
 forth-0.072
bel-0.071
ized-0.070
kins-0.069
Token was
Token ID373
Feature activation-3.11e-01

Pos logit contributions
 nine+0.092
+0.087
 thirteen+0.083
ching+0.080
 like+0.079
Neg logit contributions
lights-0.169
 forth-0.132
kins-0.129
bel-0.129
ized-0.128
Token very
Token ID845
Feature activation+6.68e-01

Pos logit contributions
 nine+0.016
 thirteen+0.016
upid+0.016
+0.015
ching+0.015
Neg logit contributions
lights-0.042
nam-0.036
 forth-0.036
bel-0.036
kins-0.034
Token happy
Token ID3772
Feature activation+5.65e-02

Pos logit contributions
lights+0.083
 forth+0.064
kins+0.062
ized+0.062
bel+0.062
Neg logit contributions
 nine-0.052
-0.049
 thirteen-0.047
 like-0.045
ching-0.045
Token was
Token ID373
Feature activation-4.66e-01

Pos logit contributions
 nine+0.018
 thirteen+0.017
ching+0.016
upid+0.016
+0.015
Neg logit contributions
lights-0.023
kins-0.018
 forth-0.018
ized-0.018
uddle-0.017
Token a
Token ID257
Feature activation-7.43e-02

Pos logit contributions
 nine+0.013
upid+0.013
 thirteen+0.013
ching+0.011
+0.010
Neg logit contributions
lights-0.075
bel-0.063
ized-0.062
apy-0.061
 forth-0.061
Token girl
Token ID2576
Feature activation-9.36e-01

Pos logit contributions
 nine+0.005
+0.005
 a+0.004
 like+0.004
 thirteen+0.004
Neg logit contributions
lights-0.011
ized-0.008
bel-0.008
kins-0.008
 forth-0.008
Token named
Token ID3706
Feature activation+1.02e+00

Pos logit contributions
 nine+0.069
 thirteen+0.065
+0.064
upid+0.062
ching+0.062
Neg logit contributions
lights-0.117
 forth-0.091
kins-0.089
bel-0.089
ized-0.089
Token Car
Token ID1879
Feature activation-2.40e+00

Pos logit contributions
lights+0.109
 forth+0.081
kins+0.079
bel+0.078
ized+0.078
Neg logit contributions
 nine-0.092
 thirteen-0.089
-0.088
ching-0.085
upid-0.084
Tokenla
Token ID5031
Feature activation-4.31e+00

Pos logit contributions
 nine+0.122
+0.114
 thirteen+0.114
ching+0.106
upid+0.105
Neg logit contributions
lights-0.347
kins-0.283
ized-0.281
 forth-0.281
bel-0.280
Token who
Token ID508
Feature activation-1.70e-01

Pos logit contributions
 nine+0.262
 thirteen+0.252
+0.242
ching+0.235
upid+0.234
Neg logit contributions
lights-0.580
kins-0.464
 forth-0.461
bel-0.459
ized-0.457
Token loved
Token ID6151
Feature activation-3.34e-01

Pos logit contributions
 nine+0.014
 thirteen+0.013
upid+0.013
ching+0.012
+0.012
Neg logit contributions
lights-0.019
ized-0.015
bel-0.015
 forth-0.015
kins-0.015
Token to
Token ID284
Feature activation-3.00e-01

Pos logit contributions
 nine+0.013
+0.012
 thirteen+0.011
ching+0.010
 like+0.010
Neg logit contributions
lights-0.054
 forth-0.044
kins-0.044
bel-0.044
ized-0.044
Token rest
Token ID1334
Feature activation+2.81e-01

Pos logit contributions
 nine+0.028
 thirteen+0.027
ching+0.026
+0.025
upid+0.025
Neg logit contributions
lights-0.031
 forth-0.023
bel-0.023
kins-0.022
apy-0.022
Token.
Token ID13
Feature activation-2.87e-01

Pos logit contributions
lights+0.041
 forth+0.033
kins+0.032
bel+0.032
ized+0.032
Neg logit contributions
 nine-0.016
-0.015
 thirteen-0.014
ching-0.013
upid-0.013
Token a
Token ID257
Feature activation-1.51e-01

Pos logit contributions
 thirteen+0.013
 nine+0.011
upid+0.011
ching+0.010
 knows+0.009
Neg logit contributions
lights-0.053
apy-0.045
ized-0.045
 forth-0.045
kins-0.045
Token little
Token ID1310
Feature activation-1.50e+00

Pos logit contributions
 nine+0.009
+0.008
 like+0.007
 a+0.007
ching+0.007
Neg logit contributions
lights-0.023
 forth-0.018
ized-0.017
bel-0.017
kins-0.017
Token girl
Token ID2576
Feature activation-7.49e-01

Pos logit contributions
 nine+0.137
+0.130
 thirteen+0.123
 like+0.123
ching+0.121
Neg logit contributions
lights-0.168
bel-0.123
kins-0.120
ized-0.119
 forth-0.119
Token named
Token ID3706
Feature activation+8.15e-01

Pos logit contributions
 nine+0.057
+0.054
 thirteen+0.054
ching+0.051
upid+0.051
Neg logit contributions
lights-0.092
 forth-0.071
kins-0.070
bel-0.070
ized-0.069
Token Mar
Token ID1526
Feature activation-1.15e+00

Pos logit contributions
lights+0.084
 forth+0.062
kins+0.060
nam+0.060
bel+0.059
Neg logit contributions
 nine-0.076
 thirteen-0.073
-0.072
ching-0.072
upid-0.069
Tokenla
Token ID5031
Feature activation-4.26e+00

Pos logit contributions
 thirteen+0.137
 nine+0.136
+0.135
ching+0.131
upid+0.128
Neg logit contributions
lights-0.087
kins-0.062
 forth-0.060
ized-0.055
bel-0.054
Token.
Token ID13
Feature activation-5.53e-01

Pos logit contributions
 nine+0.268
 thirteen+0.258
+0.241
upid+0.235
ching+0.234
Neg logit contributions
lights-0.569
kins-0.461
bel-0.453
 forth-0.453
ized-0.450
Token She
Token ID1375
Feature activation-1.25e+00

Pos logit contributions
 nine+0.033
 thirteen+0.031
+0.030
ching+0.030
upid+0.028
Neg logit contributions
lights-0.078
 forth-0.060
bel-0.060
ized-0.059
apy-0.058
Token was
Token ID373
Feature activation-2.74e-01

Pos logit contributions
 nine+0.092
+0.086
 thirteen+0.085
ching+0.080
upid+0.080
Neg logit contributions
lights-0.158
 forth-0.123
kins-0.122
bel-0.122
ized-0.120
Token walking
Token ID6155
Feature activation+8.59e-01

Pos logit contributions
 nine+0.012
 thirteen+0.012
upid+0.011
+0.011
ching+0.011
Neg logit contributions
lights-0.040
nam-0.034
bel-0.034
 forth-0.034
ized-0.033
Token in
Token ID287
Feature activation+5.47e-01

Pos logit contributions
lights+0.116
 forth+0.092
bel+0.091
kins+0.090
ized+0.089
Neg logit contributions
 nine-0.056
-0.053
 thirteen-0.052
ching-0.049
upid-0.048
Token the
Token ID262
Feature activation-3.28e-01

Pos logit contributions
lights+0.029
 forth+0.023
ths+0.023
ized+0.023
kins+0.022
Neg logit contributions
ching-0.010
 thirteen-0.010
 nine-0.010
upid-0.009
 like-0.009
Token way
Token ID835
Feature activation-9.64e-01

Pos logit contributions
 nine+0.025
+0.023
 thirteen+0.023
ching+0.023
upid+0.022
Neg logit contributions
lights-0.040
 forth-0.032
ized-0.030
kins-0.030
bel-0.030
Token home
Token ID1363
Feature activation-6.94e-02

Pos logit contributions
 nine+0.054
 thirteen+0.053
ching+0.048
+0.046
upid+0.044
Neg logit contributions
lights-0.135
 forth-0.113
ized-0.106
kins-0.105
bel-0.105
Token,
Token ID11
Feature activation-4.86e-01

Pos logit contributions
 nine+0.003
 thirteen+0.003
+0.002
ching+0.002
upid+0.002
Neg logit contributions
lights-0.011
 forth-0.009
kins-0.009
bel-0.009
ized-0.009
Token Kay
Token ID17356
Feature activation-3.87e-01

Pos logit contributions
 nine+0.034
+0.033
 a+0.029
 thirteen+0.029
 like+0.029
Neg logit contributions
lights-0.064
 forth-0.050
kins-0.049
uddle-0.049
ized-0.049
Tokenla
Token ID5031
Feature activation-4.19e+00

Pos logit contributions
 nine+0.023
 thirteen+0.021
ching+0.020
+0.020
upid+0.020
Neg logit contributions
lights-0.053
 forth-0.044
ized-0.043
kins-0.043
bel-0.042
Token started
Token ID2067
Feature activation+1.96e-01

Pos logit contributions
 nine+0.331
 thirteen+0.311
+0.303
upid+0.300
ching+0.297
Neg logit contributions
lights-0.493
 forth-0.386
ized-0.380
kins-0.380
bel-0.376
Token to
Token ID284
Feature activation-5.59e-01

Pos logit contributions
lights+0.028
bel+0.023
 forth+0.023
ized+0.022
nam+0.022
Neg logit contributions
 nine-0.010
 thirteen-0.010
upid-0.010
ching-0.009
-0.008
Token imagine
Token ID5967
Feature activation-5.67e-01

Pos logit contributions
 nine+0.047
 thirteen+0.045
ching+0.042
upid+0.041
una+0.041
Neg logit contributions
lights-0.060
 forth-0.053
nam-0.048
bel-0.047
kins-0.046
Token all
Token ID477
Feature activation-5.47e-03

Pos logit contributions
 nine+0.031
+0.029
 thirteen+0.027
ching+0.026
 like+0.026
Neg logit contributions
lights-0.082
 forth-0.066
kins-0.065
bel-0.065
ized-0.064
Token the
Token ID262
Feature activation-4.64e-01

Pos logit contributions
 nine+0.000
 thirteen+0.000
upid+0.000
 fourteen+0.000
icks+0.000
Neg logit contributions
lights-0.001
 forth-0.000
ized-0.000
bel-0.000
nam-0.000
Token knew
Token ID2993
Feature activation-1.15e+00

Pos logit contributions
 nine+0.002
 thirteen+0.002
+0.002
ching+0.002
upid+0.002
Neg logit contributions
lights-0.003
 forth-0.002
kins-0.002
bel-0.002
ized-0.002
Token it
Token ID340
Feature activation-8.21e-02

Pos logit contributions
 nine+0.075
 thirteen+0.072
upid+0.067
ching+0.067
+0.065
Neg logit contributions
lights-0.153
kins-0.120
 forth-0.119
bel-0.119
ized-0.118
Token was
Token ID373
Feature activation-4.93e-01

Pos logit contributions
 nine+0.006
+0.006
 thirteen+0.006
ching+0.006
upid+0.006
Neg logit contributions
lights-0.010
 forth-0.008
kins-0.008
bel-0.008
ized-0.008
Token her
Token ID607
Feature activation-1.84e-01

Pos logit contributions
 nine+0.027
+0.024
 thirteen+0.024
ching+0.023
upid+0.023
Neg logit contributions
lights-0.071
 forth-0.058
kins-0.057
ized-0.056
bel-0.056
Token own
Token ID898
Feature activation+1.74e-01

Pos logit contributions
 nine+0.015
+0.014
 thirteen+0.014
ching+0.013
 like+0.013
Neg logit contributions
lights-0.022
 forth-0.017
kins-0.016
bel-0.016
ized-0.016
Token fault
Token ID8046
Feature activation-4.18e+00

Pos logit contributions
lights+0.021
 forth+0.016
kins+0.016
bel+0.016
ized+0.015
Neg logit contributions
 nine-0.014
 thirteen-0.013
-0.013
ching-0.012
upid-0.012
Token.
Token ID13
Feature activation-9.83e-02

Pos logit contributions
 nine+0.273
 thirteen+0.257
+0.238
ching+0.235
upid+0.232
Neg logit contributions
lights-0.572
 forth-0.453
kins-0.443
ized-0.432
bel-0.430
Token
Token ID198
Feature activation-2.76e-01

Pos logit contributions
 nine+0.006
 thirteen+0.005
ching+0.005
upid+0.005
 like+0.005
Neg logit contributions
lights-0.014
Really-0.010
 forth-0.010
bel-0.010
nam-0.010
Token
Token ID198
Feature activation-3.04e-01

Pos logit contributions
 thirteen+0.021
 nine+0.020
 enough+0.019
upid+0.018
 like+0.018
Neg logit contributions
lights-0.032
bel-0.025
apy-0.024
kins-0.024
ized-0.024
TokenThe
Token ID464
Feature activation+2.38e-01

Pos logit contributions
 nine+0.023
 thirteen+0.023
 enough+0.022
upid+0.021
 like+0.021
Neg logit contributions
lights-0.034
bel-0.028
ized-0.027
ths-0.027
apy-0.027
Token girl
Token ID2576
Feature activation-3.77e-01

Pos logit contributions
lights+0.031
bel+0.024
kins+0.024
 forth+0.024
ized+0.024
Neg logit contributions
 nine-0.017
-0.016
 thirteen-0.015
ching-0.014
 a-0.014
Token big
Token ID1263
Feature activation-9.77e-01

Pos logit contributions
lights+0.094
 forth+0.072
bel+0.071
kins+0.071
ized+0.071
Neg logit contributions
 nine-0.062
-0.058
 thirteen-0.057
ching-0.055
upid-0.054
Token!
Token ID0
Feature activation-6.17e-01

Pos logit contributions
upid+0.057
 nine+0.056
 thirteen+0.052
ching+0.050
icks+0.049
Neg logit contributions
lights-0.133
 forth-0.111
ized-0.106
ths-0.102
kins-0.102
Token
Token ID198
Feature activation-5.61e-01

Pos logit contributions
 nine+0.036
 thirteen+0.035
ching+0.035
upid+0.032
+0.030
Neg logit contributions
lights-0.083
bel-0.066
ized-0.066
nam-0.065
Really-0.064
Token
Token ID198
Feature activation-5.82e-01

Pos logit contributions
 thirteen+0.034
 nine+0.033
upid+0.030
icks+0.027
ching+0.027
Neg logit contributions
lights-0.074
bel-0.063
ized-0.061
 sudden-0.059
apy-0.059
TokenKay
Token ID37247
Feature activation-1.03e+00

Pos logit contributions
 nine+0.051
 thirteen+0.050
icks+0.049
upid+0.049
ching+0.047
Neg logit contributions
lights-0.058
bel-0.048
ized-0.048
ths-0.046
Really-0.044
Tokenla
Token ID5031
Feature activation-4.18e+00

Pos logit contributions
 nine+0.060
 thirteen+0.058
ching+0.056
upid+0.054
+0.054
Neg logit contributions
lights-0.142
ized-0.115
 forth-0.114
bel-0.113
kins-0.111
Token wondered
Token ID14028
Feature activation-2.05e-01

Pos logit contributions
 nine+0.334
+0.316
 thirteen+0.310
ching+0.298
upid+0.294
Neg logit contributions
lights-0.499
 forth-0.383
kins-0.375
bel-0.374
ized-0.374
Token what
Token ID644
Feature activation-1.06e-01

Pos logit contributions
 thirteen+0.012
 nine+0.012
ching+0.011
upid+0.011
+0.011
Neg logit contributions
lights-0.028
 forth-0.023
nam-0.023
ized-0.022
kins-0.022
Token was
Token ID373
Feature activation-2.90e-01

Pos logit contributions
 nine+0.006
+0.006
 thirteen+0.005
ching+0.005
 like+0.005
Neg logit contributions
lights-0.015
 forth-0.012
kins-0.012
bel-0.012
ized-0.012
Token inside
Token ID2641
Feature activation+8.01e-01

Pos logit contributions
upid+0.025
 thirteen+0.025
 nine+0.025
icks+0.024
ives+0.023
Neg logit contributions
lights-0.028
 forth-0.025
nam-0.023
ized-0.023
bel-0.022
Token,
Token ID11
Feature activation-5.12e-01

Pos logit contributions
lights+0.112
 forth+0.091
kins+0.090
ized+0.090
nam+0.086
Neg logit contributions
 nine-0.047
 thirteen-0.045
ching-0.043
upid-0.040
-0.038
Token far
Token ID1290
Feature activation-1.06e+00

Pos logit contributions
lights+0.090
ized+0.067
bel+0.066
kins+0.064
 forth+0.064
Neg logit contributions
 nine-0.071
 thirteen-0.068
-0.065
ching-0.064
upid-0.064
Token from
Token ID422
Feature activation-6.06e-01

Pos logit contributions
 nine+0.080
 thirteen+0.073
upid+0.071
icks+0.066
 eight+0.064
Neg logit contributions
lights-0.134
 forth-0.115
ized-0.110
kins-0.099
bel-0.099
Token home
Token ID1363
Feature activation+5.88e-03

Pos logit contributions
+0.032
 nine+0.032
 thirteen+0.031
ching+0.031
upid+0.029
Neg logit contributions
lights-0.086
 forth-0.071
ized-0.069
bel-0.069
nam-0.068
Token.
Token ID13
Feature activation-5.37e-01

Pos logit contributions
lights+0.001
kins+0.001
 forth+0.001
bel+0.001
ized+0.001
Neg logit contributions
 nine-0.000
 thirteen-0.000
ching-0.000
-0.000
upid-0.000
Token Kay
Token ID17356
Feature activation-4.79e-01

Pos logit contributions
 nine+0.032
 thirteen+0.030
ching+0.029
upid+0.028
+0.028
Neg logit contributions
lights-0.073
bel-0.060
ized-0.058
 forth-0.057
nam-0.056
Tokenla
Token ID5031
Feature activation-4.11e+00

Pos logit contributions
 nine+0.030
 thirteen+0.028
ching+0.027
upid+0.027
 like+0.026
Neg logit contributions
lights-0.064
ized-0.053
 forth-0.053
ths-0.051
kins-0.050
Token told
Token ID1297
Feature activation-9.47e-01

Pos logit contributions
 nine+0.358
 thirteen+0.338
upid+0.332
ching+0.330
+0.324
Neg logit contributions
lights-0.448
ized-0.343
 forth-0.342
kins-0.340
bel-0.335
Token him
Token ID683
Feature activation+1.62e-01

Pos logit contributions
 thirteen+0.071
 nine+0.070
ching+0.067
upid+0.065
+0.062
Neg logit contributions
lights-0.110
ized-0.090
 forth-0.088
ths-0.085
bel-0.084
Token she
Token ID673
Feature activation-1.18e-01

Pos logit contributions
lights+0.021
bel+0.016
kins+0.016
nam+0.015
apy+0.015
Neg logit contributions
 nine-0.011
 thirteen-0.010
upid-0.010
ching-0.010
 fourteen-0.009
Token was
Token ID373
Feature activation-2.76e-01

Pos logit contributions
+0.008
 nine+0.008
 like+0.007
 thirteen+0.007
ching+0.007
Neg logit contributions
lights-0.015
 forth-0.012
kins-0.012
bel-0.012
ized-0.012
Token just
Token ID655
Feature activation+4.08e-01

Pos logit contributions
 nine+0.019
upid+0.019
 thirteen+0.019
ching+0.017
ives+0.017
Neg logit contributions
lights-0.031
kins-0.026
 forth-0.026
nam-0.026
ized-0.025
Token a
Token ID257
Feature activation-8.18e-02

Pos logit contributions
 thirteen+0.009
upid+0.008
 nine+0.008
ching+0.007
 knows+0.007
Neg logit contributions
lights-0.031
apy-0.026
 sudden-0.026
nam-0.026
ized-0.026
Token little
Token ID1310
Feature activation-1.35e+00

Pos logit contributions
 nine+0.005
+0.005
 like+0.004
 a+0.004
ching+0.004
Neg logit contributions
lights-0.012
ized-0.009
bel-0.009
 forth-0.009
kins-0.009
Token girl
Token ID2576
Feature activation-5.35e-01

Pos logit contributions
 nine+0.122
+0.117
 like+0.111
 a+0.109
 thirteen+0.107
Neg logit contributions
lights-0.152
bel-0.114
kins-0.112
ized-0.109
ths-0.106
Token named
Token ID3706
Feature activation+7.02e-01

Pos logit contributions
 nine+0.040
+0.038
 thirteen+0.036
ching+0.035
upid+0.034
Neg logit contributions
lights-0.067
 forth-0.052
kins-0.051
bel-0.051
ized-0.051
Token Is
Token ID1148
Feature activation-1.02e+00

Pos logit contributions
lights+0.085
 forth+0.064
kins+0.064
bel+0.063
ized+0.063
Neg logit contributions
 nine-0.058
-0.056
 thirteen-0.052
 like-0.052
 a-0.050
Tokenla
Token ID5031
Feature activation-4.11e+00

Pos logit contributions
 nine+0.064
 thirteen+0.062
upid+0.058
+0.056
ching+0.056
Neg logit contributions
lights-0.134
ized-0.109
bel-0.104
uddled-0.102
ths-0.101
Token.
Token ID13
Feature activation-8.65e-01

Pos logit contributions
 nine+0.220
+0.204
 thirteen+0.196
ching+0.184
upid+0.180
Neg logit contributions
lights-0.601
 forth-0.485
kins-0.479
bel-0.478
ized-0.476
Token She
Token ID1375
Feature activation-1.13e+00

Pos logit contributions
ching+0.059
 nine+0.056
 thirteen+0.054
+0.053
upid+0.053
Neg logit contributions
lights-0.112
bel-0.083
 forth-0.081
apy-0.081
Really-0.080
Token loved
Token ID6151
Feature activation-8.08e-02

Pos logit contributions
 nine+0.080
+0.076
 thirteen+0.072
ching+0.070
 like+0.069
Neg logit contributions
lights-0.148
 forth-0.116
kins-0.114
bel-0.113
ized-0.113
Token basketball
Token ID9669
Feature activation+5.43e-01

Pos logit contributions
 nine+0.003
+0.003
 thirteen+0.003
ching+0.002
upid+0.002
Neg logit contributions
lights-0.013
 forth-0.011
bel-0.011
kins-0.011
ized-0.011
Token.
Token ID13
Feature activation-7.27e-01

Pos logit contributions
lights+0.084
 forth+0.068
kins+0.067
bel+0.067
apy+0.066
Neg logit contributions
-0.025
 nine-0.025
 like-0.023
 a-0.021
ching-0.020
Token
Token ID220
Feature activation-1.50e-01

Pos logit contributions
ching+0.026
 nine+0.025
 thirteen+0.024
+0.023
upid+0.023
Neg logit contributions
lights-0.052
 forth-0.042
bel-0.041
nam-0.041
ized-0.040
Token
Token ID198
Feature activation-6.10e-01

Pos logit contributions
 nine+0.008
 thirteen+0.008
+0.007
ching+0.007
upid+0.006
Neg logit contributions
lights-0.021
bel-0.017
kins-0.017
uddle-0.017
apy-0.017
Token
Token ID198
Feature activation-6.19e-01

Pos logit contributions
 thirteen+0.044
 nine+0.039
upid+0.036
ching+0.036
icks+0.034
Neg logit contributions
lights-0.075
bel-0.063
ized-0.061
uddle-0.058
 sudden-0.058
TokenWhen
Token ID2215
Feature activation-5.56e-01

Pos logit contributions
 nine+0.048
 thirteen+0.048
upid+0.045
icks+0.045
ching+0.044
Neg logit contributions
lights-0.068
bel-0.057
ized-0.057
 forth-0.054
ths-0.054
Token Kay
Token ID17356
Feature activation-4.45e-01

Pos logit contributions
 nine+0.040
+0.038
 like+0.035
 a+0.035
 enough+0.034
Neg logit contributions
lights-0.074
kins-0.057
bel-0.056
 forth-0.056
uddle-0.055
Tokenla
Token ID5031
Feature activation-4.11e+00

Pos logit contributions
 thirteen+0.031
 nine+0.029
ching+0.028
upid+0.027
 like+0.027
Neg logit contributions
lights-0.054
 forth-0.046
ized-0.045
ths-0.044
uddle-0.043
Token got
Token ID1392
Feature activation-7.84e-01

Pos logit contributions
 nine+0.299
 thirteen+0.281
+0.276
ching+0.265
upid+0.263
Neg logit contributions
lights-0.513
 forth-0.404
ized-0.397
bel-0.395
kins-0.394
Token on
Token ID319
Feature activation-3.05e-01

Pos logit contributions
 nine+0.034
+0.031
 a+0.027
 like+0.026
 thirteen+0.025
Neg logit contributions
lights-0.127
kins-0.103
ized-0.101
 forth-0.101
bel-0.100
Token the
Token ID262
Feature activation-4.35e-01

Pos logit contributions
 nine+0.016
 thirteen+0.016
ching+0.016
+0.015
upid+0.015
Neg logit contributions
lights-0.044
 forth-0.036
ized-0.035
bel-0.034
nam-0.034
Token train
Token ID4512
Feature activation-1.00e+00

Pos logit contributions
 nine+0.033
+0.031
 thirteen+0.031
ching+0.029
upid+0.029
Neg logit contributions
lights-0.054
 forth-0.042
ized-0.041
bel-0.041
kins-0.040
Token,
Token ID11
Feature activation-3.47e-01

Pos logit contributions
 nine+0.043
 thirteen+0.040
+0.038
ching+0.036
upid+0.034
Neg logit contributions
lights-0.157
 forth-0.130
ized-0.127
bel-0.127
uddle-0.125
Token a
Token ID257
Feature activation+2.82e-03

Pos logit contributions
 thirteen+0.006
upid+0.006
 nine+0.005
ching+0.005
 knows+0.005
Neg logit contributions
lights-0.025
apy-0.022
ized-0.022
 sudden-0.021
kins-0.021
Token little
Token ID1310
Feature activation-1.34e+00

Pos logit contributions
lights+0.000
ized+0.000
bel+0.000
 forth+0.000
kins+0.000
Neg logit contributions
 nine-0.000
-0.000
 a-0.000
 like-0.000
ching-0.000
Token girl
Token ID2576
Feature activation-4.85e-01

Pos logit contributions
 nine+0.124
+0.119
 like+0.112
 thirteen+0.111
 a+0.110
Neg logit contributions
lights-0.149
bel-0.110
kins-0.107
ized-0.106
 forth-0.104
Token named
Token ID3706
Feature activation+9.10e-01

Pos logit contributions
 nine+0.037
+0.035
 thirteen+0.034
ching+0.033
upid+0.032
Neg logit contributions
lights-0.060
 forth-0.047
kins-0.046
bel-0.046
ized-0.045
Token Kay
Token ID17356
Feature activation-3.81e-01

Pos logit contributions
lights+0.102
 forth+0.077
kins+0.075
bel+0.075
ized+0.074
Neg logit contributions
 nine-0.080
-0.076
 thirteen-0.075
ching-0.073
upid-0.071
Tokenla
Token ID5031
Feature activation-4.11e+00

Pos logit contributions
 thirteen+0.025
 nine+0.024
ching+0.023
+0.023
upid+0.022
Neg logit contributions
lights-0.049
ized-0.039
kins-0.039
 forth-0.038
bel-0.038
Token.
Token ID13
Feature activation-5.66e-01

Pos logit contributions
 nine+0.227
+0.211
 thirteen+0.202
ching+0.191
upid+0.185
Neg logit contributions
lights-0.594
 forth-0.478
kins-0.472
bel-0.470
ized-0.468
Token She
Token ID1375
Feature activation-1.10e+00

Pos logit contributions
 nine+0.033
+0.031
ching+0.031
 thirteen+0.031
upid+0.028
Neg logit contributions
lights-0.079
 forth-0.063
bel-0.062
ized-0.061
kins-0.060
Token woke
Token ID19092
Feature activation-1.64e+00

Pos logit contributions
 nine+0.082
+0.076
 thirteen+0.076
upid+0.072
ching+0.071
Neg logit contributions
lights-0.139
 forth-0.108
kins-0.107
bel-0.107
ized-0.106
Token up
Token ID510
Feature activation-1.31e+00

Pos logit contributions
 nine+0.093
+0.087
 thirteen+0.083
ching+0.078
upid+0.076
Neg logit contributions
lights-0.236
 forth-0.189
kins-0.186
bel-0.186
ized-0.185
Token one
Token ID530
Feature activation-9.66e-01

Pos logit contributions
 nine+0.097
+0.093
 thirteen+0.093
upid+0.088
ching+0.088
Neg logit contributions
lights-0.162
 forth-0.128
bel-0.127
ized-0.127
kins-0.123
Tokenawn
Token ID3832
Feature activation-1.26e+00

Pos logit contributions
 nine+0.065
 thirteen+0.059
+0.059
ching+0.056
 enough+0.055
Neg logit contributions
lights-0.097
kins-0.074
ized-0.074
uddle-0.073
har-0.071
Tokenâ
Token ID22940
Feature activation-1.26e+00

Pos logit contributions
 nine+0.094
+0.088
 thirteen+0.086
ching+0.082
upid+0.081
Neg logit contributions
lights-0.158
 forth-0.123
kins-0.121
bel-0.121
ized-0.121
Token
Token ID26391
Feature activation+2.21e-01

Pos logit contributions
 nine+0.096
 thirteen+0.083
upid+0.078
ching+0.078
 enough+0.076
Neg logit contributions
lights-0.150
 forth-0.125
ized-0.124
kins-0.118
har-0.117
Token
Token ID8151
Feature activation-2.25e-01

Pos logit contributions
lights+0.029
bel+0.023
kins+0.023
ized+0.022
 forth+0.022
Neg logit contributions
 nine-0.015
 thirteen-0.014
-0.014
ching-0.013
upid-0.013
Tokens
Token ID82
Feature activation+4.07e-02

Pos logit contributions
 nine+0.018
 thirteen+0.017
ching+0.016
+0.016
 like+0.016
Neg logit contributions
lights-0.026
ized-0.020
bel-0.020
kins-0.020
uddle-0.019
Token fault
Token ID8046
Feature activation-4.10e+00

Pos logit contributions
lights+0.005
bel+0.004
 forth+0.004
kins+0.004
uddle+0.004
Neg logit contributions
 nine-0.003
 thirteen-0.002
-0.002
ching-0.002
upid-0.002
Token.
Token ID13
Feature activation-1.92e-01

Pos logit contributions
 nine+0.264
 thirteen+0.248
+0.235
ching+0.229
upid+0.225
Neg logit contributions
lights-0.550
 forth-0.438
ized-0.423
kins-0.422
bel-0.417
Token
Token ID220
Feature activation+3.42e-02

Pos logit contributions
 nine+0.012
 thirteen+0.011
ching+0.011
upid+0.010
 enough+0.010
Neg logit contributions
lights-0.025
Really-0.020
apy-0.019
uddle-0.019
 forth-0.019
Token
Token ID198
Feature activation-3.27e-01

Pos logit contributions
lights+0.005
bel+0.004
apy+0.004
uddle+0.004
kins+0.004
Neg logit contributions
 nine-0.002
 thirteen-0.002
 enough-0.002
 like-0.002
ching-0.002
Token
Token ID198
Feature activation-3.41e-01

Pos logit contributions
 nine+0.021
 thirteen+0.020
 enough+0.019
upid+0.018
icks+0.017
Neg logit contributions
lights-0.041
bel-0.034
apy-0.034
 sudden-0.034
Really-0.034
TokenThe
Token ID464
Feature activation+3.01e-01

Pos logit contributions
 nine+0.027
 thirteen+0.026
upid+0.025
icks+0.025
 enough+0.024
Neg logit contributions
lights-0.037
ized-0.030
bel-0.030
apy-0.029
ths-0.029
Tokenâ
Token ID22940
Feature activation-1.33e+00

Pos logit contributions
 nine+0.039
 thirteen+0.036
ching+0.035
+0.034
upid+0.033
Neg logit contributions
lights-0.099
 forth-0.078
bel-0.078
kins-0.077
ized-0.077
Token
Token ID26391
Feature activation+2.65e-01

Pos logit contributions
 nine+0.115
 enough+0.101
 thirteen+0.101
icks+0.100
ching+0.098
Neg logit contributions
lights-0.146
 forth-0.126
ized-0.123
ths-0.114
har-0.114
Token
Token ID198
Feature activation-5.28e-01

Pos logit contributions
lights+0.034
uddle+0.028
bel+0.028
kins+0.028
ized+0.028
Neg logit contributions
 nine-0.017
 thirteen-0.016
 enough-0.014
upid-0.014
ching-0.014
Token
Token ID198
Feature activation-5.42e-01

Pos logit contributions
 nine+0.033
 thirteen+0.032
 enough+0.029
upid+0.027
 like+0.027
Neg logit contributions
lights-0.069
apy-0.056
uddle-0.055
 sudden-0.055
bel-0.054
TokenKay
Token ID37247
Feature activation-8.18e-01

Pos logit contributions
 nine+0.044
 thirteen+0.042
 enough+0.040
icks+0.040
upid+0.040
Neg logit contributions
lights-0.059
ized-0.047
bel-0.047
apy-0.046
ths-0.045
Tokenla
Token ID5031
Feature activation-4.10e+00

Pos logit contributions
 nine+0.051
 thirteen+0.047
ching+0.046
+0.046
upid+0.044
Neg logit contributions
lights-0.110
 forth-0.089
ized-0.089
bel-0.087
kins-0.085
Token put
Token ID1234
Feature activation-6.92e-01

Pos logit contributions
 nine+0.340
 thirteen+0.317
upid+0.315
ching+0.310
 like+0.296
Neg logit contributions
lights-0.455
 forth-0.360
ized-0.358
kins-0.354
ths-0.343
Token the
Token ID262
Feature activation-3.62e-01

Pos logit contributions
 nine+0.038
+0.036
 thirteen+0.035
upid+0.032
ching+0.032
Neg logit contributions
lights-0.100
 forth-0.082
kins-0.080
bel-0.079
ized-0.079
Token bell
Token ID8966
Feature activation-1.18e+00

Pos logit contributions
 nine+0.031
+0.030
 thirteen+0.029
ching+0.028
upid+0.028
Neg logit contributions
lights-0.041
 forth-0.031
kins-0.030
bel-0.030
ized-0.030
Token and
Token ID290
Feature activation-2.75e-01

Pos logit contributions
 nine+0.075
+0.071
 thirteen+0.067
ching+0.064
 like+0.063
Neg logit contributions
lights-0.161
 forth-0.127
kins-0.126
bel-0.125
ized-0.125
Token the
Token ID262
Feature activation-2.58e-01

Pos logit contributions
 nine+0.019
+0.019
 thirteen+0.018
ching+0.017
 like+0.017
Neg logit contributions
lights-0.036
 forth-0.028
kins-0.027
bel-0.027
ized-0.027
Token family
Token ID1641
Feature activation+4.38e-01

Pos logit contributions
lights+0.157
 forth+0.117
kins+0.117
ized+0.116
bel+0.116
Neg logit contributions
-0.105
 nine-0.105
 a-0.097
 like-0.096
ching-0.093
Token.
Token ID13
Feature activation-3.53e-01

Pos logit contributions
lights+0.061
 forth+0.049
kins+0.049
ized+0.048
bel+0.048
Neg logit contributions
 nine-0.027
 thirteen-0.024
upid-0.023
-0.023
ching-0.022
Token
Token ID198
Feature activation-5.78e-01

Pos logit contributions
 nine+0.018
+0.017
 thirteen+0.015
ching+0.014
upid+0.014
Neg logit contributions
lights-0.053
 forth-0.043
kins-0.042
bel-0.042
ized-0.042
Token
Token ID198
Feature activation-5.62e-01

Pos logit contributions
 nine+0.033
 thirteen+0.032
 enough+0.029
upid+0.028
 like+0.028
Neg logit contributions
lights-0.080
bel-0.065
apy-0.064
kins-0.063
ized-0.063
TokenKay
Token ID37247
Feature activation-8.31e-01

Pos logit contributions
 nine+0.041
 thirteen+0.039
upid+0.037
 enough+0.037
 like+0.036
Neg logit contributions
lights-0.068
bel-0.054
ized-0.053
apy-0.052
kins-0.052
Tokenla
Token ID5031
Feature activation-4.09e+00

Pos logit contributions
 nine+0.057
 thirteen+0.053
ching+0.050
+0.050
upid+0.049
Neg logit contributions
lights-0.109
ized-0.087
 forth-0.086
bel-0.085
kins-0.083
Token was
Token ID373
Feature activation-1.99e-01

Pos logit contributions
 nine+0.339
 thirteen+0.320
upid+0.313
ching+0.309
+0.295
Neg logit contributions
lights-0.460
 forth-0.361
ized-0.359
kins-0.355
bel-0.348
Token very
Token ID845
Feature activation+7.74e-01

Pos logit contributions
upid+0.013
 nine+0.013
 thirteen+0.013
una+0.013
ching+0.012
Neg logit contributions
lights-0.023
 forth-0.019
har-0.019
bel-0.019
ized-0.018
Token happy
Token ID3772
Feature activation+2.51e-01

Pos logit contributions
lights+0.088
bel+0.068
 forth+0.067
kins+0.067
ized+0.066
Neg logit contributions
 nine-0.065
 thirteen-0.061
-0.060
ching-0.058
upid-0.058
Token that
Token ID326
Feature activation-1.04e+00

Pos logit contributions
lights+0.040
 forth+0.033
bel+0.032
kins+0.032
ized+0.032
Neg logit contributions
 nine-0.010
-0.009
 thirteen-0.009
ching-0.008
upid-0.008
Token she
Token ID673
Feature activation+1.02e-02

Pos logit contributions
 nine+0.082
+0.078
 thirteen+0.076
ching+0.073
upid+0.071
Neg logit contributions
lights-0.126
 forth-0.097
kins-0.095
bel-0.094
ized-0.094
Token
Token ID198
Feature activation-7.68e-01

Pos logit contributions
 thirteen+0.047
 nine+0.045
upid+0.040
ching+0.039
+0.038
Neg logit contributions
lights-0.108
bel-0.087
ized-0.086
uddle-0.083
 forth-0.083
TokenOne
Token ID3198
Feature activation-8.48e-01

Pos logit contributions
 nine+0.051
 thirteen+0.050
upid+0.047
ching+0.047
+0.045
Neg logit contributions
lights-0.098
ized-0.078
bel-0.078
 forth-0.076
ths-0.075
Token day
Token ID1110
Feature activation-7.97e-02

Pos logit contributions
 nine+0.068
 thirteen+0.065
+0.063
ching+0.061
upid+0.060
Neg logit contributions
lights-0.101
 forth-0.078
bel-0.076
kins-0.076
ized-0.075
Token,
Token ID11
Feature activation-4.61e-01

Pos logit contributions
 nine+0.003
 thirteen+0.003
+0.003
ching+0.003
upid+0.002
Neg logit contributions
lights-0.013
 forth-0.011
bel-0.010
ized-0.010
kins-0.010
Token Kay
Token ID17356
Feature activation-4.22e-01

Pos logit contributions
 nine+0.031
+0.028
 like+0.028
 a+0.027
 thirteen+0.025
Neg logit contributions
lights-0.063
kins-0.050
 forth-0.049
uddle-0.049
ized-0.047
Tokenla
Token ID5031
Feature activation-4.08e+00

Pos logit contributions
 thirteen+0.029
 nine+0.028
ching+0.026
upid+0.025
+0.025
Neg logit contributions
lights-0.054
ized-0.043
 forth-0.043
bel-0.042
kins-0.042
Token decided
Token ID3066
Feature activation-6.03e-02

Pos logit contributions
 nine+0.301
 thirteen+0.287
+0.274
upid+0.267
ching+0.267
Neg logit contributions
lights-0.505
 forth-0.398
kins-0.393
ized-0.392
bel-0.391
Token to
Token ID284
Feature activation-4.45e-01

Pos logit contributions
 nine+0.004
 thirteen+0.004
upid+0.004
ching+0.003
icks+0.003
Neg logit contributions
lights-0.008
 forth-0.007
ized-0.007
bel-0.007
ths-0.006
Token take
Token ID1011
Feature activation-1.01e+00

Pos logit contributions
 thirteen+0.037
 nine+0.036
ching+0.034
 fourteen+0.032
upid+0.030
Neg logit contributions
lights-0.048
 forth-0.041
kins-0.037
bel-0.037
ths-0.036
Token the
Token ID262
Feature activation-4.13e-01

Pos logit contributions
 thirteen+0.045
 nine+0.041
upid+0.038
+0.035
ching+0.032
Neg logit contributions
lights-0.150
 forth-0.131
nam-0.123
kins-0.122
ized-0.122
Token subway
Token ID19612
Feature activation-1.30e+00

Pos logit contributions
 nine+0.034
 thirteen+0.033
+0.032
ching+0.031
upid+0.031
Neg logit contributions
lights-0.048
 forth-0.037
ized-0.036
bel-0.036
kins-0.035
Token a
Token ID257
Feature activation+3.37e-03

Pos logit contributions
 thirteen+0.006
upid+0.006
 nine+0.006
ching+0.005
 knows+0.005
Neg logit contributions
lights-0.028
apy-0.024
 forth-0.023
ized-0.023
kins-0.023
Token little
Token ID1310
Feature activation-1.31e+00

Pos logit contributions
lights+0.001
ized+0.000
bel+0.000
 forth+0.000
kins+0.000
Neg logit contributions
 nine-0.000
-0.000
 a-0.000
 like-0.000
ching-0.000
Token girl
Token ID2576
Feature activation-5.02e-01

Pos logit contributions
 nine+0.120
+0.115
 like+0.108
 thirteen+0.108
ching+0.106
Neg logit contributions
lights-0.144
bel-0.106
kins-0.103
ized-0.102
 forth-0.102
Token named
Token ID3706
Feature activation+9.16e-01

Pos logit contributions
 nine+0.039
+0.037
 thirteen+0.037
ching+0.035
upid+0.035
Neg logit contributions
lights-0.061
 forth-0.047
kins-0.046
bel-0.046
ized-0.045
Token Car
Token ID1879
Feature activation-1.95e+00

Pos logit contributions
lights+0.104
 forth+0.078
kins+0.076
bel+0.076
ized+0.075
Neg logit contributions
 nine-0.080
-0.077
 thirteen-0.075
ching-0.072
upid-0.071
Tokenla
Token ID5031
Feature activation-4.08e+00

Pos logit contributions
 thirteen+0.105
 nine+0.103
+0.098
upid+0.093
ching+0.092
Neg logit contributions
lights-0.270
kins-0.226
bel-0.220
ized-0.219
uddle-0.212
Token.
Token ID13
Feature activation-5.62e-01

Pos logit contributions
 nine+0.252
 thirteen+0.243
+0.232
upid+0.222
ching+0.221
Neg logit contributions
lights-0.549
kins-0.445
bel-0.438
 forth-0.437
ized-0.433
Token She
Token ID1375
Feature activation-1.11e+00

Pos logit contributions
 nine+0.032
+0.032
ching+0.031
 thirteen+0.030
upid+0.029
Neg logit contributions
lights-0.077
 forth-0.062
bel-0.061
nam-0.060
ized-0.059
Token was
Token ID373
Feature activation-1.36e-01

Pos logit contributions
 nine+0.078
+0.074
 thirteen+0.071
ching+0.068
upid+0.067
Neg logit contributions
lights-0.144
 forth-0.113
kins-0.111
bel-0.110
ized-0.110
Token three
Token ID1115
Feature activation-3.56e-01

Pos logit contributions
 nine+0.007
 thirteen+0.006
+0.006
upid+0.006
ching+0.006
Neg logit contributions
lights-0.020
 forth-0.016
nam-0.016
bel-0.016
kins-0.016
Token years
Token ID812
Feature activation-8.21e-02

Pos logit contributions
 nine+0.030
+0.029
 like+0.028
 thirteen+0.027
 a+0.027
Neg logit contributions
lights-0.040
 forth-0.031
bel-0.031
kins-0.029
ized-0.029
Token was
Token ID373
Feature activation-2.10e-01

Pos logit contributions
lights+0.001
 forth+0.000
kins+0.000
ized+0.000
bel+0.000
Neg logit contributions
 nine-0.000
 thirteen-0.000
-0.000
ching-0.000
upid-0.000
Token a
Token ID257
Feature activation-8.41e-02

Pos logit contributions
 thirteen+0.007
 nine+0.007
upid+0.006
ching+0.006
 knows+0.005
Neg logit contributions
lights-0.033
ized-0.028
apy-0.028
kins-0.027
 forth-0.027
Token girl
Token ID2576
Feature activation-5.24e-01

Pos logit contributions
 nine+0.004
+0.004
 a+0.004
 like+0.003
ching+0.003
Neg logit contributions
lights-0.014
ized-0.011
bel-0.011
 forth-0.011
kins-0.010
Token named
Token ID3706
Feature activation+7.88e-01

Pos logit contributions
 nine+0.038
+0.036
 thirteen+0.034
 like+0.033
ching+0.033
Neg logit contributions
lights-0.068
 forth-0.052
kins-0.052
bel-0.052
ized-0.051
Token Kay
Token ID17356
Feature activation-4.27e-01

Pos logit contributions
lights+0.095
 forth+0.072
kins+0.071
bel+0.071
ized+0.071
Neg logit contributions
 nine-0.065
-0.063
 thirteen-0.059
 like-0.057
ching-0.057
Tokenla
Token ID5031
Feature activation-4.08e+00

Pos logit contributions
 thirteen+0.029
 nine+0.028
+0.026
ching+0.026
upid+0.025
Neg logit contributions
lights-0.055
ized-0.044
 forth-0.043
kins-0.043
bel-0.043
Token.
Token ID13
Feature activation-6.95e-01

Pos logit contributions
 nine+0.202
+0.191
 like+0.166
 thirteen+0.164
ching+0.162
Neg logit contributions
lights-0.624
 forth-0.505
ized-0.493
bel-0.491
kins-0.490
Token Kay
Token ID17356
Feature activation-4.44e-01

Pos logit contributions
 nine+0.043
ching+0.041
+0.040
 thirteen+0.040
upid+0.037
Neg logit contributions
lights-0.095
 forth-0.074
bel-0.074
ized-0.073
nam-0.070
Tokenla
Token ID5031
Feature activation-4.07e+00

Pos logit contributions
 nine+0.028
 thirteen+0.028
ching+0.026
upid+0.025
+0.025
Neg logit contributions
lights-0.059
ized-0.048
 forth-0.046
kins-0.046
bel-0.045
Token went
Token ID1816
Feature activation-1.31e-01

Pos logit contributions
 nine+0.282
+0.273
 thirteen+0.254
 like+0.244
ching+0.244
Neg logit contributions
lights-0.535
 forth-0.418
bel-0.408
kins-0.408
ized-0.406
Token out
Token ID503
Feature activation-1.28e+00

Pos logit contributions
 thirteen+0.008
+0.008
 nine+0.008
upid+0.007
ching+0.007
Neg logit contributions
lights-0.017
 forth-0.015
bel-0.015
uddle-0.014
ized-0.014
Token spraying
Token ID40170
Feature activation-4.87e-01

Pos logit contributions
 nine+0.039
upid+0.035
 thirteen+0.034
+0.033
ching+0.031
Neg logit contributions
lights-0.069
 forth-0.054
ized-0.054
kins-0.053
uddle-0.051
Token all
Token ID477
Feature activation+1.91e-01

Pos logit contributions
 nine+0.032
+0.028
 thirteen+0.028
upid+0.027
ching+0.027
Neg logit contributions
lights-0.067
 forth-0.052
kins-0.051
ized-0.051
bel-0.050
Token around
Token ID1088
Feature activation-7.78e-01

Pos logit contributions
lights+0.026
 forth+0.021
ized+0.019
kins+0.018
bel+0.017
Neg logit contributions
 nine-0.013
 thirteen-0.013
ching-0.012
upid-0.012
-0.012
Token.
Token ID13
Feature activation-3.27e-01

Pos logit contributions
 nine+0.047
 thirteen+0.043
+0.042
upid+0.042
ching+0.041
Neg logit contributions
lights-0.109
 forth-0.087
kins-0.086
ized-0.085
bel-0.083
Token Mar
Token ID1526
Feature activation-1.04e+00

Pos logit contributions
 nine+0.016
 thirteen+0.015
ching+0.013
upid+0.013
+0.013
Neg logit contributions
lights-0.049
bel-0.039
ized-0.039
apy-0.039
 forth-0.039
Tokenla
Token ID5031
Feature activation-4.08e+00

Pos logit contributions
 nine+0.069
 thirteen+0.066
+0.066
ching+0.065
upid+0.062
Neg logit contributions
lights-0.135
 forth-0.111
kins-0.107
ized-0.107
bel-0.105
Token was
Token ID373
Feature activation-2.23e-01

Pos logit contributions
 nine+0.332
 thirteen+0.308
+0.308
ching+0.296
upid+0.294
Neg logit contributions
lights-0.480
 forth-0.368
kins-0.363
ized-0.362
bel-0.359
Token so
Token ID523
Feature activation+7.88e-01

Pos logit contributions
upid+0.018
 nine+0.017
una+0.017
 thirteen+0.016
ives+0.016
Neg logit contributions
lights-0.023
 sudden-0.019
 forth-0.019
bel-0.019
ized-0.019
Token excited
Token ID6568
Feature activation+6.72e-01

Pos logit contributions
lights+0.081
ized+0.065
bel+0.064
apy+0.064
kins+0.062
Neg logit contributions
 nine-0.073
 thirteen-0.068
ching-0.064
upid-0.064
una-0.062
Token -
Token ID532
Feature activation+1.81e+00

Pos logit contributions
lights+0.093
ized+0.076
 forth+0.075
bel+0.072
ths+0.071
Neg logit contributions
 nine-0.044
 thirteen-0.041
upid-0.040
ching-0.037
-0.036
Token she
Token ID673
Feature activation-9.64e-02

Pos logit contributions
lights+0.192
 forth+0.150
bel+0.142
ized+0.140
apy+0.139
Neg logit contributions
 nine-0.162
 thirteen-0.158
upid-0.153
ching-0.152
-0.142
Token year
Token ID614
Feature activation-1.80e+00

Pos logit contributions
 nine+0.017
+0.016
 a+0.014
 like+0.014
ching+0.014
Neg logit contributions
lights-0.031
 forth-0.025
bel-0.024
ized-0.024
nam-0.024
Token old
Token ID1468
Feature activation-7.27e-01

Pos logit contributions
 nine+0.131
+0.123
 thirteen+0.122
ching+0.119
upid+0.115
Neg logit contributions
lights-0.231
ized-0.175
 forth-0.175
bel-0.173
kins-0.173
Token girl
Token ID2576
Feature activation-4.37e-01

Pos logit contributions
 nine+0.061
+0.055
 a+0.054
 like+0.054
 thirteen+0.051
Neg logit contributions
lights-0.088
ized-0.066
kins-0.066
 forth-0.066
bel-0.066
Token named
Token ID3706
Feature activation+8.20e-01

Pos logit contributions
 nine+0.034
 thirteen+0.032
+0.032
ching+0.031
upid+0.031
Neg logit contributions
lights-0.053
 forth-0.041
kins-0.040
bel-0.040
ized-0.039
Token Kay
Token ID17356
Feature activation-3.78e-01

Pos logit contributions
lights+0.084
 forth+0.063
bel+0.061
nam+0.061
kins+0.060
Neg logit contributions
 nine-0.075
 thirteen-0.074
ching-0.073
-0.072
upid-0.069
Tokenla
Token ID5031
Feature activation-4.08e+00

Pos logit contributions
 thirteen+0.025
 nine+0.023
ching+0.022
upid+0.022
+0.021
Neg logit contributions
lights-0.049
ized-0.039
kins-0.039
bel-0.039
 forth-0.038
Token.
Token ID13
Feature activation-8.57e-01

Pos logit contributions
 nine+0.219
+0.205
 thirteen+0.192
ching+0.183
 like+0.177
Neg logit contributions
lights-0.599
 forth-0.483
kins-0.475
bel-0.474
ized-0.472
Token Every
Token ID3887
Feature activation-1.62e+00

Pos logit contributions
ching+0.060
 nine+0.057
+0.056
 thirteen+0.054
upid+0.053
Neg logit contributions
lights-0.110
 forth-0.082
bel-0.082
Really-0.080
nam-0.080
Token day
Token ID1110
Feature activation-1.02e-01

Pos logit contributions
 thirteen+0.157
 nine+0.155
upid+0.136
 fourteen+0.135
ching+0.131
Neg logit contributions
lights-0.162
 forth-0.124
uddle-0.120
apy-0.119
bel-0.117
Token,
Token ID11
Feature activation-5.78e-01

Pos logit contributions
 thirteen+0.006
 nine+0.006
ching+0.006
upid+0.005
+0.005
Neg logit contributions
lights-0.014
 forth-0.011
bel-0.011
ized-0.011
apy-0.011
Token Kay
Token ID17356
Feature activation-4.00e-01

Pos logit contributions
 nine+0.045
+0.043
 thirteen+0.040
 like+0.039
ching+0.038
Neg logit contributions
lights-0.071
 forth-0.055
kins-0.054
ized-0.053
bel-0.053
Token her
Token ID607
Feature activation-1.95e-01

Pos logit contributions
 nine+0.007
 thirteen+0.006
ching+0.006
+0.006
upid+0.006
Neg logit contributions
lights-0.014
ized-0.012
 forth-0.011
bel-0.011
kins-0.011
Token.
Token ID13
Feature activation-3.97e-01

Pos logit contributions
 nine+0.013
 thirteen+0.012
upid+0.012
ching+0.012
+0.011
Neg logit contributions
lights-0.025
bel-0.020
 forth-0.020
kins-0.020
ized-0.019
Token He
Token ID679
Feature activation-5.88e-01

Pos logit contributions
ching+0.027
 nine+0.027
upid+0.026
 thirteen+0.026
una+0.025
Neg logit contributions
lights-0.048
bel-0.040
Really-0.038
ized-0.037
nam-0.036
Token asked
Token ID1965
Feature activation+4.02e-01

Pos logit contributions
 nine+0.044
+0.043
 thirteen+0.040
ching+0.038
 like+0.038
Neg logit contributions
lights-0.074
 forth-0.057
kins-0.056
bel-0.056
ized-0.055
Token Kay
Token ID17356
Feature activation-4.40e-01

Pos logit contributions
lights+0.052
bel+0.043
nam+0.042
 forth+0.042
ized+0.042
Neg logit contributions
 thirteen-0.024
ching-0.024
 nine-0.024
upid-0.023
-0.022
Tokenla
Token ID5031
Feature activation-4.08e+00

Pos logit contributions
 thirteen+0.034
ching+0.033
 nine+0.032
upid+0.032
icks+0.031
Neg logit contributions
lights-0.049
bel-0.038
 forth-0.038
ized-0.038
nam-0.036
Token what
Token ID644
Feature activation-6.73e-02

Pos logit contributions
 thirteen+0.282
ching+0.259
 nine+0.255
upid+0.253
 fourteen+0.244
Neg logit contributions
lights-0.474
kins-0.395
bel-0.393
nam-0.389
 forth-0.385
Token she
Token ID673
Feature activation-1.10e-01

Pos logit contributions
 nine+0.006
 thirteen+0.005
upid+0.005
ching+0.005
+0.005
Neg logit contributions
lights-0.008
kins-0.006
bel-0.006
ized-0.006
 forth-0.006
Token was
Token ID373
Feature activation-2.55e-01

Pos logit contributions
+0.007
 nine+0.007
 like+0.006
 a+0.006
ching+0.006
Neg logit contributions
lights-0.016
 forth-0.012
bel-0.012
kins-0.012
nam-0.012
Token doing
Token ID1804
Feature activation-1.16e+00

Pos logit contributions
 thirteen+0.022
upid+0.022
ching+0.022
 nine+0.021
una+0.021
Neg logit contributions
ized-0.020
kins-0.020
 forth-0.019
lights-0.019
nam-0.018
Token so
Token ID523
Feature activation+8.03e-01

Pos logit contributions
 nine+0.077
 thirteen+0.075
upid+0.071
ching+0.068
icks+0.062
Neg logit contributions
lights-0.153
kins-0.128
 forth-0.124
ized-0.124
bel-0.122
Token that
Token ID326
Feature activation-9.46e-01

Pos logit contributions
lights+0.069
 forth+0.057
ized+0.056
ths+0.055
kins+0.055
Neg logit contributions
 nine-0.022
-0.021
 thirteen-0.021
ching-0.020
upid-0.019
Token day
Token ID1110
Feature activation+7.61e-02

Pos logit contributions
 thirteen+0.113
icks+0.103
 nine+0.103
upid+0.100
aly+0.096
Neg logit contributions
lights-0.063
 forth-0.061
lf-0.047
kins-0.046
 sudden-0.045
Token on
Token ID319
Feature activation-1.23e-01

Pos logit contributions
lights+0.010
 forth+0.009
kins+0.008
ized+0.008
bel+0.008
Neg logit contributions
 nine-0.004
 thirteen-0.004
-0.004
ching-0.004
upid-0.004
Token,
Token ID11
Feature activation-1.41e-01

Pos logit contributions
 nine+0.003
+0.003
 thirteen+0.003
ching+0.002
 like+0.002
Neg logit contributions
lights-0.021
 forth-0.018
bel-0.018
kins-0.018
ized-0.018
Token she
Token ID673
Feature activation+2.52e-01

Pos logit contributions
 a+0.008
 nine+0.008
 like+0.008
+0.008
 right+0.007
Neg logit contributions
lights-0.021
uddle-0.017
har-0.017
kins-0.017
ushed-0.017
Token saved
Token ID7448
Feature activation+1.68e+00

Pos logit contributions
lights+0.033
 forth+0.028
kins+0.027
bel+0.027
ths+0.027
Neg logit contributions
 nine-0.015
 thirteen-0.015
upid-0.014
-0.014
ching-0.013
Token every
Token ID790
Feature activation+5.09e-01

Pos logit contributions
lights+0.230
 forth+0.192
ized+0.186
nam+0.185
bel+0.185
Neg logit contributions
 nine-0.095
-0.092
 thirteen-0.090
upid-0.087
ching-0.085
Token penny
Token ID26369
Feature activation-3.94e-01

Pos logit contributions
lights+0.067
 forth+0.052
kins+0.051
bel+0.051
ized+0.051
Neg logit contributions
 nine-0.036
-0.034
 thirteen-0.032
ching-0.031
 like-0.030
Token she
Token ID673
Feature activation+2.10e-01

Pos logit contributions
 nine+0.027
 thirteen+0.027
upid+0.025
icks+0.022
+0.022
Neg logit contributions
lights-0.049
kins-0.042
bel-0.041
ized-0.041
 forth-0.041
Token got
Token ID1392
Feature activation-5.60e-01

Pos logit contributions
lights+0.030
apy+0.022
 forth+0.022
uddle+0.022
kins+0.021
Neg logit contributions
-0.014
 nine-0.014
 like-0.014
 never-0.013
 a-0.013
Token and
Token ID290
Feature activation-2.05e-01

Pos logit contributions
 nine+0.029
+0.027
 thirteen+0.026
ching+0.024
upid+0.024
Neg logit contributions
lights-0.082
 forth-0.067
bel-0.066
kins-0.066
ized-0.066
Token Ben
Token ID3932
Feature activation-5.45e-01

Pos logit contributions
lights+0.023
 forth+0.021
nam+0.019
kins+0.018
ized+0.018
Neg logit contributions
ching-0.013
 nine-0.013
-0.012
 thirteen-0.012
 never-0.011
Token say
Token ID910
Feature activation-2.55e-01

Pos logit contributions
 nine+0.042
 thirteen+0.041
ching+0.041
one+0.041
upid+0.039
Neg logit contributions
lights-0.052
 forth-0.051
nam-0.043
kins-0.042
uddle-0.042
Token,
Token ID11
Feature activation+3.08e-02

Pos logit contributions
 nine+0.013
 thirteen+0.013
+0.012
upid+0.012
ching+0.012
Neg logit contributions
lights-0.035
apy-0.029
kins-0.029
 forth-0.029
uddle-0.028
Token "
Token ID366
Feature activation+1.26e+00

Pos logit contributions
lights+0.004
 forth+0.003
kins+0.003
bel+0.003
ized+0.003
Neg logit contributions
 nine-0.002
upid-0.002
-0.002
 thirteen-0.002
ching-0.002
TokenYou
Token ID1639
Feature activation-1.93e-01

Pos logit contributions
lights+0.137
 forth+0.101
kins+0.099
bel+0.098
ized+0.098
Neg logit contributions
 nine-0.117
-0.112
 thirteen-0.109
ching-0.105
 like-0.104
Token too
Token ID1165
Feature activation+2.38e+00

Pos logit contributions
 thirteen+0.011
 nine+0.011
ching+0.011
una+0.010
upid+0.009
Neg logit contributions
lights-0.022
 forth-0.020
kins-0.019
nam-0.019
uddle-0.019
Token,
Token ID11
Feature activation+9.01e-02

Pos logit contributions
lights+0.282
bel+0.233
uddle+0.227
nam+0.227
ized+0.222
Neg logit contributions
 thirteen-0.153
 nine-0.151
ching-0.141
-0.139
upid-0.135
Token lady
Token ID10846
Feature activation-3.97e-01

Pos logit contributions
lights+0.011
 forth+0.009
kins+0.008
uddle+0.008
ized+0.008
Neg logit contributions
ching-0.006
 nine-0.006
-0.006
 thirteen-0.006
upid-0.006
Token!
Token ID0
Feature activation+1.42e-01

Pos logit contributions
 thirteen+0.026
upid+0.026
ching+0.025
 nine+0.025
+0.024
Neg logit contributions
lights-0.048
kins-0.040
 forth-0.039
bel-0.038
uddle-0.036
Token Bye
Token ID47843
Feature activation-6.03e-01

Pos logit contributions
lights+0.015
Really+0.012
apy+0.012
 forth+0.011
 Sorry+0.011
Neg logit contributions
 nine-0.011
ching-0.011
 thirteen-0.011
upid-0.010
-0.010
Token!"
Token ID2474
Feature activation-1.13e+00

Pos logit contributions
 nine+0.027
+0.026
 thirteen+0.024
ching+0.023
upid+0.021
Neg logit contributions
lights-0.092
 forth-0.076
bel-0.075
kins-0.074
uddle-0.074
Token perfect
Token ID2818
Feature activation+1.57e-01

Pos logit contributions
 nine+0.001
+0.001
 thirteen+0.001
 like+0.001
ching+0.001
Neg logit contributions
lights-0.002
 forth-0.001
kins-0.001
ized-0.001
bel-0.001
Token place
Token ID1295
Feature activation+1.36e+00

Pos logit contributions
lights+0.018
 forth+0.014
bel+0.014
kins+0.014
uddle+0.013
Neg logit contributions
 nine-0.013
 thirteen-0.012
-0.012
ching-0.012
upid-0.012
Token to
Token ID284
Feature activation-3.20e-01

Pos logit contributions
lights+0.206
kins+0.165
 forth+0.164
bel+0.164
ized+0.163
Neg logit contributions
 nine-0.068
 thirteen-0.062
-0.058
ching-0.058
upid-0.057
Token learn
Token ID2193
Feature activation-8.84e-01

Pos logit contributions
 nine+0.024
 thirteen+0.024
ching+0.022
+0.022
upid+0.021
Neg logit contributions
lights-0.038
 forth-0.030
kins-0.029
bel-0.029
ized-0.029
Token and
Token ID290
Feature activation-1.09e-01

Pos logit contributions
 nine+0.059
 thirteen+0.057
upid+0.053
ching+0.049
+0.047
Neg logit contributions
lights-0.121
ized-0.091
bel-0.091
kins-0.090
 forth-0.088
Token explore
Token ID7301
Feature activation+1.99e+00

Pos logit contributions
 nine+0.007
 thirteen+0.006
+0.006
ching+0.006
upid+0.006
Neg logit contributions
lights-0.015
 forth-0.012
bel-0.012
kins-0.011
ized-0.011
Token new
Token ID649
Feature activation+8.63e-01

Pos logit contributions
lights+0.277
 forth+0.222
bel+0.218
kins+0.217
ized+0.215
Neg logit contributions
 nine-0.119
-0.115
 thirteen-0.105
 like-0.103
ching-0.103
Token things
Token ID1243
Feature activation-1.81e-01

Pos logit contributions
lights+0.091
 forth+0.066
kins+0.065
bel+0.065
ized+0.064
Neg logit contributions
 nine-0.082
-0.079
 thirteen-0.076
ching-0.074
 like-0.073
Token.
Token ID13
Feature activation-1.17e-01

Pos logit contributions
 nine+0.013
 thirteen+0.012
upid+0.011
ching+0.011
+0.011
Neg logit contributions
lights-0.024
kins-0.019
ized-0.019
 forth-0.019
bel-0.018
Token
Token ID220
Feature activation+4.04e-03

Pos logit contributions
 nine+0.006
 thirteen+0.006
ching+0.006
+0.005
upid+0.005
Neg logit contributions
lights-0.017
 forth-0.013
bel-0.013
kins-0.013
ized-0.013
Token
Token ID198
Feature activation-4.00e-01

Pos logit contributions
lights+0.001
bel+0.000
kins+0.000
uddle+0.000
apy+0.000
Neg logit contributions
 nine-0.000
 thirteen-0.000
 enough-0.000
 like-0.000
ching-0.000
Token not
Token ID407
Feature activation+1.40e-01

Pos logit contributions
lights+0.019
 forth+0.015
kins+0.015
ized+0.015
bel+0.015
Neg logit contributions
 nine-0.007
 thirteen-0.007
-0.007
ching-0.007
upid-0.006
Token listen
Token ID6004
Feature activation-8.43e-01

Pos logit contributions
lights+0.018
 forth+0.016
kins+0.015
bel+0.014
nam+0.014
Neg logit contributions
 nine-0.008
 thirteen-0.008
-0.007
upid-0.007
 fourteen-0.007
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
 nine+0.065
 thirteen+0.062
upid+0.060
+0.056
ching+0.055
Neg logit contributions
lights-0.108
bel-0.081
ized-0.080
kins-0.078
 forth-0.077
Token They
Token ID1119
Feature activation+1.54e-01

Pos logit contributions
lights+0.033
 forth+0.025
bel+0.024
kins+0.024
ized+0.024
Neg logit contributions
 nine-0.020
-0.019
 thirteen-0.018
ching-0.018
upid-0.017
Token were
Token ID547
Feature activation+2.40e-01

Pos logit contributions
lights+0.021
 forth+0.016
bel+0.016
kins+0.016
ized+0.016
Neg logit contributions
 nine-0.010
-0.010
 like-0.010
 a-0.009
 thirteen-0.009
Token too
Token ID1165
Feature activation+2.29e+00

Pos logit contributions
lights+0.028
 forth+0.022
kins+0.022
nam+0.021
ized+0.021
Neg logit contributions
-0.018
 nine-0.018
 thirteen-0.017
upid-0.017
ching-0.017
Token playful
Token ID34264
Feature activation-9.34e-02

Pos logit contributions
lights+0.273
bel+0.207
kins+0.207
 forth+0.205
ized+0.205
Neg logit contributions
 nine-0.184
 thirteen-0.177
-0.176
ching-0.164
upid-0.163
Token.
Token ID13
Feature activation+2.94e-01

Pos logit contributions
 nine+0.006
 thirteen+0.006
upid+0.006
+0.005
ching+0.005
Neg logit contributions
lights-0.013
 forth-0.010
ized-0.009
bel-0.009
kins-0.009
Token They
Token ID1119
Feature activation+1.79e-01

Pos logit contributions
lights+0.038
 forth+0.029
kins+0.029
bel+0.029
ized+0.028
Neg logit contributions
 nine-0.021
-0.020
 thirteen-0.020
ching-0.019
upid-0.018
Token kept
Token ID4030
Feature activation+1.36e+00

Pos logit contributions
lights+0.024
 forth+0.018
kins+0.018
bel+0.018
ized+0.018
Neg logit contributions
 nine-0.013
-0.012
 like-0.012
 thirteen-0.011
 a-0.011
Token playing
Token ID2712
Feature activation+7.50e-01

Pos logit contributions
lights+0.188
kins+0.144
bel+0.144
uddle+0.143
ized+0.143
Neg logit contributions
 nine-0.090
-0.084
 thirteen-0.078
 a-0.078
 like-0.077
Token said
Token ID531
Feature activation+6.99e-01

Pos logit contributions
 nine+0.167
+0.163
 thirteen+0.155
ching+0.151
 like+0.149
Neg logit contributions
lights-0.212
 forth-0.156
bel-0.154
kins-0.154
ized-0.152
Token.
Token ID13
Feature activation+3.94e-01

Pos logit contributions
lights+0.105
 forth+0.085
ized+0.084
bel+0.084
kins+0.084
Neg logit contributions
 nine-0.034
-0.033
 like-0.029
 thirteen-0.029
ching-0.029
Token "
Token ID366
Feature activation+1.20e+00

Pos logit contributions
lights+0.063
 forth+0.053
kins+0.052
ized+0.052
bel+0.052
Neg logit contributions
 nine-0.016
-0.016
 a-0.013
 like-0.012
 thirteen-0.012
TokenWe
Token ID1135
Feature activation+1.12e+00

Pos logit contributions
lights+0.154
 forth+0.121
kins+0.118
uddle+0.116
ized+0.116
Neg logit contributions
 nine-0.087
-0.084
 thirteen-0.080
ching-0.077
 like-0.077
Token can
Token ID460
Feature activation-1.26e+00

Pos logit contributions
lights+0.161
 forth+0.129
kins+0.127
bel+0.127
ized+0.126
Neg logit contributions
 nine-0.063
-0.059
 thirteen-0.057
ching-0.054
upid-0.052
Token fix
Token ID4259
Feature activation+1.91e+00

Pos logit contributions
+0.096
 nine+0.093
 like+0.085
 a+0.083
 never+0.083
Neg logit contributions
lights-0.163
kins-0.125
bel-0.123
 forth-0.121
ized-0.118
Token it
Token ID340
Feature activation+6.64e-01

Pos logit contributions
lights+0.268
 forth+0.216
kins+0.211
ized+0.211
bel+0.206
Neg logit contributions
 nine-0.112
-0.104
 thirteen-0.102
ching-0.096
upid-0.094
Token together
Token ID1978
Feature activation+1.55e+00

Pos logit contributions
lights+0.088
 forth+0.070
kins+0.068
ized+0.068
bel+0.067
Neg logit contributions
 nine-0.044
 thirteen-0.041
-0.041
ching-0.038
upid-0.038
Token."
Token ID526
Feature activation-1.03e+00

Pos logit contributions
lights+0.216
 forth+0.174
kins+0.173
ized+0.169
bel+0.168
Neg logit contributions
 nine-0.087
 thirteen-0.083
-0.080
ching-0.080
upid-0.076
Token
Token ID198
Feature activation+9.70e-02

Pos logit contributions
+0.029
 nine+0.027
 a+0.022
 right+0.018
 like+0.018
Neg logit contributions
lights-0.179
kins-0.151
bel-0.151
 forth-0.149
ized-0.149
Token
Token ID198
Feature activation+4.87e-02

Pos logit contributions
lights+0.017
 forth+0.014
kins+0.014
ized+0.014
bel+0.014
Neg logit contributions
 nine-0.002
-0.002
ching-0.002
 a-0.002
upid-0.001
Token and
Token ID290
Feature activation-1.30e-01

Pos logit contributions
lights+0.054
 forth+0.043
ized+0.043
bel+0.042
kins+0.042
Neg logit contributions
 nine-0.019
upid-0.018
 thirteen-0.018
-0.016
ching-0.016
Token said
Token ID531
Feature activation+2.83e-01

Pos logit contributions
 nine+0.011
+0.010
 thirteen+0.010
ching+0.009
 like+0.009
Neg logit contributions
lights-0.016
 forth-0.012
kins-0.012
bel-0.011
ized-0.011
Token,
Token ID11
Feature activation-2.61e-01

Pos logit contributions
lights+0.035
apy+0.030
kins+0.030
bel+0.029
ized+0.028
Neg logit contributions
 nine-0.017
 Africa-0.016
upid-0.016
 thirteen-0.016
 supposed-0.016
Token "
Token ID366
Feature activation+9.08e-01

Pos logit contributions
 nine+0.021
upid+0.020
 thirteen+0.019
ching+0.019
+0.019
Neg logit contributions
lights-0.029
kins-0.023
 forth-0.023
bel-0.023
ized-0.022
TokenGood
Token ID10248
Feature activation-3.14e-01

Pos logit contributions
lights+0.089
 forth+0.066
bel+0.065
ized+0.065
kins+0.063
Neg logit contributions
 nine-0.090
-0.084
 thirteen-0.084
upid-0.083
ching-0.081
Token luck
Token ID8458
Feature activation-3.80e-02

Pos logit contributions
 nine+0.027
+0.025
 thirteen+0.025
ching+0.024
upid+0.023
Neg logit contributions
lights-0.036
 forth-0.028
kins-0.027
bel-0.026
ized-0.026
Token,
Token ID11
Feature activation-1.60e-01

Pos logit contributions
 nine+0.003
 thirteen+0.003
+0.002
upid+0.002
 Africa+0.002
Neg logit contributions
lights-0.004
kins-0.004
uddle-0.004
 forth-0.003
ized-0.003
Token little
Token ID1310
Feature activation-1.16e+00

Pos logit contributions
 nine+0.013
 thirteen+0.012
upid+0.012
ching+0.011
icks+0.011
Neg logit contributions
lights-0.017
 forth-0.014
uddle-0.013
kins-0.013
Really-0.013
Token one
Token ID530
Feature activation-7.27e-01

Pos logit contributions
 nine+0.095
+0.090
 thirteen+0.088
ching+0.084
upid+0.084
Neg logit contributions
lights-0.138
 forth-0.106
kins-0.103
ized-0.103
bel-0.102
Token.
Token ID13
Feature activation+2.97e-01

Pos logit contributions
 nine+0.045
 thirteen+0.042
upid+0.040
+0.039
ching+0.038
Neg logit contributions
lights-0.096
 forth-0.081
kins-0.076
bel-0.075
uddle-0.075
Token I
Token ID314
Feature activation-3.64e-01

Pos logit contributions
lights+0.032
Really+0.026
 forth+0.024
ths+0.023
apy+0.023
Neg logit contributions
 nine-0.023
ching-0.023
 thirteen-0.022
upid-0.021
 enough-0.021
Token important
Token ID1593
Feature activation+7.61e-02

Pos logit contributions
 nine+0.014
+0.013
 thirteen+0.013
ching+0.012
upid+0.012
Neg logit contributions
lights-0.026
 forth-0.021
kins-0.020
bel-0.020
ized-0.020
Token to
Token ID284
Feature activation-1.43e-01

Pos logit contributions
lights+0.011
 forth+0.009
bel+0.009
ized+0.009
kins+0.009
Neg logit contributions
 nine-0.004
 thirteen-0.004
-0.004
ching-0.003
upid-0.003
Token not
Token ID407
Feature activation+6.41e-02

Pos logit contributions
 thirteen+0.012
 nine+0.011
+0.010
ching+0.010
icks+0.010
Neg logit contributions
 forth-0.014
lights-0.014
ized-0.012
nam-0.012
ths-0.012
Token let
Token ID1309
Feature activation-5.58e-01

Pos logit contributions
lights+0.007
 forth+0.006
nam+0.006
bel+0.006
ized+0.006
Neg logit contributions
 thirteen-0.005
 nine-0.005
una-0.004
 Mae-0.004
upid-0.004
Token others
Token ID1854
Feature activation-8.40e-02

Pos logit contributions
 nine+0.044
 thirteen+0.041
+0.037
ching+0.035
upid+0.034
Neg logit contributions
lights-0.067
 forth-0.054
ized-0.052
bel-0.050
ths-0.050
Token tease
Token ID34691
Feature activation-4.34e-01

Pos logit contributions
 nine+0.006
 thirteen+0.006
upid+0.005
+0.005
ching+0.005
Neg logit contributions
lights-0.011
 forth-0.009
bel-0.009
ized-0.009
nam-0.008
Token you
Token ID345
Feature activation-9.43e-01

Pos logit contributions
 nine+0.027
+0.026
 like+0.024
ching+0.023
 thirteen+0.023
Neg logit contributions
lights-0.060
kins-0.047
bel-0.047
uddle-0.047
 forth-0.046
Token into
Token ID656
Feature activation+5.89e-01

Pos logit contributions
 nine+0.065
 thirteen+0.062
una+0.052
+0.052
upid+0.051
Neg logit contributions
lights-0.121
 forth-0.103
ized-0.098
nam-0.098
bel-0.098
Token doing
Token ID1804
Feature activation-7.53e-01

Pos logit contributions
lights+0.075
 forth+0.059
kins+0.058
ized+0.058
bel+0.058
Neg logit contributions
 nine-0.042
-0.040
 thirteen-0.039
ching-0.036
upid-0.036
Token something
Token ID1223
Feature activation+1.64e+00

Pos logit contributions
 nine+0.061
 thirteen+0.059
+0.056
upid+0.052
ching+0.051
Neg logit contributions
lights-0.087
 forth-0.070
ized-0.068
nam-0.065
kins-0.065
Token that
Token ID326
Feature activation-9.09e-01

Pos logit contributions
lights+0.227
 forth+0.181
ized+0.180
kins+0.178
uddle+0.177
Neg logit contributions
 nine-0.106
 thirteen-0.095
-0.090
upid-0.085
ching-0.082
Token they
Token ID484
Feature activation+5.95e-01

Pos logit contributions
lights+0.119
bel+0.100
kins+0.097
ized+0.096
uddle+0.094
Neg logit contributions
 nine-0.042
 a-0.039
-0.037
 enough-0.036
 two-0.032
Token were
Token ID547
Feature activation+3.69e-01

Pos logit contributions
lights+0.076
 forth+0.059
kins+0.058
bel+0.058
ized+0.057
Neg logit contributions
 nine-0.044
-0.042
 thirteen-0.040
ching-0.038
 like-0.038
Token done
Token ID1760
Feature activation-4.76e-01

Pos logit contributions
lights+0.051
 forth+0.042
uddle+0.040
ized+0.040
kins+0.040
Neg logit contributions
-0.021
 nine-0.021
 thirteen-0.020
ching-0.020
upid-0.019
Token,
Token ID11
Feature activation+1.58e-01

Pos logit contributions
 nine+0.022
 thirteen+0.021
+0.021
ching+0.020
upid+0.019
Neg logit contributions
lights-0.072
 forth-0.060
kins-0.058
bel-0.058
ized-0.058
Token they
Token ID484
Feature activation+6.33e-01

Pos logit contributions
lights+0.022
kins+0.017
uddle+0.017
bel+0.017
 forth+0.017
Neg logit contributions
 nine-0.010
-0.010
 a-0.009
 like-0.009
 enough-0.009
Token put
Token ID1234
Feature activation-2.16e-01

Pos logit contributions
lights+0.084
bel+0.063
kins+0.062
 forth+0.062
ized+0.062
Neg logit contributions
 nine-0.048
-0.046
 like-0.043
 a-0.041
 thirteen-0.041
Token the
Token ID262
Feature activation+1.50e-01

Pos logit contributions
 nine+0.009
 a+0.008
 like+0.007
 enough+0.007
+0.007
Neg logit contributions
lights-0.035
bel-0.029
ized-0.028
uddle-0.028
ths-0.028
Token toys
Token ID14958
Feature activation-6.12e-01

Pos logit contributions
lights+0.018
ths+0.014
ized+0.014
bel+0.014
apy+0.013
Neg logit contributions
 nine-0.012
 like-0.011
 a-0.011
 right-0.011
-0.011
Token back
Token ID736
Feature activation-1.41e-01

Pos logit contributions
 nine+0.032
+0.029
 thirteen+0.027
 like+0.026
ching+0.026
Neg logit contributions
lights-0.091
 forth-0.073
kins-0.073
bel-0.072
ized-0.072
Token in
Token ID287
Feature activation+1.14e+00

Pos logit contributions
 nine+0.009
+0.009
 thirteen+0.008
ching+0.008
 like+0.008
Neg logit contributions
lights-0.019
 forth-0.015
kins-0.015
bel-0.015
ized-0.014
Token the
Token ID262
Feature activation+1.04e-01

Pos logit contributions
lights+0.174
 forth+0.141
kins+0.141
bel+0.138
ized+0.138
Neg logit contributions
 nine-0.050
 thirteen-0.048
-0.048
ching-0.044
upid-0.042
Token of
Token ID286
Feature activation+8.65e-02

Pos logit contributions
 nine+0.017
 thirteen+0.016
+0.015
ching+0.014
upid+0.014
Neg logit contributions
lights-0.033
 forth-0.027
kins-0.025
ized-0.025
bel-0.025
Token a
Token ID257
Feature activation+1.15e-01

Pos logit contributions
lights+0.012
 sudden+0.010
kins+0.010
 forth+0.010
apy+0.010
Neg logit contributions
 thirteen-0.004
-0.004
upid-0.004
 nine-0.004
ives-0.003
Token sudden
Token ID4802
Feature activation+2.15e+00

Pos logit contributions
lights+0.010
kins+0.005
bel+0.005
uddled+0.005
ized+0.005
Neg logit contributions
-0.015
 nine-0.015
 a-0.014
ching-0.014
 two-0.014
Token,
Token ID11
Feature activation-4.29e-01

Pos logit contributions
lights+0.362
 forth+0.301
kins+0.298
bel+0.296
ized+0.296
Neg logit contributions
 nine-0.067
-0.059
 thirteen-0.054
ching-0.048
upid-0.046
Token the
Token ID262
Feature activation-3.17e-01

Pos logit contributions
 nine+0.008
 a+0.007
+0.006
 like+0.005
 thirteen+0.004
Neg logit contributions
lights-0.080
uddle-0.066
bel-0.066
 forth-0.066
kins-0.066
Token bunny
Token ID44915
Feature activation-7.09e-02

Pos logit contributions
+0.022
 nine+0.022
 a+0.021
 like+0.021
ching+0.020
Neg logit contributions
lights-0.042
bel-0.033
kins-0.032
ths-0.031
ized-0.031
Token noticed
Token ID6810
Feature activation-4.35e-01

Pos logit contributions
 nine+0.006
 thirteen+0.005
+0.005
upid+0.005
ching+0.005
Neg logit contributions
lights-0.008
 forth-0.007
ized-0.006
kins-0.006
bel-0.006
Token a
Token ID257
Feature activation+5.51e-02

Pos logit contributions
 nine+0.016
 thirteen+0.015
+0.015
upid+0.014
ching+0.012
Neg logit contributions
lights-0.070
ized-0.059
 forth-0.057
kins-0.057
apy-0.056
Token strange
Token ID6283
Feature activation-6.01e-01

Pos logit contributions
lights+0.007
 forth+0.006
kins+0.006
bel+0.006
ized+0.006
Neg logit contributions
 nine-0.004
-0.003
 thirteen-0.003
ching-0.003
 like-0.003
Token crack
Token ID8469
Feature activation+3.94e-02

Pos logit contributions
 nine+0.052
+0.049
 thirteen+0.048
upid+0.047
ching+0.045
Neg logit contributions
lights-0.068
 forth-0.052
uddle-0.051
kins-0.051
ized-0.050
Token in
Token ID287
Feature activation+7.29e-01

Pos logit contributions
lights+0.005
kins+0.004
ized+0.004
 forth+0.004
bel+0.004
Neg logit contributions
 nine-0.003
upid-0.003
-0.003
 thirteen-0.003
 know-0.003
Token,
Token ID11
Feature activation+1.17e-01

Pos logit contributions
lights+0.017
bel+0.014
 forth+0.014
kins+0.014
ized+0.014
Neg logit contributions
 nine-0.002
-0.002
 thirteen-0.002
 like-0.001
 a-0.001
Token Anna
Token ID11735
Feature activation-1.49e+00

Pos logit contributions
lights+0.014
 forth+0.011
kins+0.011
ized+0.011
uddle+0.011
Neg logit contributions
 nine-0.009
-0.008
 thirteen-0.008
ching-0.008
upid-0.008
Token and
Token ID290
Feature activation+2.71e-01

Pos logit contributions
upid+0.106
 thirteen+0.104
 nine+0.103
ching+0.091
+0.089
Neg logit contributions
lights-0.186
kins-0.155
 forth-0.152
ized-0.145
bel-0.139
Token Ben
Token ID3932
Feature activation-5.73e-01

Pos logit contributions
lights+0.038
 forth+0.033
nam+0.031
kins+0.031
ized+0.031
Neg logit contributions
 nine-0.014
-0.013
ching-0.013
 thirteen-0.013
upid-0.012
Token,"
Token ID553
Feature activation-3.60e-01

Pos logit contributions
 nine+0.048
 thirteen+0.047
upid+0.045
ching+0.041
 fourteen+0.040
Neg logit contributions
lights-0.058
 forth-0.051
kins-0.050
ized-0.048
uddle-0.045
Token the
Token ID262
Feature activation+1.99e-01

Pos logit contributions
 nine+0.017
+0.015
 a+0.014
 thirteen+0.014
 like+0.013
Neg logit contributions
lights-0.057
 forth-0.046
uddle-0.046
bel-0.046
ized-0.046
Token bird
Token ID6512
Feature activation+5.97e-01

Pos logit contributions
lights+0.026
 forth+0.020
bel+0.020
kins+0.020
ized+0.020
Neg logit contributions
 nine-0.015
-0.013
 thirteen-0.013
ching-0.012
 a-0.012
Token says
Token ID1139
Feature activation+2.40e-01

Pos logit contributions
lights+0.080
 forth+0.064
kins+0.062
bel+0.062
ized+0.062
Neg logit contributions
 nine-0.038
-0.036
 thirteen-0.035
upid-0.033
ching-0.033
Token.
Token ID13
Feature activation+6.43e-01

Pos logit contributions
lights+0.033
 forth+0.026
kins+0.026
bel+0.026
ized+0.026
Neg logit contributions
 nine-0.015
-0.014
 thirteen-0.013
upid-0.013
ching-0.013
Token "
Token ID366
Feature activation+1.22e+00

Pos logit contributions
lights+0.069
Really+0.051
kins+0.049
apy+0.048
bel+0.046
Neg logit contributions
upid-0.053
 nine-0.050
 supposed-0.049
ont-0.049
 thirteen-0.049
TokenI
Token ID40
Feature activation+6.48e-01

Pos logit contributions
lights+0.130
bel+0.102
Really+0.101
 forth+0.101
ized+0.099
Neg logit contributions
 nine-0.103
upid-0.098
 enough-0.096
 thirteen-0.096
-0.095
Token of
Token ID286
Feature activation+1.30e-01

Pos logit contributions
 nine+0.008
+0.008
 thirteen+0.008
upid+0.007
ching+0.007
Neg logit contributions
lights-0.020
 forth-0.016
bel-0.016
kins-0.016
ized-0.016
Token the
Token ID262
Feature activation-1.27e-01

Pos logit contributions
lights+0.019
 forth+0.016
kins+0.016
ized+0.016
bel+0.015
Neg logit contributions
 nine-0.006
-0.006
 thirteen-0.006
ching-0.005
upid-0.005
Token sport
Token ID6332
Feature activation-9.08e-01

Pos logit contributions
 nine+0.009
+0.009
ching+0.009
 like+0.008
 thirteen+0.008
Neg logit contributions
lights-0.016
bel-0.012
kins-0.012
 forth-0.012
ized-0.012
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
 nine+0.046
+0.042
 thirteen+0.041
ching+0.038
upid+0.037
Neg logit contributions
lights-0.135
 forth-0.110
kins-0.108
bel-0.108
ized-0.107
Token After
Token ID2293
Feature activation+7.52e-01

Pos logit contributions
 nine+0.006
 thirteen+0.006
ching+0.006
+0.005
upid+0.005
Neg logit contributions
lights-0.014
 forth-0.010
bel-0.010
ized-0.010
Really-0.010
Token that
Token ID326
Feature activation-8.72e-01

Pos logit contributions
lights+0.110
 forth+0.091
apy+0.089
ized+0.089
kins+0.088
Neg logit contributions
 nine-0.036
 thirteen-0.034
-0.033
upid-0.033
ching-0.032
Token day
Token ID1110
Feature activation+3.03e-02

Pos logit contributions
 nine+0.043
 thirteen+0.039
+0.033
upid+0.033
ching+0.033
Neg logit contributions
lights-0.132
 forth-0.114
ized-0.107
kins-0.106
ths-0.105
Token,
Token ID11
Feature activation-1.20e-02

Pos logit contributions
lights+0.004
 forth+0.004
ized+0.004
kins+0.004
apy+0.004
Neg logit contributions
 nine-0.001
 thirteen-0.001
-0.001
upid-0.001
ching-0.001
Token she
Token ID673
Feature activation+1.41e-01

Pos logit contributions
 nine+0.001
+0.001
 like+0.001
 a+0.001
 thirteen+0.001
Neg logit contributions
lights-0.002
 forth-0.001
uddle-0.001
kins-0.001
ized-0.001
Token went
Token ID1816
Feature activation+3.64e-02

Pos logit contributions
lights+0.015
 forth+0.012
ized+0.011
kins+0.011
uddle+0.011
Neg logit contributions
 nine-0.013
 thirteen-0.012
upid-0.012
ching-0.011
-0.011
Token back
Token ID736
Feature activation-3.86e-01

Pos logit contributions
lights+0.004
 forth+0.004
uddle+0.004
bel+0.003
ized+0.003
Neg logit contributions
 thirteen-0.003
 nine-0.003
-0.002
upid-0.002
ching-0.002
TokenThe
Token ID464
Feature activation+2.76e-01

Pos logit contributions
 nine+0.023
 thirteen+0.023
 enough+0.022
upid+0.022
icks+0.021
Neg logit contributions
lights-0.045
Really-0.037
bel-0.036
ths-0.036
ized-0.036
Token end
Token ID886
Feature activation-3.66e-01

Pos logit contributions
lights+0.037
kins+0.029
ized+0.029
 forth+0.029
bel+0.029
Neg logit contributions
 nine-0.019
-0.018
 thirteen-0.017
ching-0.016
 like-0.016
Token.
Token ID13
Feature activation-7.46e-02

Pos logit contributions
 nine+0.021
 thirteen+0.019
+0.019
upid+0.018
ching+0.018
Neg logit contributions
lights-0.053
 forth-0.042
bel-0.041
kins-0.041
uddle-0.040
Token<|endoftext|>
Token ID50256
Feature activation+1.60e+00

Pos logit contributions
 nine+0.004
 thirteen+0.004
ching+0.004
upid+0.003
 enough+0.003
Neg logit contributions
lights-0.010
Really-0.008
bel-0.008
apy-0.008
nam-0.008
TokenOnce
Token ID7454
Feature activation+9.49e-02

Pos logit contributions
lights+0.173
kins+0.136
uddle+0.133
 forth+0.126
bel+0.126
Neg logit contributions
 thirteen-0.133
 nine-0.130
upid-0.119
 enough-0.112
 fourteen-0.110
Token upon
Token ID2402
Feature activation-5.53e-01

Pos logit contributions
lights+0.010
 forth+0.007
kins+0.007
bel+0.007
ized+0.007
Neg logit contributions
 nine-0.009
 thirteen-0.008
-0.008
ching-0.008
 like-0.008
Token a
Token ID257
Feature activation+4.12e-02

Pos logit contributions
 thirteen+0.022
 nine+0.021
upid+0.021
ching+0.016
+0.015
Neg logit contributions
lights-0.084
bel-0.072
nam-0.071
apy-0.069
ized-0.069
Token time
Token ID640
Feature activation-1.04e+00

Pos logit contributions
lights+0.006
uddle+0.005
 forth+0.005
 sudden+0.005
ized+0.005
Neg logit contributions
 thirteen-0.002
 nine-0.002
upid-0.002
ching-0.002
-0.002
Token there
Token ID612
Feature activation+2.73e-02

Pos logit contributions
 thirteen+0.062
 nine+0.058
ching+0.054
upid+0.050
+0.047
Neg logit contributions
lights-0.144
kins-0.115
apy-0.115
uddle-0.113
 forth-0.112
Token was
Token ID373
Feature activation-2.14e-01

Pos logit contributions
lights+0.003
 forth+0.003
kins+0.002
bel+0.002
ized+0.002
Neg logit contributions
 nine-0.002
 thirteen-0.002
-0.002
ching-0.002
upid-0.002
Token a
Token ID257
Feature activation-4.84e-03

Pos logit contributions
 thirteen+0.007
upid+0.007
 nine+0.006
ching+0.006
 knows+0.005
Neg logit contributions
lights-0.034
apy-0.028
ized-0.028
 forth-0.028
 sudden-0.028
Token the
Token ID262
Feature activation-2.56e-01

Pos logit contributions
 nine+0.012
+0.011
 thirteen+0.011
ching+0.010
 like+0.010
Neg logit contributions
lights-0.037
 forth-0.030
kins-0.030
bel-0.029
ized-0.029
Token castle
Token ID16669
Feature activation+1.69e-02

Pos logit contributions
+0.027
 nine+0.027
ching+0.027
upid+0.026
 thirteen+0.026
Neg logit contributions
lights-0.022
 forth-0.016
bel-0.016
kins-0.015
uddle-0.015
Token and
Token ID290
Feature activation-1.27e-01

Pos logit contributions
lights+0.002
 forth+0.002
bel+0.002
ized+0.002
kins+0.002
Neg logit contributions
 thirteen-0.001
 nine-0.001
upid-0.001
-0.001
ching-0.001
Token took
Token ID1718
Feature activation-6.00e-01

Pos logit contributions
 nine+0.009
+0.009
 like+0.008
 thirteen+0.008
 a+0.008
Neg logit contributions
lights-0.016
kins-0.013
 forth-0.012
uddle-0.012
ized-0.012
Token the
Token ID262
Feature activation-2.32e-01

Pos logit contributions
 nine+0.027
 thirteen+0.026
+0.025
upid+0.023
ching+0.023
Neg logit contributions
lights-0.089
 forth-0.074
bel-0.072
apy-0.071
kins-0.071
Token princess
Token ID21752
Feature activation-1.02e+00

Pos logit contributions
 nine+0.019
+0.019
 thirteen+0.018
ching+0.017
upid+0.017
Neg logit contributions
lights-0.027
 forth-0.021
bel-0.020
kins-0.020
ized-0.020
Token away
Token ID1497
Feature activation-1.20e+00

Pos logit contributions
 thirteen+0.072
 nine+0.063
upid+0.058
 fourteen+0.058
+0.056
Neg logit contributions
lights-0.129
bel-0.113
 forth-0.110
kins-0.106
ized-0.100
Token.
Token ID13
Feature activation-3.24e-01

Pos logit contributions
 nine+0.079
 thirteen+0.078
+0.075
upid+0.073
ching+0.071
Neg logit contributions
lights-0.163
bel-0.126
 forth-0.123
kins-0.122
ized-0.122
Token The
Token ID383
Feature activation+2.56e-01

Pos logit contributions
 nine+0.019
+0.018
 thirteen+0.017
ching+0.017
upid+0.017
Neg logit contributions
lights-0.045
bel-0.036
 forth-0.036
ized-0.035
kins-0.035
Token king
Token ID5822
Feature activation-1.57e-01

Pos logit contributions
lights+0.033
ized+0.025
 forth+0.025
bel+0.025
uddle+0.025
Neg logit contributions
 nine-0.020
-0.018
 thirteen-0.017
 a-0.017
 like-0.017
Token and
Token ID290
Feature activation-8.04e-02

Pos logit contributions
 nine+0.012
+0.011
 thirteen+0.011
ching+0.010
upid+0.010
Neg logit contributions
lights-0.020
 forth-0.015
kins-0.015
bel-0.015
ized-0.015
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
lights+0.018
kins+0.014
 forth+0.014
ized+0.014
bel+0.014
Neg logit contributions
 nine-0.009
 thirteen-0.008
upid-0.008
-0.008
ching-0.007
Token It
Token ID632
Feature activation+7.18e-01

Pos logit contributions
lights+0.016
bel+0.012
apy+0.012
uddle+0.012
Really+0.012
Neg logit contributions
 nine-0.007
ching-0.006
 thirteen-0.006
-0.006
upid-0.006
Token was
Token ID373
Feature activation+1.62e-01

Pos logit contributions
lights+0.092
 forth+0.072
kins+0.071
bel+0.070
ized+0.070
Neg logit contributions
 nine-0.052
-0.050
 thirteen-0.047
ching-0.046
 like-0.045
Token green
Token ID4077
Feature activation-5.57e-01

Pos logit contributions
lights+0.024
 forth+0.019
kins+0.019
nam+0.019
bel+0.019
Neg logit contributions
 nine-0.007
upid-0.007
ching-0.007
-0.007
 thirteen-0.007
Token and
Token ID290
Feature activation+1.42e-02

Pos logit contributions
upid+0.033
 nine+0.029
ching+0.027
 thirteen+0.027
+0.026
Neg logit contributions
lights-0.082
 forth-0.065
ized-0.063
uddle-0.063
kins-0.062
Token yellow
Token ID7872
Feature activation-6.23e-01

Pos logit contributions
lights+0.002
uddle+0.001
ized+0.001
bel+0.001
 forth+0.001
Neg logit contributions
-0.001
 nine-0.001
 a-0.001
 like-0.001
 thirteen-0.001
Token and
Token ID290
Feature activation+2.14e-02

Pos logit contributions
upid+0.034
 nine+0.034
ching+0.031
+0.030
 thirteen+0.030
Neg logit contributions
lights-0.089
 forth-0.070
uddle-0.068
kins-0.067
ized-0.067
Token had
Token ID550
Feature activation+4.72e-01

Pos logit contributions
lights+0.003
ized+0.002
uddle+0.002
 forth+0.002
bel+0.002
Neg logit contributions
-0.001
 nine-0.001
 thirteen-0.001
 like-0.001
 a-0.001
Token a
Token ID257
Feature activation+3.54e-01

Pos logit contributions
lights+0.063
bel+0.048
nam+0.046
apy+0.046
 brightly+0.046
Neg logit contributions
upid-0.026
-0.025
 nine-0.025
ching-0.024
 thirteen-0.022
Token lightning
Token ID14357
Feature activation+5.37e-01

Pos logit contributions
lights+0.042
 forth+0.031
uddle+0.031
kins+0.031
bel+0.031
Neg logit contributions
 nine-0.028
-0.026
 thirteen-0.026
upid-0.025
ching-0.024
Token bolt
Token ID18100
Feature activation+1.13e+00

Pos logit contributions
lights+0.070
 forth+0.054
bel+0.051
ized+0.051
kins+0.049
Neg logit contributions
 nine-0.040
upid-0.036
 thirteen-0.034
-0.034
 knows-0.032
Token a
Token ID257
Feature activation-5.35e-02

Pos logit contributions
 thirteen+0.007
upid+0.007
 nine+0.006
ching+0.006
 knows+0.005
Neg logit contributions
lights-0.029
apy-0.025
ized-0.024
nam-0.024
 forth-0.024
Token poor
Token ID3595
Feature activation-1.64e+00

Pos logit contributions
 nine+0.003
+0.003
 like+0.003
 a+0.003
ching+0.002
Neg logit contributions
lights-0.008
 forth-0.006
ized-0.006
kins-0.006
bel-0.006
Token girl
Token ID2576
Feature activation-5.10e-01

Pos logit contributions
 nine+0.117
+0.110
 thirteen+0.104
ching+0.102
 like+0.102
Neg logit contributions
lights-0.211
 forth-0.165
bel-0.162
kins-0.161
ized-0.161
Token.
Token ID13
Feature activation-8.47e-01

Pos logit contributions
 nine+0.039
+0.037
 thirteen+0.036
ching+0.034
upid+0.034
Neg logit contributions
lights-0.063
 forth-0.049
bel-0.048
kins-0.048
ized-0.048
Token She
Token ID1375
Feature activation-1.06e+00

Pos logit contributions
 nine+0.035
+0.033
 thirteen+0.029
 like+0.028
ching+0.027
Neg logit contributions
lights-0.135
 forth-0.112
kins-0.110
ized-0.110
bel-0.110
Token wanted
Token ID2227
Feature activation-6.79e-01

Pos logit contributions
 nine+0.074
+0.072
 thirteen+0.067
 like+0.065
ching+0.065
Neg logit contributions
lights-0.140
 forth-0.109
kins-0.107
bel-0.106
ized-0.106
Token very
Token ID845
Feature activation+9.23e-01

Pos logit contributions
 nine+0.031
 thirteen+0.030
upid+0.029
+0.029
ching+0.028
Neg logit contributions
lights-0.101
nam-0.083
 forth-0.083
bel-0.082
ized-0.081
Token much
Token ID881
Feature activation-4.97e-01

Pos logit contributions
lights+0.145
 forth+0.119
kins+0.118
bel+0.116
ized+0.116
Neg logit contributions
 nine-0.041
-0.037
 thirteen-0.033
ching-0.032
 like-0.031
Token to
Token ID284
Feature activation-3.89e-01

Pos logit contributions
 nine+0.035
 thirteen+0.033
+0.033
upid+0.031
ching+0.031
Neg logit contributions
lights-0.065
 forth-0.050
kins-0.049
uddle-0.049
ized-0.049
Token have
Token ID423
Feature activation+4.71e-02

Pos logit contributions
 nine+0.029
 thirteen+0.027
+0.026
ching+0.025
upid+0.024
Neg logit contributions
lights-0.048
 forth-0.038
bel-0.037
kins-0.037
ized-0.037
Token a
Token ID257
Feature activation+4.14e-02

Pos logit contributions
lights+0.008
 forth+0.006
ized+0.006
kins+0.006
nam+0.006
Neg logit contributions
 nine-0.002
 thirteen-0.002
-0.001
upid-0.001
ching-0.001
Token parents
Token ID3397
Feature activation-3.61e-01

Pos logit contributions
 nine+0.001
+0.001
 a+0.001
 like+0.001
 thirteen+0.001
Neg logit contributions
lights-0.002
ized-0.001
bel-0.001
 forth-0.001
kins-0.001
Token said
Token ID531
Feature activation+2.53e-01

Pos logit contributions
 nine+0.031
 thirteen+0.030
+0.028
upid+0.028
ching+0.028
Neg logit contributions
lights-0.040
 forth-0.031
kins-0.030
ized-0.030
bel-0.030
Token no
Token ID645
Feature activation-4.66e-02

Pos logit contributions
lights+0.031
kins+0.024
apy+0.024
 forth+0.023
ized+0.023
Neg logit contributions
 nine-0.019
upid-0.017
 thirteen-0.017
ching-0.016
-0.016
Token.
Token ID13
Feature activation-5.33e-01

Pos logit contributions
 nine+0.003
 thirteen+0.003
ching+0.003
+0.003
upid+0.003
Neg logit contributions
lights-0.006
 forth-0.005
ized-0.005
bel-0.005
uddle-0.005
Token Id
Token ID5121
Feature activation-4.22e-01

Pos logit contributions
 nine+0.029
+0.027
 thirteen+0.026
ching+0.025
upid+0.024
Neg logit contributions
lights-0.077
 forth-0.062
kins-0.061
bel-0.061
ized-0.061
Tokena
Token ID64
Feature activation-3.02e+00

Pos logit contributions
 nine+0.016
+0.015
 thirteen+0.013
ching+0.013
upid+0.012
Neg logit contributions
lights-0.068
 forth-0.056
kins-0.055
bel-0.055
ized-0.055
Token felt
Token ID2936
Feature activation+2.85e-01

Pos logit contributions
 nine+0.224
+0.221
 thirteen+0.203
ching+0.198
 like+0.195
Neg logit contributions
lights-0.383
 forth-0.293
bel-0.288
kins-0.288
ized-0.284
Token very
Token ID845
Feature activation+9.13e-01

Pos logit contributions
lights+0.029
ized+0.022
 forth+0.022
nam+0.022
apy+0.021
Neg logit contributions
 nine-0.026
 thirteen-0.024
upid-0.023
ont-0.022
one-0.022
Token sad
Token ID6507
Feature activation-2.23e-01

Pos logit contributions
lights+0.104
 forth+0.079
kins+0.078
ized+0.078
bel+0.077
Neg logit contributions
 nine-0.078
-0.073
 thirteen-0.072
ching-0.068
upid-0.068
Token.
Token ID13
Feature activation-4.88e-01

Pos logit contributions
 nine+0.015
 thirteen+0.014
+0.013
upid+0.013
ching+0.013
Neg logit contributions
lights-0.031
 forth-0.024
ized-0.023
kins-0.023
bel-0.023
Token So
Token ID1406
Feature activation+5.25e-01

Pos logit contributions
 nine+0.026
 thirteen+0.023
+0.023
ching+0.022
upid+0.021
Neg logit contributions
lights-0.072
 forth-0.057
bel-0.057
ized-0.057
uddle-0.056
TokenOnce
Token ID7454
Feature activation+2.80e-01

Pos logit contributions
lights+0.199
kins+0.159
uddle+0.154
 forth+0.150
bel+0.149
Neg logit contributions
 nine-0.115
 thirteen-0.115
upid-0.102
 enough-0.093
 fourteen-0.091
Token there
Token ID612
Feature activation+6.53e-02

Pos logit contributions
lights+0.032
 forth+0.023
kins+0.023
bel+0.023
ized+0.023
Neg logit contributions
 nine-0.024
 thirteen-0.023
-0.023
ching-0.022
 like-0.021
Token was
Token ID373
Feature activation-1.57e-01

Pos logit contributions
lights+0.007
 forth+0.006
kins+0.006
ized+0.005
bel+0.005
Neg logit contributions
 nine-0.006
 thirteen-0.005
ching-0.005
-0.005
upid-0.005
Token a
Token ID257
Feature activation-1.54e-02

Pos logit contributions
 thirteen+0.006
upid+0.006
 nine+0.006
ching+0.005
 knows+0.005
Neg logit contributions
lights-0.024
apy-0.020
ized-0.020
 sudden-0.019
nam-0.019
Token fle
Token ID5104
Feature activation+3.45e-01

Pos logit contributions
 nine+0.001
+0.001
 like+0.001
ching+0.001
 thirteen+0.001
Neg logit contributions
lights-0.002
 forth-0.002
ized-0.002
kins-0.002
bel-0.002
Tokena
Token ID64
Feature activation-3.08e+00

Pos logit contributions
lights+0.059
kins+0.049
 forth+0.049
bel+0.049
ized+0.049
Neg logit contributions
 nine-0.010
-0.009
 thirteen-0.008
ching-0.006
upid-0.006
Token who
Token ID508
Feature activation-4.24e-03

Pos logit contributions
 thirteen+0.233
 nine+0.225
upid+0.214
+0.203
ching+0.197
Neg logit contributions
lights-0.371
kins-0.299
 forth-0.296
ized-0.295
bel-0.294
Token wanted
Token ID2227
Feature activation-7.48e-01

Pos logit contributions
 nine+0.000
 thirteen+0.000
upid+0.000
+0.000
ching+0.000
Neg logit contributions
lights-0.000
bel-0.000
 forth-0.000
kins-0.000
ized-0.000
Token to
Token ID284
Feature activation-3.92e-01

Pos logit contributions
 nine+0.047
upid+0.047
 thirteen+0.047
ching+0.042
+0.040
Neg logit contributions
lights-0.092
nam-0.077
bel-0.075
 forth-0.073
apy-0.073
Token quit
Token ID11238
Feature activation+3.59e-01

Pos logit contributions
 nine+0.030
 thirteen+0.028
+0.026
ching+0.026
upid+0.025
Neg logit contributions
lights-0.048
 forth-0.038
bel-0.037
kins-0.037
ized-0.036
Token.
Token ID13
Feature activation-6.98e-01

Pos logit contributions
lights+0.047
 forth+0.038
kins+0.037
ized+0.037
bel+0.036
Neg logit contributions
 nine-0.024
-0.023
 thirteen-0.023
upid-0.021
ching-0.021
Token and
Token ID290
Feature activation+2.49e-01

Pos logit contributions
lights+0.106
 forth+0.096
ized+0.090
kins+0.090
nam+0.084
Neg logit contributions
 thirteen-0.059
 nine-0.058
upid-0.052
icks-0.050
ching-0.049
Token not
Token ID407
Feature activation+2.06e-01

Pos logit contributions
lights+0.035
 forth+0.028
bel+0.028
kins+0.028
ized+0.027
Neg logit contributions
 nine-0.015
 thirteen-0.014
-0.013
ching-0.013
upid-0.012
Token be
Token ID307
Feature activation+1.56e+00

Pos logit contributions
lights+0.024
 forth+0.021
bel+0.019
nam+0.019
ized+0.019
Neg logit contributions
 nine-0.015
 thirteen-0.014
-0.013
upid-0.013
ching-0.013
Token too
Token ID1165
Feature activation+2.32e+00

Pos logit contributions
lights+0.160
 forth+0.138
nam+0.134
bel+0.128
ized+0.128
Neg logit contributions
-0.127
 nine-0.127
upid-0.125
 thirteen-0.124
 fourteen-0.111
Token nos
Token ID43630
Feature activation+7.45e-01

Pos logit contributions
lights+0.217
ized+0.174
bel+0.174
nam+0.171
 forth+0.167
Neg logit contributions
 nine-0.217
 thirteen-0.213
-0.206
upid-0.195
icks-0.188
Tokeny
Token ID88
Feature activation-2.63e+00

Pos logit contributions
lights+0.094
 forth+0.074
ized+0.072
bel+0.072
uddle+0.068
Neg logit contributions
 nine-0.055
-0.052
 thirteen-0.052
upid-0.046
 a-0.045
Token.
Token ID13
Feature activation+3.69e-01

Pos logit contributions
 nine+0.203
 thirteen+0.194
upid+0.178
+0.174
ching+0.163
Neg logit contributions
lights-0.305
 forth-0.250
kins-0.237
bel-0.235
ized-0.233
Token And
Token ID843
Feature activation+2.26e+00

Pos logit contributions
lights+0.047
uddle+0.036
apy+0.035
Really+0.035
kins+0.035
Neg logit contributions
 nine-0.026
 thirteen-0.025
ching-0.023
-0.023
upid-0.023
Token they
Token ID484
Feature activation+7.33e-01

Pos logit contributions
lights+0.267
 forth+0.210
bel+0.202
kins+0.201
ized+0.199
Neg logit contributions
 nine-0.182
 thirteen-0.171
upid-0.166
ching-0.164
-0.164
Token all
Token ID477
Feature activation+7.46e-01

Pos logit contributions
lights+0.091
 forth+0.073
kins+0.070
ized+0.070
bel+0.069
Neg logit contributions
 nine-0.053
 thirteen-0.050
-0.049
ching-0.048
upid-0.047
Token lived
Token ID5615
Feature activation+1.61e+00

Pos logit contributions
lights+0.067
 forth+0.052
ized+0.046
kins+0.046
apy+0.045
Neg logit contributions
 nine-0.077
 thirteen-0.074
ching-0.071
-0.069
upid-0.069
Token it
Token ID340
Feature activation+4.96e-01

Pos logit contributions
ching+0.036
ives+0.035
upid+0.034
+0.034
 thirteen+0.033
Neg logit contributions
lights-0.043
ized-0.036
 forth-0.032
nam-0.032
ised-0.030
Token and
Token ID290
Feature activation+6.04e-02

Pos logit contributions
lights+0.072
 forth+0.059
ized+0.058
uddle+0.057
kins+0.057
Neg logit contributions
 nine-0.026
upid-0.025
 thirteen-0.024
ching-0.023
-0.021
Token sees
Token ID7224
Feature activation-1.03e+00

Pos logit contributions
lights+0.008
 forth+0.007
bel+0.006
kins+0.006
ized+0.006
Neg logit contributions
 nine-0.004
-0.003
 thirteen-0.003
ching-0.003
upid-0.003
Token the
Token ID262
Feature activation+4.53e-02

Pos logit contributions
+0.041
 nine+0.040
ching+0.037
 thirteen+0.037
upid+0.037
Neg logit contributions
lights-0.160
nam-0.132
ized-0.132
kins-0.129
bel-0.128
Token smile
Token ID8212
Feature activation-4.14e-01

Pos logit contributions
lights+0.006
 forth+0.004
bel+0.004
kins+0.004
ized+0.004
Neg logit contributions
 nine-0.004
-0.003
 thirteen-0.003
ching-0.003
 like-0.003
Tokeny
Token ID88
Feature activation-2.70e+00

Pos logit contributions
 nine+0.027
 thirteen+0.024
upid+0.024
+0.023
ching+0.022
Neg logit contributions
lights-0.055
 forth-0.044
kins-0.044
bel-0.043
ized-0.042
Token face
Token ID1986
Feature activation+1.46e+00

Pos logit contributions
 nine+0.224
+0.215
 thirteen+0.208
ching+0.200
 like+0.198
Neg logit contributions
lights-0.315
 forth-0.238
bel-0.233
ized-0.233
kins-0.231
Token and
Token ID290
Feature activation+1.77e-01

Pos logit contributions
lights+0.193
kins+0.149
 forth+0.149
ized+0.147
bel+0.144
Neg logit contributions
 nine-0.099
upid-0.090
 thirteen-0.087
-0.084
ching-0.082
Token the
Token ID262
Feature activation+4.42e-02

Pos logit contributions
lights+0.023
 forth+0.018
bel+0.018
kins+0.018
ized+0.017
Neg logit contributions
 nine-0.012
-0.011
 thirteen-0.011
ching-0.011
upid-0.011
Token heart
Token ID2612
Feature activation+2.12e-01

Pos logit contributions
lights+0.005
 forth+0.004
kins+0.004
bel+0.004
ized+0.004
Neg logit contributions
 nine-0.004
-0.003
 thirteen-0.003
ching-0.003
 like-0.003
Token.
Token ID13
Feature activation+4.86e-01

Pos logit contributions
lights+0.028
 forth+0.023
kins+0.022
bel+0.022
ized+0.022
Neg logit contributions
 nine-0.014
-0.013
 thirteen-0.013
ching-0.012
 like-0.012
TokenHe
Token ID1544
Feature activation-9.39e-02

Pos logit contributions
 nine+0.059
 thirteen+0.056
+0.055
upid+0.053
ching+0.052
Neg logit contributions
lights-0.088
 forth-0.068
bel-0.067
ized-0.066
kins-0.066
Token saw
Token ID2497
Feature activation-4.72e-01

Pos logit contributions
+0.006
 nine+0.006
 a+0.005
 like+0.005
 never+0.005
Neg logit contributions
lights-0.014
kins-0.011
bel-0.010
nam-0.010
ized-0.010
Token a
Token ID257
Feature activation+3.29e-02

Pos logit contributions
 thirteen+0.019
+0.019
 nine+0.018
upid+0.018
ching+0.017
Neg logit contributions
lights-0.072
nam-0.060
ized-0.059
apy-0.059
 forth-0.059
Token large
Token ID1588
Feature activation-1.37e-01

Pos logit contributions
lights+0.004
 forth+0.003
kins+0.003
ized+0.003
bel+0.003
Neg logit contributions
 nine-0.002
-0.002
 thirteen-0.002
ching-0.002
 like-0.002
Token tr
Token ID491
Feature activation-4.05e-01

Pos logit contributions
 nine+0.010
+0.010
 thirteen+0.010
ching+0.009
upid+0.009
Neg logit contributions
lights-0.017
 forth-0.013
kins-0.013
ized-0.013
bel-0.013
Tokenamp
Token ID696
Feature activation-2.84e+00

Pos logit contributions
 nine+0.030
+0.029
 thirteen+0.027
ching+0.026
upid+0.026
Neg logit contributions
lights-0.051
 forth-0.039
bel-0.039
kins-0.039
ized-0.038
Tokenoline
Token ID14453
Feature activation-2.13e+00

Pos logit contributions
 nine+0.189
+0.182
 thirteen+0.174
ching+0.166
upid+0.164
Neg logit contributions
lights-0.383
 forth-0.303
ized-0.298
kins-0.295
bel-0.285
Token.
Token ID13
Feature activation-3.97e-01

Pos logit contributions
 nine+0.126
+0.116
 thirteen+0.114
upid+0.113
ching+0.108
Neg logit contributions
lights-0.296
 forth-0.242
ized-0.234
kins-0.233
bel-0.230
Token It
Token ID632
Feature activation+4.19e-01

Pos logit contributions
 nine+0.019
+0.019
 thirteen+0.017
 like+0.017
 a+0.017
Neg logit contributions
lights-0.060
 forth-0.050
kins-0.050
ized-0.049
bel-0.049
Token was
Token ID373
Feature activation-1.12e-01

Pos logit contributions
lights+0.056
kins+0.044
 forth+0.044
bel+0.044
ized+0.043
Neg logit contributions
-0.028
 nine-0.028
 thirteen-0.025
ching-0.025
 like-0.025
Token round
Token ID2835
Feature activation-7.07e-03

Pos logit contributions
upid+0.006
 nine+0.006
ives+0.006
+0.006
ching+0.006
Neg logit contributions
lights-0.015
 forth-0.012
nam-0.012
apy-0.012
bel-0.011