TOP ACTIVATIONS
MAX = 0.250

a . " Uh , what are you ?"
on her costume . " Uh oh , Mom my .
's daddy said , " Uh - oh , there 's
scared . " Uh - oh !" Tom said
open freezer and said " Uh oh !" He quickly shut
what to say . " Uh , ok !" it said
. Emma said , " Uh - oh , now what
â Uh - oh , â
to Tim my , " Uh oh , the roof has
worried . " Uh - oh , this fire
in the distance . " Uh oh , that cloud looks
. " Uh oh , we have a
angry . " Uh oh . We 're in
in their tracks . " Uh , nothing ," they said
The fox said , " Uh oh , I shouldn 't
her . " Uh - oh , Lily ,"
everywhere . " Uh - oh !" Tim said
Lily . " Uh oh . We 're in
scared , she said " Uh - oh ", and ran
in and said , " Uh oh , you boys made

MIN ACTIVATIONS
MIN = -0.170

" news " on it . Tim was very curious about
" I love this shirt . It is so nice !"
and wide for his amazing feats ! He could jump higher
- ch oo " sound . The train liked to go
, slide and see - saw . But their favorite thing
ck " all day long . One day ,
Once there was a bunny . The bunny had two big
were applauded for their brave feats . <|endoftext|> Once upon a
" Be careful , Tim . This box may have a
No , it is fragile . You might break it ."
is a vest , Tim . You wear it on your
seat on the see - saw . She ran to it
" Be careful , Sara . The onion can make your
, slide and see - saw . But when
down on the see - saw . After
Max , I am cold . Let 's sit closer to
" My block is better . It is red like fire
t about the see - saw and how much fun it
Leo continued to perform amazing feats for his friends in the
to make a delicious cake . I can 't wait to

INTERVAL 0.145 - 0.250
CONTAINS 2.393%

their tasty home . Then one day , some
using the tools . Steve worked on the black
had ever seen . He began to gra
replied his mom . The little owl was so
kind to each other ." The two friends were

INTERVAL 0.040 - 0.145
CONTAINS 25.577%

liked to slide , swing , and run . One day
He planted the flowers and waited for them to grow .
would sleep all day and never play with the other cats
it is too hard . " No , Sara
my said . His friends were amazed . " Wow ,

INTERVAL -0.065 - 0.040
CONTAINS 58.819%

see the big , gray animal with the point y horn
got a bucket and filled it with pe b bles .
there was a battery . It had a very important job
She opened the door and saw stairs . She climbed the
Tom che wed his gum too . He smiled

INTERVAL -0.170 - -0.065
CONTAINS 13.211%

her mom what was inside . Her mom said it was
. They loved the snow . They put on their coats
he will come back and play with them another day .
a little girl named Daisy . Daisy wanted to learn how
. He wonders where they went . He hopes they are
Tokena
Token ID64
Feature activation+6.55e-02

Pos logit contributions
ths+0.078
agg+0.076
eking+0.074
aman+0.070
Kevin+0.066
Neg logit contributions
.-0.108
."-0.103
ashes-0.098
 He-0.096
 rider-0.094
Token.
Token ID13
Feature activation-1.45e-01

Pos logit contributions
agg+0.190
eking+0.189
ths+0.188
ering+0.179
Jess+0.178
Neg logit contributions
ashes-0.023
 rider-0.016
."-0.014
 Let-0.012
 He-0.011
Token
Token ID220
Feature activation+1.82e-01

Pos logit contributions
.+0.174
."+0.161
ashes+0.156
 rider+0.143
 He+0.138
Neg logit contributions
ths-0.314
agg-0.307
eking-0.297
aman-0.294
Kevin-0.284
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
ths+0.355
agg+0.352
eking+0.338
aman+0.335
Kevin+0.322
Neg logit contributions
.-0.244
."-0.229
ashes-0.227
 rider-0.216
 He-0.206
Token"
Token ID1
Feature activation+2.86e-02

Pos logit contributions
ths+0.324
agg+0.313
eking+0.311
aman+0.302
prisingly+0.286
Neg logit contributions
.-0.188
."-0.172
 He-0.156
ashes-0.153
 They-0.146
TokenUh
Token ID34653
Feature activation+2.50e-01

Pos logit contributions
ths+0.061
eking+0.060
agg+0.059
aman+0.057
ering+0.055
Neg logit contributions
.-0.038
."-0.035
 He-0.034
ashes-0.032
 Let-0.032
Token,
Token ID11
Feature activation+8.75e-02

Pos logit contributions
ths+0.417
agg+0.396
aman+0.391
eking+0.377
Kevin+0.364
Neg logit contributions
.-0.475
."-0.446
 He-0.389
 rider-0.384
 Let-0.382
Token what
Token ID644
Feature activation-2.91e-02

Pos logit contributions
ths+0.175
agg+0.170
eking+0.166
aman+0.162
Kevin+0.155
Neg logit contributions
.-0.124
."-0.115
ashes-0.110
 He-0.105
 rider-0.101
Token are
Token ID389
Feature activation+1.02e-01

Pos logit contributions
ashes+0.034
.+0.034
."+0.032
 towards+0.031
 He+0.030
Neg logit contributions
agg-0.059
ths-0.058
eking-0.057
Kevin-0.055
Jess-0.054
Token you
Token ID345
Feature activation+8.10e-03

Pos logit contributions
ths+0.160
agg+0.155
eking+0.149
aman+0.147
Kevin+0.138
Neg logit contributions
.-0.194
."-0.184
ashes-0.169
 He-0.168
 They-0.163
Token?"
Token ID1701
Feature activation-2.05e-03

Pos logit contributions
ths+0.015
agg+0.014
Jess+0.013
aman+0.013
prisingly+0.013
Neg logit contributions
.-0.016
."-0.015
 like-0.013
 name-0.013
 play-0.013
Token on
Token ID319
Feature activation-5.57e-02

Pos logit contributions
 rider+0.000
."+0.000
ashes+0.000
 He+0.000
 Let+0.000
Neg logit contributions
ths-0.001
eking-0.001
agg-0.001
aman-0.001
ering-0.001
Token her
Token ID607
Feature activation-3.53e-02

Pos logit contributions
.+0.080
."+0.074
ashes+0.067
 He+0.067
 They+0.064
Neg logit contributions
ths-0.114
agg-0.110
eking-0.109
aman-0.105
Kevin-0.100
Token costume
Token ID16569
Feature activation-5.03e-02

Pos logit contributions
ashes+0.048
 He+0.045
 They+0.045
 Let+0.045
 rider+0.044
Neg logit contributions
agg-0.065
ths-0.065
eking-0.065
aman-0.059
Kevin-0.058
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
ashes+0.023
."+0.020
.+0.020
 Let+0.018
 rider+0.018
Neg logit contributions
ths-0.138
eking-0.136
aman-0.135
agg-0.135
ering-0.127
Token "
Token ID366
Feature activation+6.55e-02

Pos logit contributions
.+0.137
."+0.122
 He+0.109
ashes+0.105
 They+0.101
Neg logit contributions
ths-0.346
agg-0.337
eking-0.336
aman-0.323
prisingly-0.315
TokenUh
Token ID34653
Feature activation+2.49e-01

Pos logit contributions
ths+0.130
eking+0.128
agg+0.128
aman+0.121
ering+0.120
Neg logit contributions
.-0.092
."-0.087
ashes-0.082
 He-0.080
 Let-0.080
Token oh
Token ID11752
Feature activation+9.20e-02

Pos logit contributions
ths+0.460
aman+0.448
agg+0.446
eking+0.422
Kevin+0.421
Neg logit contributions
.-0.426
."-0.395
ashes-0.324
 Let-0.323
 play-0.322
Token,
Token ID11
Feature activation+9.24e-02

Pos logit contributions
ths+0.169
agg+0.164
eking+0.160
aman+0.155
prisingly+0.148
Neg logit contributions
.-0.144
."-0.135
ashes-0.131
 He-0.127
 They-0.122
Token Mom
Token ID11254
Feature activation+4.34e-02

Pos logit contributions
ths+0.191
agg+0.185
eking+0.181
aman+0.177
Kevin+0.169
Neg logit contributions
.-0.128
."-0.118
ashes-0.110
 He-0.108
 rider-0.102
Tokenmy
Token ID1820
Feature activation+2.49e-02

Pos logit contributions
ths+0.075
eking+0.071
aman+0.068
agg+0.066
ering+0.063
Neg logit contributions
ashes-0.073
five-0.067
powers-0.067
 He-0.065
 They-0.064
Token.
Token ID13
Feature activation-1.53e-01

Pos logit contributions
ths+0.053
eking+0.052
aman+0.049
ering+0.049
agg+0.048
Neg logit contributions
ashes-0.031
five-0.026
 They-0.025
 He-0.025
powers-0.025
Token's
Token ID338
Feature activation+2.45e-02

Pos logit contributions
ths+0.052
agg+0.051
eking+0.050
aman+0.049
prisingly+0.047
Neg logit contributions
.-0.029
."-0.026
 He-0.023
ashes-0.023
 They-0.022
Token daddy
Token ID35822
Feature activation+2.34e-02

Pos logit contributions
ths+0.039
agg+0.037
eking+0.036
aman+0.034
Kevin+0.034
Neg logit contributions
.-0.043
."-0.041
ashes-0.041
 He-0.039
 Let-0.038
Token said
Token ID531
Feature activation+7.58e-02

Pos logit contributions
ths+0.044
agg+0.044
eking+0.042
aman+0.041
prisingly+0.039
Neg logit contributions
.-0.038
."-0.034
 He-0.032
ashes-0.030
 They-0.030
Token,
Token ID11
Feature activation+8.59e-02

Pos logit contributions
ths+0.180
agg+0.175
eking+0.174
aman+0.171
prisingly+0.164
Neg logit contributions
.-0.093
."-0.079
 He-0.072
 They-0.065
 towards-0.064
Token "
Token ID366
Feature activation+6.54e-02

Pos logit contributions
ths+0.186
agg+0.180
eking+0.177
aman+0.173
Kevin+0.166
Neg logit contributions
.-0.108
."-0.100
ashes-0.094
 He-0.088
 rider-0.086
TokenUh
Token ID34653
Feature activation+2.49e-01

Pos logit contributions
agg+0.132
eking+0.129
ths+0.128
aman+0.118
Kevin+0.114
Neg logit contributions
.-0.096
."-0.089
 He-0.089
 Let-0.087
 They-0.084
Token-
Token ID12
Feature activation+2.43e-02

Pos logit contributions
ths+0.458
agg+0.452
aman+0.438
eking+0.427
Kevin+0.413
Neg logit contributions
.-0.420
."-0.382
 He-0.330
ashes-0.326
 rider-0.325
Tokenoh
Token ID1219
Feature activation+1.66e-01

Pos logit contributions
ths+0.031
agg+0.030
eking+0.029
aman+0.028
Jess+0.025
Neg logit contributions
.-0.053
."-0.050
ashes-0.048
 He-0.047
 Let-0.046
Token,
Token ID11
Feature activation+8.46e-02

Pos logit contributions
ths+0.306
eking+0.298
agg+0.288
aman+0.285
prisingly+0.271
Neg logit contributions
ashes-0.231
.-0.220
."-0.216
 He-0.212
 They-0.211
Token there
Token ID612
Feature activation-1.74e-02

Pos logit contributions
ths+0.181
agg+0.177
eking+0.174
aman+0.169
Kevin+0.163
Neg logit contributions
.-0.112
."-0.103
 He-0.093
ashes-0.093
 They-0.087
Token's
Token ID338
Feature activation+2.09e-02

Pos logit contributions
ashes+0.020
.+0.019
five+0.019
 rider+0.018
 He+0.018
Neg logit contributions
ths-0.036
aman-0.035
agg-0.034
eking-0.034
ering-0.032
Token scared
Token ID12008
Feature activation-1.22e-02

Pos logit contributions
.+0.000
."+0.000
 rider+0.000
ashes+0.000
 Let+0.000
Neg logit contributions
ths-0.000
eking-0.000
agg-0.000
 impressed-0.000
 unfortunately-0.000
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
powers+0.009
ashes+0.009
 rider+0.008
 pedal+0.008
five+0.008
Neg logit contributions
ths-0.029
eking-0.028
 unfortunately-0.027
ering-0.027
Jane-0.027
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
.+0.131
."+0.117
ashes+0.107
 rider+0.097
 He+0.096
Neg logit contributions
ths-0.348
agg-0.341
eking-0.332
aman-0.328
Kevin-0.318
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
ths+0.369
eking+0.355
agg+0.345
aman+0.341
prisingly+0.322
Neg logit contributions
.-0.162
."-0.140
 He-0.125
 They-0.121
 Let-0.103
Token"
Token ID1
Feature activation+2.27e-02

Pos logit contributions
ths+0.249
agg+0.240
eking+0.234
aman+0.227
Kevin+0.216
Neg logit contributions
.-0.244
."-0.230
ashes-0.218
 He-0.212
 rider-0.206
TokenUh
Token ID34653
Feature activation+2.48e-01

Pos logit contributions
eking+0.045
agg+0.044
ths+0.043
ering+0.041
aman+0.041
Neg logit contributions
.-0.034
."-0.032
 Let-0.030
 They-0.030
ashes-0.029
Token-
Token ID12
Feature activation+2.56e-02

Pos logit contributions
ths+0.550
agg+0.541
aman+0.529
eking+0.518
Kevin+0.508
Neg logit contributions
.-0.334
."-0.301
ashes-0.247
 He-0.246
 Let-0.238
Tokenoh
Token ID1219
Feature activation+1.67e-01

Pos logit contributions
ths+0.027
agg+0.026
eking+0.025
aman+0.023
Kevin+0.021
Neg logit contributions
.-0.061
."-0.058
ashes-0.056
 He-0.055
 rider-0.054
Token!"
Token ID2474
Feature activation-3.13e-02

Pos logit contributions
ths+0.358
eking+0.349
agg+0.346
aman+0.334
prisingly+0.321
Neg logit contributions
.-0.184
ashes-0.181
 He-0.177
."-0.172
 They-0.169
Token Tom
Token ID4186
Feature activation+3.31e-02

Pos logit contributions
.+0.036
."+0.032
 He+0.029
ashes+0.028
 They+0.027
Neg logit contributions
ths-0.075
agg-0.072
eking-0.072
aman-0.070
prisingly-0.067
Token said
Token ID531
Feature activation+6.54e-02

Pos logit contributions
ths+0.069
agg+0.067
eking+0.067
aman+0.064
Kevin+0.061
Neg logit contributions
.-0.039
."-0.038
ashes-0.037
 rider-0.034
five-0.033
Token open
Token ID1280
Feature activation-5.60e-02

Pos logit contributions
.+0.053
."+0.049
ashes+0.045
 He+0.045
 rider+0.043
Neg logit contributions
ths-0.068
agg-0.066
eking-0.065
aman-0.063
prisingly-0.060
Token freezer
Token ID30967
Feature activation+3.99e-02

Pos logit contributions
ashes+0.089
."+0.083
.+0.080
powers+0.079
 Let+0.079
Neg logit contributions
aman-0.095
ths-0.094
agg-0.092
eking-0.083
Jess-0.079
Token and
Token ID290
Feature activation+5.20e-02

Pos logit contributions
ths+0.098
eking+0.093
agg+0.092
aman+0.092
ering+0.087
Neg logit contributions
ashes-0.035
.-0.035
."-0.035
powers-0.029
 rider-0.029
Token said
Token ID531
Feature activation+7.76e-02

Pos logit contributions
ths+0.100
agg+0.097
eking+0.095
aman+0.092
Kevin+0.088
Neg logit contributions
.-0.079
."-0.074
ashes-0.070
 He-0.068
 rider-0.065
Token "
Token ID366
Feature activation+6.33e-02

Pos logit contributions
ths+0.170
agg+0.164
eking+0.164
aman+0.160
prisingly+0.152
Neg logit contributions
.-0.102
."-0.091
 He-0.084
ashes-0.081
 They-0.078
TokenUh
Token ID34653
Feature activation+2.48e-01

Pos logit contributions
ths+0.114
agg+0.111
eking+0.111
aman+0.100
ering+0.098
Neg logit contributions
.-0.104
."-0.097
 He-0.092
 Let-0.090
 towards-0.088
Token oh
Token ID11752
Feature activation+9.19e-02

Pos logit contributions
ths+0.475
agg+0.459
eking+0.449
aman+0.438
Kevin+0.416
Neg logit contributions
.-0.385
."-0.359
ashes-0.333
 He-0.327
 rider-0.313
Token!"
Token ID2474
Feature activation-5.29e-02

Pos logit contributions
ths+0.165
agg+0.160
eking+0.156
aman+0.150
prisingly+0.145
Neg logit contributions
ashes-0.140
.-0.137
."-0.129
 He-0.126
 rider-0.125
Token He
Token ID679
Feature activation-2.15e-02

Pos logit contributions
.+0.064
."+0.058
ashes+0.053
 He+0.052
 rider+0.049
Neg logit contributions
ths-0.119
agg-0.116
eking-0.114
aman-0.111
Kevin-0.106
Token quickly
Token ID2952
Feature activation-7.20e-02

Pos logit contributions
.+0.031
."+0.027
 He+0.026
 bar+0.024
 They+0.024
Neg logit contributions
ths-0.044
eking-0.043
agg-0.043
aman-0.042
Kevin-0.040
Token shut
Token ID4423
Feature activation-5.37e-02

Pos logit contributions
.+0.105
."+0.103
ashes+0.099
 rider+0.093
 He+0.092
Neg logit contributions
ths-0.139
agg-0.135
eking-0.131
aman-0.127
Kevin-0.120
Token what
Token ID644
Feature activation-3.04e-02

Pos logit contributions
ths+0.079
agg+0.077
eking+0.074
aman+0.073
Kevin+0.069
Neg logit contributions
.-0.082
."-0.077
 He-0.070
ashes-0.070
 Let-0.067
Token to
Token ID284
Feature activation+3.23e-04

Pos logit contributions
.+0.030
."+0.027
ashes+0.024
 He+0.023
 rider+0.022
Neg logit contributions
ths-0.075
agg-0.073
eking-0.072
aman-0.070
Kevin-0.068
Token say
Token ID910
Feature activation+5.57e-02

Pos logit contributions
agg+0.001
ths+0.001
eking+0.001
aman+0.001
Kevin+0.001
Neg logit contributions
ashes-0.000
.-0.000
."-0.000
 He-0.000
 Let-0.000
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
eking+0.149
ths+0.148
agg+0.142
aman+0.138
ering+0.138
Neg logit contributions
ashes-0.034
ny-0.025
powers-0.025
 rider-0.024
 He-0.021
Token "
Token ID366
Feature activation+6.79e-02

Pos logit contributions
.+0.163
."+0.148
ashes+0.141
 rider+0.131
 He+0.128
Neg logit contributions
ths-0.313
agg-0.306
eking-0.295
aman-0.291
Jess-0.281
TokenUh
Token ID34653
Feature activation+2.48e-01

Pos logit contributions
eking+0.140
ths+0.138
agg+0.137
aman+0.134
ering+0.129
Neg logit contributions
.-0.089
."-0.083
 Let-0.081
 He-0.080
 rider-0.077
Token,
Token ID11
Feature activation+8.85e-02

Pos logit contributions
ths+0.487
agg+0.470
aman+0.463
eking+0.453
Kevin+0.436
Neg logit contributions
.-0.387
."-0.359
 He-0.309
ashes-0.308
 Let-0.301
Token ok
Token ID12876
Feature activation+9.81e-02

Pos logit contributions
ths+0.184
agg+0.178
eking+0.175
aman+0.170
Jess+0.163
Neg logit contributions
.-0.118
."-0.109
ashes-0.105
 He-0.100
 rider-0.095
Token!"
Token ID2474
Feature activation-5.44e-02

Pos logit contributions
ths+0.197
agg+0.185
eking+0.179
aman+0.178
Jess+0.171
Neg logit contributions
ashes-0.135
five-0.123
.-0.118
 He-0.116
powers-0.115
Token it
Token ID340
Feature activation+2.26e-02

Pos logit contributions
.+0.089
."+0.085
ashes+0.083
 rider+0.079
 He+0.077
Neg logit contributions
ths-0.094
agg-0.092
eking-0.088
aman-0.085
Jess-0.082
Token said
Token ID531
Feature activation+7.43e-02

Pos logit contributions
ths+0.043
agg+0.041
eking+0.040
aman+0.039
prisingly+0.037
Neg logit contributions
.-0.035
."-0.033
ashes-0.031
 He-0.030
 rider-0.029
Token.
Token ID13
Feature activation-1.45e-01

Pos logit contributions
 Let+0.002
."+0.002
five+0.002
eer+0.002
ashes+0.002
Neg logit contributions
ths-0.008
eking-0.008
aman-0.007
agg-0.007
ering-0.007
Token Emma
Token ID18966
Feature activation+2.49e-02

Pos logit contributions
.+0.278
ashes+0.265
."+0.264
 rider+0.252
 He+0.243
Neg logit contributions
ths-0.207
agg-0.198
aman-0.187
eking-0.186
Jess-0.175
Token said
Token ID531
Feature activation+7.68e-02

Pos logit contributions
ths+0.052
agg+0.050
eking+0.050
aman+0.048
prisingly+0.046
Neg logit contributions
.-0.034
."-0.031
ashes-0.029
 He-0.028
 They-0.027
Token,
Token ID11
Feature activation+8.68e-02

Pos logit contributions
ths+0.181
agg+0.175
eking+0.174
aman+0.171
Kevin+0.164
Neg logit contributions
.-0.092
."-0.080
 He-0.071
ashes-0.067
 towards-0.066
Token "
Token ID366
Feature activation+6.67e-02

Pos logit contributions
ths+0.211
agg+0.205
eking+0.202
aman+0.197
prisingly+0.192
Neg logit contributions
.-0.099
."-0.086
 He-0.079
 They-0.073
 Let-0.071
TokenUh
Token ID34653
Feature activation+2.48e-01

Pos logit contributions
eking+0.124
ths+0.123
agg+0.119
ering+0.113
aman+0.107
Neg logit contributions
.-0.105
."-0.098
 Let-0.095
 He-0.091
 They-0.090
Token-
Token ID12
Feature activation+2.26e-02

Pos logit contributions
ths+0.456
agg+0.442
eking+0.427
aman+0.425
Kevin+0.406
Neg logit contributions
.-0.412
."-0.382
ashes-0.341
 He-0.337
 rider-0.329
Tokenoh
Token ID1219
Feature activation+1.66e-01

Pos logit contributions
ths+0.031
agg+0.030
eking+0.029
aman+0.028
Kevin+0.026
Neg logit contributions
.-0.047
."-0.044
ashes-0.042
 He-0.042
 rider-0.040
Token,
Token ID11
Feature activation+8.57e-02

Pos logit contributions
ths+0.302
eking+0.294
agg+0.292
aman+0.288
prisingly+0.270
Neg logit contributions
ashes-0.243
 He-0.224
.-0.223
 They-0.223
."-0.219
Token now
Token ID783
Feature activation+2.95e-02

Pos logit contributions
ths+0.167
agg+0.161
eking+0.158
aman+0.154
Kevin+0.146
Neg logit contributions
.-0.127
."-0.118
ashes-0.114
 He-0.110
 rider-0.105
Token what
Token ID644
Feature activation-3.16e-02

Pos logit contributions
ths+0.049
aman+0.042
eking+0.041
agg+0.041
 unfortunately+0.040
Neg logit contributions
ashes-0.054
five-0.048
v-0.048
eer-0.047
ny-0.047
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
ths+0.356
eking+0.346
agg+0.342
aman+0.329
prisingly+0.314
Neg logit contributions
.-0.170
."-0.150
 He-0.135
 They-0.126
 Let-0.120
Tokenâ
Token ID22940
Feature activation+6.88e-02

Pos logit contributions
ths+0.166
agg+0.155
eking+0.149
aman+0.143
Kevin+0.131
Neg logit contributions
.-0.337
."-0.323
ashes-0.312
 He-0.304
 rider-0.297
Token
Token ID26391
Feature activation+7.77e-02

Pos logit contributions
ths+0.111
eking+0.108
agg+0.106
aman+0.104
prisingly+0.097
Neg logit contributions
.-0.119
."-0.114
ashes-0.111
 He-0.106
powers-0.103
Token
Token ID129
Feature activation+3.88e-02

Pos logit contributions
ths+0.155
agg+0.151
eking+0.148
aman+0.144
prisingly+0.138
Neg logit contributions
.-0.115
."-0.106
 He-0.097
ashes-0.096
 They-0.093
Token
Token ID241
Feature activation-1.15e-02

Pos logit contributions
ths+0.065
eking+0.063
agg+0.061
aman+0.059
Kevin+0.055
Neg logit contributions
.-0.066
."-0.063
ashes-0.061
 Let-0.059
 He-0.059
TokenUh
Token ID34653
Feature activation+2.48e-01

Pos logit contributions
.+0.019
."+0.019
ashes+0.019
 rider+0.017
 bars+0.017
Neg logit contributions
agg-0.017
Kevin-0.017
Jess-0.017
ths-0.017
aman-0.017
Token-
Token ID12
Feature activation+2.59e-02

Pos logit contributions
ths+0.542
agg+0.524
aman+0.515
eking+0.504
Kevin+0.489
Neg logit contributions
.-0.336
."-0.299
 He-0.255
ashes-0.250
 towards-0.245
Tokenoh
Token ID1219
Feature activation+1.67e-01

Pos logit contributions
ths+0.029
agg+0.027
eking+0.026
aman+0.025
Kevin+0.023
Neg logit contributions
.-0.060
."-0.058
ashes-0.056
 He-0.055
 They-0.053
Token,
Token ID11
Feature activation+8.93e-02

Pos logit contributions
eking+0.361
ths+0.355
agg+0.341
aman+0.328
ering+0.325
Neg logit contributions
ashes-0.188
 They-0.178
 He-0.176
.-0.172
."-0.167
Tokenâ
Token ID22940
Feature activation+6.85e-02

Pos logit contributions
ths+0.147
agg+0.139
eking+0.136
aman+0.133
Jess+0.124
Neg logit contributions
.-0.158
."-0.150
ashes-0.149
 He-0.140
 rider-0.138
Token
Token ID26391
Feature activation+7.85e-02

Pos logit contributions
ths+0.095
eking+0.092
agg+0.089
aman+0.089
prisingly+0.079
Neg logit contributions
.-0.132
ashes-0.129
."-0.128
powers-0.122
 He-0.121
Token to
Token ID284
Feature activation-2.25e-03

Pos logit contributions
ths+0.181
agg+0.176
eking+0.175
aman+0.171
Kevin+0.164
Neg logit contributions
.-0.092
."-0.082
 He-0.073
ashes-0.072
 They-0.068
Token Tim
Token ID5045
Feature activation+5.34e-02

Pos logit contributions
.+0.003
."+0.003
 He+0.002
 play+0.002
 They+0.002
Neg logit contributions
ths-0.005
agg-0.005
eking-0.005
prisingly-0.005
Kevin-0.005
Tokenmy
Token ID1820
Feature activation+2.22e-02

Pos logit contributions
ths+0.100
agg+0.098
eking+0.095
aman+0.092
Jess+0.088
Neg logit contributions
.-0.086
."-0.079
ashes-0.073
 He-0.073
 rider-0.070
Token,
Token ID11
Feature activation+9.16e-02

Pos logit contributions
agg+0.053
ths+0.052
eking+0.051
aman+0.049
Jess+0.048
Neg logit contributions
.-0.027
."-0.023
 He-0.021
 They-0.019
ashes-0.019
Token "
Token ID366
Feature activation+6.35e-02

Pos logit contributions
ths+0.220
agg+0.217
eking+0.212
aman+0.205
prisingly+0.198
Neg logit contributions
.-0.106
."-0.093
 He-0.085
 They-0.078
 Let-0.078
TokenUh
Token ID34653
Feature activation+2.48e-01

Pos logit contributions
agg+0.138
ths+0.136
eking+0.134
aman+0.125
Kevin+0.122
Neg logit contributions
.-0.083
."-0.077
 He-0.072
 Let-0.072
 They-0.068
Token oh
Token ID11752
Feature activation+9.28e-02

Pos logit contributions
ths+0.379
agg+0.375
aman+0.360
eking+0.350
Kevin+0.339
Neg logit contributions
.-0.497
."-0.461
 He-0.408
ashes-0.405
 play-0.401
Token,
Token ID11
Feature activation+8.93e-02

Pos logit contributions
ths+0.167
agg+0.160
eking+0.158
aman+0.152
prisingly+0.146
Neg logit contributions
.-0.147
."-0.139
ashes-0.137
 He-0.131
 rider-0.128
Token the
Token ID262
Feature activation-3.57e-02

Pos logit contributions
ths+0.188
agg+0.183
eking+0.179
aman+0.174
Kevin+0.167
Neg logit contributions
.-0.122
."-0.112
ashes-0.102
 He-0.101
 Let-0.096
Token roof
Token ID9753
Feature activation-3.81e-02

Pos logit contributions
.+0.045
."+0.042
ashes+0.040
 He+0.039
 rider+0.037
Neg logit contributions
ths-0.077
agg-0.074
eking-0.072
aman-0.071
Jess-0.068
Token has
Token ID468
Feature activation-3.04e-02

Pos logit contributions
.+0.038
ashes+0.038
 rider+0.036
 He+0.036
."+0.036
Neg logit contributions
ths-0.086
eking-0.083
agg-0.079
aman-0.078
ering-0.076
Token worried
Token ID7960
Feature activation+1.51e-02

Pos logit contributions
ths+0.118
agg+0.116
eking+0.113
aman+0.106
Kevin+0.102
Neg logit contributions
.-0.120
."-0.114
ashes-0.109
 rider-0.107
 He-0.107
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
ths+0.042
eking+0.040
agg+0.040
ering+0.039
aman+0.039
Neg logit contributions
ashes-0.008
 rider-0.006
five-0.006
powers-0.006
 pedal-0.005
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
.+0.140
."+0.125
 He+0.116
ashes+0.109
 They+0.108
Neg logit contributions
ths-0.331
eking-0.322
agg-0.320
aman-0.309
prisingly-0.299
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
eking+0.401
ths+0.399
aman+0.378
agg+0.367
ering+0.361
Neg logit contributions
.-0.144
."-0.122
 He-0.117
 They-0.110
 Let-0.087
Token"
Token ID1
Feature activation+3.01e-02

Pos logit contributions
eking+0.273
ths+0.267
aman+0.258
agg+0.255
ering+0.239
Neg logit contributions
.-0.239
."-0.222
 He-0.219
 They-0.212
 Let-0.200
TokenUh
Token ID34653
Feature activation+2.48e-01

Pos logit contributions
eking+0.061
agg+0.060
ths+0.059
ering+0.058
aman+0.057
Neg logit contributions
.-0.039
 Let-0.036
."-0.036
 He-0.034
 They-0.033
Token-
Token ID12
Feature activation+2.53e-02

Pos logit contributions
ths+0.465
agg+0.452
aman+0.440
eking+0.437
Kevin+0.417
Neg logit contributions
.-0.403
."-0.374
 He-0.328
ashes-0.324
 Let-0.318
Tokenoh
Token ID1219
Feature activation+1.68e-01

Pos logit contributions
ths+0.029
agg+0.029
eking+0.027
aman+0.026
Kevin+0.023
Neg logit contributions
.-0.058
."-0.055
ashes-0.052
 He-0.052
 Let-0.051
Token,
Token ID11
Feature activation+9.02e-02

Pos logit contributions
ths+0.375
agg+0.367
eking+0.364
aman+0.351
prisingly+0.337
Neg logit contributions
.-0.182
ashes-0.171
."-0.168
 He-0.164
 They-0.157
Token this
Token ID428
Feature activation+3.15e-02

Pos logit contributions
ths+0.169
agg+0.163
eking+0.160
aman+0.155
Kevin+0.147
Neg logit contributions
.-0.143
."-0.134
ashes-0.124
 He-0.123
 They-0.117
Token fire
Token ID2046
Feature activation+9.39e-03

Pos logit contributions
ths+0.066
agg+0.064
eking+0.062
aman+0.061
Kevin+0.058
Neg logit contributions
.-0.042
."-0.039
ashes-0.037
 He-0.036
 rider-0.034
Token in
Token ID287
Feature activation-5.68e-02

Pos logit contributions
eking+0.044
ths+0.042
ering+0.039
 nowhere+0.037
agg+0.037
Neg logit contributions
powers-0.024
five-0.024
ashes-0.023
 rider-0.022
."-0.020
Token the
Token ID262
Feature activation-3.51e-02

Pos logit contributions
ashes+0.079
.+0.079
."+0.075
 rider+0.071
 Let+0.070
Neg logit contributions
ths-0.109
agg-0.104
aman-0.102
eking-0.101
Jess-0.099
Token distance
Token ID5253
Feature activation+2.12e-02

Pos logit contributions
.+0.055
."+0.052
ashes+0.052
 He+0.050
 rider+0.049
Neg logit contributions
ths-0.061
agg-0.060
aman-0.058
eking-0.058
Jess-0.055
Token.
Token ID13
Feature activation-1.42e-01

Pos logit contributions
eking+0.052
aman+0.050
ering+0.049
ths+0.048
Jane+0.047
Neg logit contributions
powers-0.017
ashes-0.016
 rider-0.013
five-0.012
 player-0.012
Token "
Token ID366
Feature activation+6.62e-02

Pos logit contributions
.+0.174
ashes+0.170
."+0.157
 rider+0.145
five+0.141
Neg logit contributions
ths-0.295
agg-0.279
aman-0.270
eking-0.270
Jess-0.262
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
agg+0.125
ths+0.125
eking+0.123
aman+0.115
ering+0.111
Neg logit contributions
.-0.102
."-0.096
 He-0.091
 rider-0.088
 Let-0.088
Token oh
Token ID11752
Feature activation+9.59e-02

Pos logit contributions
ths+0.560
aman+0.543
agg+0.537
Kevin+0.525
eking+0.509
Neg logit contributions
.-0.342
."-0.303
 towards-0.232
 play-0.231
 like-0.228
Token,
Token ID11
Feature activation+8.76e-02

Pos logit contributions
ths+0.201
agg+0.193
eking+0.191
aman+0.185
prisingly+0.180
Neg logit contributions
.-0.120
ashes-0.116
."-0.111
 He-0.106
 They-0.102
Token that
Token ID326
Feature activation-1.74e-02

Pos logit contributions
ths+0.196
agg+0.195
eking+0.191
aman+0.184
Kevin+0.179
Neg logit contributions
.-0.109
."-0.100
 He-0.089
 rider-0.084
ashes-0.082
Token cloud
Token ID6279
Feature activation+1.86e-02

Pos logit contributions
.+0.021
."+0.020
ashes+0.017
 He+0.017
 rider+0.016
Neg logit contributions
ths-0.039
agg-0.038
eking-0.038
aman-0.037
Kevin-0.035
Token looks
Token ID3073
Feature activation+5.39e-03

Pos logit contributions
ths+0.042
eking+0.041
agg+0.040
aman+0.039
ering+0.038
Neg logit contributions
.-0.019
ashes-0.018
 He-0.017
."-0.017
 rider-0.016
Token.
Token ID13
Feature activation-1.43e-01

Pos logit contributions
 rider+0.056
five+0.051
powers+0.046
ashes+0.046
 likes+0.043
Neg logit contributions
ths-0.106
eking-0.101
aman-0.098
agg-0.098
 unfortunately-0.095
Token
Token ID220
Feature activation+1.81e-01

Pos logit contributions
.+0.169
."+0.152
 He+0.141
 They+0.136
ashes+0.128
Neg logit contributions
ths-0.341
eking-0.332
agg-0.331
aman-0.314
prisingly-0.309
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
ths+0.471
eking+0.446
agg+0.441
aman+0.428
Kevin+0.410
Neg logit contributions
.-0.205
."-0.181
 He-0.161
 They-0.155
ashes-0.135
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
ths+0.393
eking+0.378
agg+0.368
aman+0.353
Kevin+0.337
Neg logit contributions
.-0.158
."-0.137
 He-0.119
 They-0.116
 Let-0.101
Token"
Token ID1
Feature activation+2.37e-02

Pos logit contributions
ths+0.240
agg+0.230
eking+0.224
aman+0.219
prisingly+0.207
Neg logit contributions
.-0.252
."-0.238
ashes-0.230
 He-0.222
 rider-0.219
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
agg+0.051
eking+0.051
ths+0.048
ering+0.047
aman+0.044
Neg logit contributions
.-0.031
 Let-0.028
."-0.028
 player-0.028
 play-0.028
Token oh
Token ID11752
Feature activation+9.55e-02

Pos logit contributions
ths+0.459
agg+0.453
aman+0.446
eking+0.429
Kevin+0.427
Neg logit contributions
.-0.424
."-0.391
 play-0.323
 Let-0.321
ashes-0.320
Token,
Token ID11
Feature activation+8.61e-02

Pos logit contributions
ths+0.175
agg+0.168
eking+0.166
aman+0.159
prisingly+0.155
Neg logit contributions
.-0.141
ashes-0.139
."-0.132
 He-0.130
 They-0.125
Token we
Token ID356
Feature activation-3.49e-02

Pos logit contributions
ths+0.195
agg+0.191
eking+0.188
aman+0.183
Kevin+0.178
Neg logit contributions
.-0.105
."-0.096
 He-0.084
ashes-0.082
 Let-0.080
Token have
Token ID423
Feature activation-1.67e-02

Pos logit contributions
.+0.038
."+0.034
ashes+0.028
 play+0.027
 They+0.026
Neg logit contributions
ths-0.087
agg-0.086
aman-0.082
eking-0.082
Jess-0.079
Token a
Token ID257
Feature activation-2.92e-02

Pos logit contributions
.+0.011
."+0.010
ashes+0.007
 He+0.006
 They+0.006
Neg logit contributions
ths-0.047
agg-0.047
eking-0.046
aman-0.045
Kevin-0.044
Token angry
Token ID7954
Feature activation+1.57e-02

Pos logit contributions
ths+0.114
agg+0.108
aman+0.105
eking+0.101
Kevin+0.098
Neg logit contributions
.-0.138
."-0.129
ashes-0.120
 He-0.117
 towards-0.113
Token.
Token ID13
Feature activation-1.41e-01

Pos logit contributions
ths+0.038
eking+0.037
ering+0.035
 unfortunately+0.034
prisingly+0.034
Neg logit contributions
 pedal-0.011
ashes-0.011
powers-0.011
 rider-0.010
 tire-0.010
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
.+0.084
."+0.064
 They+0.063
 He+0.062
 Let+0.042
Neg logit contributions
ths-0.424
eking-0.420
agg-0.416
aman-0.396
prisingly-0.393
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
ths+0.388
eking+0.377
agg+0.365
aman+0.362
ering+0.343
Neg logit contributions
.-0.156
."-0.132
 He-0.118
 They-0.116
 play-0.095
Token"
Token ID1
Feature activation+2.41e-02

Pos logit contributions
agg+0.279
ths+0.276
eking+0.274
aman+0.267
Kevin+0.242
Neg logit contributions
.-0.231
."-0.209
 He-0.194
 They-0.193
 Let-0.185
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
agg+0.053
eking+0.051
ths+0.048
ering+0.047
aman+0.047
Neg logit contributions
.-0.032
 Let-0.029
."-0.028
 dog-0.028
 They-0.028
Token oh
Token ID11752
Feature activation+9.61e-02

Pos logit contributions
ths+0.517
agg+0.514
aman+0.505
Kevin+0.485
eking+0.482
Neg logit contributions
.-0.373
."-0.338
 He-0.271
 Let-0.264
 play-0.263
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
ths+0.211
agg+0.205
eking+0.200
aman+0.198
Kevin+0.191
Neg logit contributions
.-0.136
."-0.125
 He-0.105
 Let-0.102
ashes-0.100
Token We
Token ID775
Feature activation-2.08e-02

Pos logit contributions
.+0.176
 rider+0.155
ashes+0.153
."+0.150
 pedal+0.142
Neg logit contributions
ths-0.336
agg-0.325
aman-0.310
eking-0.310
Jess-0.303
Token're
Token ID821
Feature activation+1.20e-01

Pos logit contributions
.+0.031
."+0.028
ashes+0.026
 He+0.025
 They+0.024
Neg logit contributions
ths-0.042
agg-0.041
eking-0.040
aman-0.039
Kevin-0.037
Token in
Token ID287
Feature activation-5.39e-02

Pos logit contributions
ths+0.212
agg+0.211
aman+0.203
Kevin+0.193
eking+0.189
Neg logit contributions
.-0.224
."-0.210
 like-0.178
ashes-0.177
 He-0.177
Token in
Token ID287
Feature activation-5.54e-02

Pos logit contributions
ths+0.094
agg+0.091
eking+0.089
aman+0.087
Kevin+0.082
Neg logit contributions
.-0.075
."-0.070
ashes-0.066
 He-0.064
 rider-0.062
Token their
Token ID511
Feature activation+1.70e-02

Pos logit contributions
.+0.075
."+0.066
 He+0.060
ashes+0.058
 They+0.057
Neg logit contributions
ths-0.122
agg-0.119
eking-0.117
aman-0.113
prisingly-0.109
Token tracks
Token ID8339
Feature activation-1.06e-01

Pos logit contributions
ths+0.034
agg+0.033
eking+0.031
aman+0.031
Kevin+0.030
Neg logit contributions
.-0.024
."-0.023
ashes-0.022
 rider-0.021
 He-0.020
Token.
Token ID13
Feature activation-1.42e-01

Pos logit contributions
ashes+0.070
powers+0.062
."+0.061
 rider+0.055
.+0.052
Neg logit contributions
ths-0.278
aman-0.272
eking-0.271
agg-0.264
ering-0.255
Token "
Token ID366
Feature activation+6.65e-02

Pos logit contributions
.+0.138
."+0.118
 They+0.114
 He+0.114
 Let+0.098
Neg logit contributions
ths-0.370
eking-0.368
agg-0.355
aman-0.342
prisingly-0.342
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
eking+0.147
ths+0.145
agg+0.144
ering+0.140
aman+0.133
Neg logit contributions
.-0.079
."-0.071
 Let-0.071
 They-0.070
 He-0.068
Token,
Token ID11
Feature activation+8.73e-02

Pos logit contributions
ths+0.419
agg+0.412
aman+0.410
eking+0.383
Kevin+0.380
Neg logit contributions
.-0.458
."-0.422
 Let-0.357
 play-0.355
 He-0.351
Token nothing
Token ID2147
Feature activation+1.61e-02

Pos logit contributions
ths+0.166
agg+0.161
eking+0.158
aman+0.153
Kevin+0.146
Neg logit contributions
.-0.135
."-0.126
ashes-0.117
 He-0.115
 rider-0.110
Token,"
Token ID553
Feature activation+1.87e-02

Pos logit contributions
eking+0.026
ths+0.026
agg+0.025
ering+0.024
prisingly+0.023
Neg logit contributions
 He-0.024
ashes-0.024
 They-0.024
.-0.024
 rider-0.023
Token they
Token ID484
Feature activation-3.05e-02

Pos logit contributions
eking+0.039
ths+0.038
agg+0.037
aman+0.035
iter+0.035
Neg logit contributions
.-0.030
 He-0.026
."-0.026
 They-0.025
 Let-0.022
Token said
Token ID531
Feature activation+7.26e-02

Pos logit contributions
.+0.046
."+0.040
 He+0.038
 They+0.036
ny+0.033
Neg logit contributions
ths-0.064
agg-0.061
eking-0.059
aman-0.058
prisingly-0.057
TokenThe
Token ID464
Feature activation+1.32e-02

Pos logit contributions
ths+0.201
agg+0.192
eking+0.180
Jess+0.177
Kevin+0.175
Neg logit contributions
.-0.284
ashes-0.271
."-0.270
 rider-0.247
eer-0.244
Token fox
Token ID21831
Feature activation-3.38e-03

Pos logit contributions
ths+0.030
agg+0.029
eking+0.029
aman+0.028
Kevin+0.027
Neg logit contributions
.-0.016
."-0.014
ashes-0.013
 He-0.013
 rider-0.012
Token said
Token ID531
Feature activation+7.64e-02

Pos logit contributions
.+0.005
."+0.004
 He+0.004
ny+0.004
 play+0.004
Neg logit contributions
ths-0.007
eking-0.007
agg-0.007
aman-0.007
Kevin-0.006
Token,
Token ID11
Feature activation+8.54e-02

Pos logit contributions
ths+0.169
agg+0.164
eking+0.161
aman+0.157
Kevin+0.150
Neg logit contributions
.-0.095
."-0.087
ashes-0.081
 He-0.078
 rider-0.074
Token "
Token ID366
Feature activation+6.49e-02

Pos logit contributions
ths+0.191
agg+0.186
eking+0.183
aman+0.179
prisingly+0.171
Neg logit contributions
.-0.106
."-0.096
 He-0.087
ashes-0.085
 They-0.081
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
ths+0.132
agg+0.131
eking+0.130
aman+0.121
ering+0.117
Neg logit contributions
.-0.091
."-0.084
 He-0.082
 Let-0.079
ny-0.078
Token oh
Token ID11752
Feature activation+9.67e-02

Pos logit contributions
ths+0.393
agg+0.379
eking+0.365
aman+0.362
Kevin+0.339
Neg logit contributions
.-0.472
."-0.442
 He-0.405
ashes-0.404
 rider-0.393
Token,
Token ID11
Feature activation+8.45e-02

Pos logit contributions
ths+0.163
agg+0.159
eking+0.157
prisingly+0.146
aman+0.146
Neg logit contributions
ashes-0.158
.-0.141
 They-0.136
."-0.135
 rider-0.135
Token I
Token ID314
Feature activation-7.14e-02

Pos logit contributions
ths+0.181
agg+0.176
eking+0.173
aman+0.169
prisingly+0.162
Neg logit contributions
.-0.114
."-0.105
 He-0.094
ashes-0.090
 Let-0.089
Token shouldn
Token ID6584
Feature activation+1.02e-02

Pos logit contributions
.+0.090
."+0.082
ashes+0.076
 He+0.074
 rider+0.070
Neg logit contributions
ths-0.158
agg-0.153
eking-0.150
aman-0.147
Kevin-0.140
Token't
Token ID470
Feature activation+9.81e-02

Pos logit contributions
ths+0.013
agg+0.013
eking+0.012
aman+0.012
prisingly+0.011
Neg logit contributions
.-0.023
."-0.022
 He-0.021
 Let-0.020
 They-0.020
Token her
Token ID607
Feature activation-3.57e-02

Pos logit contributions
ths+0.088
agg+0.086
eking+0.084
aman+0.083
Jess+0.080
Neg logit contributions
.-0.052
."-0.046
 He-0.042
ashes-0.041
 They-0.039
Token.
Token ID13
Feature activation-1.46e-01

Pos logit contributions
ashes+0.043
five+0.042
v+0.041
round+0.039
 They+0.039
Neg logit contributions
ths-0.066
agg-0.063
 nowhere-0.062
eking-0.062
aman-0.061
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
.+0.155
."+0.140
ashes+0.132
 rider+0.119
 He+0.116
Neg logit contributions
ths-0.340
agg-0.334
eking-0.325
aman-0.321
Kevin-0.311
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
ths+0.361
eking+0.347
agg+0.341
aman+0.333
prisingly+0.319
Neg logit contributions
.-0.169
."-0.148
 He-0.136
 They-0.126
ashes-0.114
Token"
Token ID1
Feature activation+2.42e-02

Pos logit contributions
ths+0.256
agg+0.246
eking+0.241
aman+0.234
Kevin+0.221
Neg logit contributions
.-0.242
."-0.227
ashes-0.215
 He-0.210
 rider-0.202
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
ths+0.047
agg+0.046
eking+0.046
aman+0.044
ering+0.041
Neg logit contributions
.-0.037
."-0.034
 He-0.033
ashes-0.032
 They-0.031
Token-
Token ID12
Feature activation+2.37e-02

Pos logit contributions
ths+0.546
agg+0.532
aman+0.524
eking+0.514
Kevin+0.499
Neg logit contributions
.-0.329
."-0.297
 He-0.248
ashes-0.247
 rider-0.236
Tokenoh
Token ID1219
Feature activation+1.66e-01

Pos logit contributions
ths+0.025
agg+0.024
eking+0.023
aman+0.021
Kevin+0.020
Neg logit contributions
.-0.057
."-0.054
ashes-0.052
 He-0.051
 rider-0.050
Token,
Token ID11
Feature activation+8.66e-02

Pos logit contributions
ths+0.348
eking+0.339
agg+0.334
aman+0.323
prisingly+0.310
Neg logit contributions
ashes-0.192
.-0.188
 He-0.181
."-0.179
 They-0.178
Token Lily
Token ID20037
Feature activation+3.78e-03

Pos logit contributions
ths+0.198
agg+0.195
eking+0.190
aman+0.185
Kevin+0.180
Neg logit contributions
.-0.106
."-0.096
 He-0.085
ashes-0.082
 Let-0.079
Token,"
Token ID553
Feature activation+3.24e-02

Pos logit contributions
ths+0.007
eking+0.006
aman+0.006
agg+0.006
ering+0.006
Neg logit contributions
ashes-0.006
powers-0.005
five-0.005
 towards-0.005
 He-0.005
Token everywhere
Token ID8347
Feature activation-1.76e-03

Pos logit contributions
.+0.110
."+0.107
ashes+0.101
 rider+0.101
 He+0.100
Neg logit contributions
ths-0.168
eking-0.162
agg-0.151
aman-0.150
prisingly-0.145
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
ashes+0.001
 rider+0.001
five+0.000
 pedal+0.000
eer+0.000
Neg logit contributions
ths-0.005
eking-0.005
agg-0.005
ering-0.005
Jess-0.005
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
.+0.153
."+0.138
 He+0.131
 They+0.123
ashes+0.113
Neg logit contributions
ths-0.362
eking-0.351
agg-0.350
aman-0.337
prisingly-0.323
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
ths+0.393
eking+0.382
aman+0.368
agg+0.367
ering+0.350
Neg logit contributions
.-0.148
."-0.127
 He-0.121
 They-0.113
 Let-0.091
Token"
Token ID1
Feature activation+2.56e-02

Pos logit contributions
agg+0.286
eking+0.281
ths+0.281
aman+0.270
Kevin+0.252
Neg logit contributions
.-0.218
."-0.198
 He-0.191
 They-0.183
 Let-0.177
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
agg+0.049
eking+0.048
ths+0.048
ering+0.046
aman+0.045
Neg logit contributions
.-0.039
."-0.037
 Let-0.035
 He-0.035
ashes-0.034
Token-
Token ID12
Feature activation+2.62e-02

Pos logit contributions
ths+0.558
agg+0.548
aman+0.539
eking+0.527
Kevin+0.517
Neg logit contributions
.-0.318
."-0.287
ashes-0.235
 He-0.234
 Let-0.224
Tokenoh
Token ID1219
Feature activation+1.66e-01

Pos logit contributions
ths+0.028
agg+0.027
eking+0.026
aman+0.025
Kevin+0.022
Neg logit contributions
.-0.062
."-0.059
ashes-0.057
 He-0.056
 rider-0.055
Token!"
Token ID2474
Feature activation-2.96e-02

Pos logit contributions
ths+0.383
agg+0.371
eking+0.371
aman+0.358
prisingly+0.345
Neg logit contributions
.-0.169
ashes-0.158
."-0.155
 He-0.150
 They-0.144
Token Tim
Token ID5045
Feature activation+3.94e-02

Pos logit contributions
.+0.036
."+0.031
 He+0.030
 They+0.028
ashes+0.026
Neg logit contributions
ths-0.069
agg-0.068
eking-0.067
aman-0.065
Kevin-0.063
Token said
Token ID531
Feature activation+6.61e-02

Pos logit contributions
ths+0.069
eking+0.065
agg+0.065
aman+0.062
prisingly+0.059
Neg logit contributions
.-0.063
."-0.060
ashes-0.060
 He-0.056
 rider-0.056
Token Lily
Token ID20037
Feature activation+5.56e-03

Pos logit contributions
.+0.006
ashes+0.005
."+0.005
 rider+0.005
powers+0.005
Neg logit contributions
ths-0.008
agg-0.008
eking-0.008
aman-0.007
Kevin-0.007
Token.
Token ID13
Feature activation-1.46e-01

Pos logit contributions
eking+0.015
ths+0.015
ering+0.014
aman+0.014
agg+0.014
Neg logit contributions
ashes-0.003
 rider-0.002
powers-0.002
."-0.002
five-0.002
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
.+0.170
."+0.149
 He+0.142
 They+0.131
ashes+0.130
Neg logit contributions
ths-0.346
agg-0.337
eking-0.336
aman-0.323
prisingly-0.312
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
ths+0.330
eking+0.317
agg+0.317
aman+0.306
prisingly+0.292
Neg logit contributions
.-0.179
."-0.161
 He-0.146
ashes-0.138
 They-0.137
Token"
Token ID1
Feature activation+2.39e-02

Pos logit contributions
ths+0.254
agg+0.245
eking+0.239
aman+0.232
Kevin+0.220
Neg logit contributions
.-0.243
."-0.228
ashes-0.215
 He-0.211
 rider-0.203
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
eking+0.051
agg+0.050
aman+0.050
ering+0.048
ths+0.047
Neg logit contributions
.-0.031
 They-0.029
."-0.028
ashes-0.028
 He-0.027
Token oh
Token ID11752
Feature activation+9.65e-02

Pos logit contributions
ths+0.524
agg+0.518
aman+0.508
eking+0.490
Kevin+0.486
Neg logit contributions
.-0.359
."-0.324
 He-0.267
ashes-0.260
 Let-0.257
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
ths+0.199
agg+0.193
eking+0.189
aman+0.185
Kevin+0.177
Neg logit contributions
.-0.139
."-0.128
ashes-0.115
 He-0.114
 Let-0.109
Token We
Token ID775
Feature activation-2.17e-02

Pos logit contributions
.+0.171
ashes+0.152
 rider+0.151
."+0.143
 pedal+0.139
Neg logit contributions
ths-0.338
agg-0.326
aman-0.310
eking-0.309
Jess-0.308
Token're
Token ID821
Feature activation+1.19e-01

Pos logit contributions
.+0.033
."+0.031
ashes+0.028
 He+0.028
 They+0.027
Neg logit contributions
ths-0.043
agg-0.041
eking-0.040
aman-0.039
Kevin-0.037
Token in
Token ID287
Feature activation-5.43e-02

Pos logit contributions
ths+0.215
agg+0.212
aman+0.202
eking+0.195
Kevin+0.193
Neg logit contributions
.-0.215
."-0.202
ashes-0.174
 He-0.173
 like-0.170
Token scared
Token ID12008
Feature activation-1.36e-02

Pos logit contributions
ths+0.129
aman+0.120
eking+0.117
agg+0.116
prisingly+0.109
Neg logit contributions
.-0.153
."-0.141
 He-0.133
ashes-0.130
 They-0.127
Token,
Token ID11
Feature activation+9.13e-02

Pos logit contributions
ashes+0.015
powers+0.013
 rider+0.013
."+0.013
five+0.013
Neg logit contributions
ths-0.030
aman-0.029
eking-0.029
agg-0.029
 unfortunately-0.027
Token she
Token ID673
Feature activation-4.65e-02

Pos logit contributions
ths+0.192
agg+0.190
eking+0.182
aman+0.175
prisingly+0.174
Neg logit contributions
.-0.137
."-0.119
 He-0.114
 They-0.106
 towards-0.104
Token said
Token ID531
Feature activation+7.77e-02

Pos logit contributions
.+0.077
."+0.073
ashes+0.070
 He+0.067
 rider+0.065
Neg logit contributions
ths-0.082
agg-0.079
eking-0.078
aman-0.075
Kevin-0.071
Token "
Token ID366
Feature activation+6.62e-02

Pos logit contributions
ths+0.185
agg+0.179
eking+0.177
aman+0.173
prisingly+0.167
Neg logit contributions
.-0.093
."-0.080
 He-0.070
ashes-0.065
 They-0.065
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
agg+0.136
ths+0.135
eking+0.132
aman+0.122
prisingly+0.121
Neg logit contributions
.-0.092
."-0.084
 He-0.077
 rider-0.076
 Let-0.075
Token-
Token ID12
Feature activation+2.33e-02

Pos logit contributions
ths+0.443
agg+0.424
eking+0.423
aman+0.397
prisingly+0.386
Neg logit contributions
.-0.400
."-0.376
ashes-0.372
 He-0.361
 They-0.348
Tokenoh
Token ID1219
Feature activation+1.64e-01

Pos logit contributions
ths+0.029
agg+0.027
eking+0.026
aman+0.025
Kevin+0.023
Neg logit contributions
.-0.052
."-0.049
ashes-0.048
 He-0.047
 They-0.046
Token",
Token ID1600
Feature activation+1.80e-03

Pos logit contributions
ths+0.302
eking+0.294
agg+0.288
aman+0.282
tha+0.271
Neg logit contributions
ashes-0.236
 They-0.215
 He-0.211
powers-0.209
.-0.204
Token and
Token ID290
Feature activation+4.81e-02

Pos logit contributions
ths+0.004
agg+0.004
eking+0.004
aman+0.004
prisingly+0.004
Neg logit contributions
.-0.002
."-0.002
 He-0.002
 They-0.001
ashes-0.001
Token ran
Token ID4966
Feature activation-1.22e-01

Pos logit contributions
ths+0.087
agg+0.085
eking+0.083
aman+0.081
Kevin+0.078
Neg logit contributions
.-0.080
."-0.074
 He-0.069
ashes-0.066
 They-0.065
Token in
Token ID287
Feature activation-5.68e-02

Pos logit contributions
ths+0.063
eking+0.062
agg+0.060
aman+0.057
prisingly+0.057
Neg logit contributions
ashes-0.029
 rider-0.028
.-0.028
."-0.027
five-0.026
Token and
Token ID290
Feature activation+4.61e-02

Pos logit contributions
.+0.042
ashes+0.042
."+0.041
 rider+0.037
 He+0.034
Neg logit contributions
ths-0.142
agg-0.138
aman-0.137
eking-0.136
Kevin-0.131
Token said
Token ID531
Feature activation+7.77e-02

Pos logit contributions
agg+0.106
ths+0.103
eking+0.100
aman+0.099
prisingly+0.094
Neg logit contributions
.-0.065
."-0.054
 play-0.048
 He-0.048
 towards-0.045
Token,
Token ID11
Feature activation+8.82e-02

Pos logit contributions
ths+0.191
eking+0.187
agg+0.187
aman+0.183
prisingly+0.177
Neg logit contributions
.-0.092
."-0.077
 He-0.070
 They-0.064
 Let-0.059
Token "
Token ID366
Feature activation+6.48e-02

Pos logit contributions
agg+0.228
ths+0.226
eking+0.219
aman+0.215
prisingly+0.211
Neg logit contributions
.-0.095
."-0.077
 He-0.073
 They-0.068
 Let-0.062
TokenUh
Token ID34653
Feature activation+2.47e-01

Pos logit contributions
agg+0.146
eking+0.137
ths+0.136
iter+0.124
ering+0.123
Neg logit contributions
.-0.085
 He-0.081
 Let-0.078
."-0.076
 They-0.075
Token oh
Token ID11752
Feature activation+9.62e-02

Pos logit contributions
ths+0.403
agg+0.402
aman+0.384
eking+0.377
Kevin+0.366
Neg logit contributions
.-0.468
."-0.432
 He-0.380
 play-0.374
 rider-0.374
Token,
Token ID11
Feature activation+8.71e-02

Pos logit contributions
ths+0.180
agg+0.171
eking+0.170
aman+0.163
prisingly+0.157
Neg logit contributions
.-0.141
ashes-0.139
."-0.134
 He-0.126
 rider-0.125
Token you
Token ID345
Feature activation+5.75e-03

Pos logit contributions
agg+0.208
ths+0.204
eking+0.201
aman+0.195
Kevin+0.194
Neg logit contributions
.-0.099
."-0.090
 He-0.080
 They-0.075
 Let-0.075
Token boys
Token ID6510
Feature activation-5.21e-02

Pos logit contributions
ths+0.012
agg+0.011
eking+0.011
aman+0.011
Kevin+0.010
Neg logit contributions
.-0.008
ashes-0.007
."-0.007
 He-0.006
 towards-0.006
Token made
Token ID925
Feature activation-2.86e-02

Pos logit contributions
ashes+0.049
 He+0.049
powers+0.048
 rider+0.045
five+0.045
Neg logit contributions
eking-0.114
ths-0.113
aman-0.109
ering-0.105
 done-0.102
Token "
Token ID366
Feature activation+5.84e-02

Pos logit contributions
ashes+0.071
powers+0.061
eer+0.056
ny+0.055
five+0.054
Neg logit contributions
ths-0.083
 unfortunately-0.077
eking-0.077
aman-0.075
lf-0.073
Tokennews
Token ID10827
Feature activation+6.63e-02

Pos logit contributions
ths+0.108
agg+0.104
eking+0.102
aman+0.099
prisingly+0.094
Neg logit contributions
.-0.092
."-0.086
ashes-0.081
 He-0.079
 rider-0.076
Token"
Token ID1
Feature activation+1.47e-02

Pos logit contributions
ths+0.109
agg+0.104
eking+0.101
aman+0.097
Kevin+0.093
Neg logit contributions
.-0.113
ashes-0.108
."-0.106
 He-0.103
 rider-0.100
Token on
Token ID319
Feature activation-6.15e-02

Pos logit contributions
ths+0.033
agg+0.031
eking+0.031
aman+0.030
Kevin+0.029
Neg logit contributions
.-0.016
."-0.015
ashes-0.015
 Let-0.013
five-0.013
Token it
Token ID340
Feature activation+1.85e-02

Pos logit contributions
.+0.086
."+0.081
ashes+0.079
 He+0.073
 rider+0.071
Neg logit contributions
ths-0.123
agg-0.118
eking-0.116
aman-0.114
Kevin-0.108
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
ths+0.045
 unfortunately+0.043
eking+0.043
ering+0.041
 nowhere+0.041
Neg logit contributions
ashes-0.014
five-0.013
powers-0.011
eer-0.011
 likes-0.010
Token Tim
Token ID5045
Feature activation+3.68e-02

Pos logit contributions
ashes+0.223
 rider+0.223
.+0.217
."+0.208
ny+0.202
Neg logit contributions
agg-0.315
ths-0.312
aman-0.289
Jane-0.279
eking-0.278
Token was
Token ID373
Feature activation+5.10e-02

Pos logit contributions
ths+0.076
agg+0.073
eking+0.073
aman+0.071
Kevin+0.067
Neg logit contributions
.-0.048
."-0.045
ashes-0.044
 He-0.041
 rider-0.040
Token very
Token ID845
Feature activation+6.50e-02

Pos logit contributions
ths+0.100
agg+0.097
aman+0.095
eking+0.092
Kevin+0.088
Neg logit contributions
.-0.082
."-0.075
 He-0.070
ashes-0.067
 They-0.065
Token curious
Token ID11040
Feature activation-1.37e-02

Pos logit contributions
ths+0.102
agg+0.098
eking+0.096
aman+0.092
Kevin+0.087
Neg logit contributions
.-0.123
."-0.116
ashes-0.110
 He-0.108
 rider-0.105
Token about
Token ID546
Feature activation+4.04e-02

Pos logit contributions
ashes+0.015
five+0.012
powers+0.011
atters+0.011
 rider+0.010
Neg logit contributions
ths-0.030
ering-0.028
Jane-0.028
agg-0.028
 nowhere-0.028
Token "
Token ID366
Feature activation+5.91e-02

Pos logit contributions
ths+0.184
agg+0.180
eking+0.176
aman+0.173
prisingly+0.166
Neg logit contributions
.-0.095
."-0.085
 He-0.077
ashes-0.074
 They-0.072
TokenI
Token ID40
Feature activation-8.29e-02

Pos logit contributions
ths+0.074
Fore+0.069
aman+0.069
Jess+0.069
Kevin+0.068
Neg logit contributions
.-0.120
."-0.112
ashes-0.109
powers-0.102
 towards-0.100
Token love
Token ID1842
Feature activation+2.96e-02

Pos logit contributions
.+0.093
."+0.087
ashes+0.086
 He+0.082
 Let+0.079
Neg logit contributions
agg-0.175
ths-0.170
prisingly-0.167
eking-0.166
Kevin-0.163
Token this
Token ID428
Feature activation+2.90e-02

Pos logit contributions
ths+0.041
eking+0.037
agg+0.033
ering+0.031
aman+0.031
Neg logit contributions
ashes-0.058
ny-0.054
.-0.053
 He-0.052
five-0.052
Token shirt
Token ID10147
Feature activation-4.53e-02

Pos logit contributions
pron+0.047
mber+0.047
agg+0.046
aman+0.046
eking+0.046
Neg logit contributions
ashes-0.040
 He-0.038
five-0.037
 They-0.036
powers-0.035
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
ashes+0.056
five+0.049
 Let+0.046
 pedal+0.046
powers+0.046
Neg logit contributions
ths-0.080
eking-0.075
 exactly-0.074
 done-0.074
agg-0.074
Token It
Token ID632
Feature activation+3.41e-02

Pos logit contributions
ashes+0.255
.+0.245
powers+0.206
 towards+0.202
 bars+0.198
Neg logit contributions
mmm-0.285
omm-0.264
 unfortunately-0.263
hh-0.256
prisingly-0.256
Token is
Token ID318
Feature activation+5.75e-02

Pos logit contributions
ths+0.062
eking+0.061
agg+0.058
aman+0.055
prisingly+0.055
Neg logit contributions
ashes-0.045
.-0.042
five-0.042
 towards-0.040
."-0.038
Token so
Token ID523
Feature activation+7.21e-02

Pos logit contributions
ths+0.098
eking+0.095
agg+0.094
aman+0.090
prisingly+0.086
Neg logit contributions
.-0.091
ashes-0.089
."-0.086
five-0.083
 He-0.081
Token nice
Token ID3621
Feature activation+4.02e-04

Pos logit contributions
agg+0.124
ths+0.119
eking+0.119
Kevin+0.109
 impressed+0.109
Neg logit contributions
.-0.107
ashes-0.106
."-0.100
five-0.099
 rider-0.098
Token!"
Token ID2474
Feature activation-6.48e-02

Pos logit contributions
mber+0.001
ths+0.001
agg+0.001
ll+0.001
prisingly+0.001
Neg logit contributions
 pedal-0.000
 pedals-0.000
 tire-0.000
ashes-0.000
five-0.000
Token and
Token ID290
Feature activation+4.43e-02

Pos logit contributions
ashes+0.062
powers+0.058
five+0.057
 Let+0.057
 They+0.053
Neg logit contributions
eking-0.077
ths-0.074
ering-0.074
aman-0.072
 setup-0.068
Token wide
Token ID3094
Feature activation-6.94e-03

Pos logit contributions
ths+0.076
eking+0.070
agg+0.070
prisingly+0.065
 impressed+0.064
Neg logit contributions
.-0.074
ashes-0.072
."-0.071
ny-0.065
 He-0.065
Token for
Token ID329
Feature activation-6.43e-03

Pos logit contributions
ashes+0.007
five+0.007
round+0.005
iffs+0.005
ny+0.005
Neg logit contributions
ths-0.016
eking-0.015
 exactly-0.014
 impressed-0.014
ering-0.014
Token his
Token ID465
Feature activation-1.67e-02

Pos logit contributions
.+0.010
."+0.009
ashes+0.008
 He+0.008
 rider+0.008
Neg logit contributions
ths-0.013
agg-0.012
eking-0.012
aman-0.012
Kevin-0.011
Token amazing
Token ID4998
Feature activation+4.80e-02

Pos logit contributions
ashes+0.025
.+0.024
."+0.024
ny+0.023
 He+0.023
Neg logit contributions
ths-0.032
agg-0.028
eking-0.027
aman-0.027
Kevin-0.026
Token feats
Token ID35664
Feature activation-1.70e-01

Pos logit contributions
ths+0.098
agg+0.088
aman+0.085
eking+0.082
Kevin+0.078
Neg logit contributions
ashes-0.065
 They-0.060
."-0.058
ny-0.058
 He-0.057
Token!
Token ID0
Feature activation-1.30e-01

Pos logit contributions
ashes+0.122
ny+0.083
 bone+0.081
 fur+0.074
powers+0.070
Neg logit contributions
ths-0.435
eking-0.426
agg-0.413
prisingly-0.401
ering-0.398
Token He
Token ID679
Feature activation-2.15e-02

Pos logit contributions
ashes+0.176
.+0.156
 rider+0.148
."+0.146
 towards+0.144
Neg logit contributions
aman-0.246
agg-0.242
ths-0.234
Jess-0.232
Jane-0.228
Token could
Token ID714
Feature activation-1.85e-02

Pos logit contributions
.+0.028
."+0.027
ashes+0.027
 He+0.024
 Let+0.023
Neg logit contributions
ths-0.045
agg-0.043
eking-0.041
aman-0.040
Kevin-0.039
Token jump
Token ID4391
Feature activation-5.66e-02

Pos logit contributions
.+0.024
."+0.023
ashes+0.022
 Let+0.021
 He+0.020
Neg logit contributions
ths-0.038
agg-0.037
eking-0.036
aman-0.034
Kevin-0.034
Token higher
Token ID2440
Feature activation-7.21e-03

Pos logit contributions
.+0.066
."+0.064
ashes+0.063
 rider+0.058
 Let+0.058
Neg logit contributions
ths-0.118
agg-0.115
eking-0.112
aman-0.108
Jess-0.105
Token-
Token ID12
Feature activation+2.14e-02

Pos logit contributions
ths+0.069
eking+0.066
agg+0.066
aman+0.064
ering+0.060
Neg logit contributions
.-0.044
ashes-0.043
 He-0.041
."-0.040
 Let-0.038
Tokench
Token ID354
Feature activation+2.36e-02

Pos logit contributions
ths+0.042
eking+0.040
agg+0.039
aman+0.038
prisingly+0.037
Neg logit contributions
.-0.030
."-0.028
ashes-0.027
 He-0.026
 They-0.025
Tokenoo
Token ID2238
Feature activation+3.45e-02

Pos logit contributions
ths+0.026
agg+0.025
eking+0.024
aman+0.023
Kevin+0.021
Neg logit contributions
.-0.055
."-0.053
ashes-0.050
 He-0.050
 rider-0.048
Token"
Token ID1
Feature activation+1.92e-02

Pos logit contributions
ths+0.073
eking+0.070
agg+0.069
aman+0.067
ering+0.064
Neg logit contributions
.-0.040
ashes-0.039
 He-0.037
."-0.036
 Let-0.035
Token sound
Token ID2128
Feature activation+1.70e-03

Pos logit contributions
ths+0.042
agg+0.040
eking+0.039
aman+0.038
prisingly+0.038
Neg logit contributions
.-0.020
ashes-0.019
."-0.018
five-0.017
 He-0.016
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
ths+0.004
eking+0.004
agg+0.004
aman+0.004
Kevin+0.003
Neg logit contributions
.-0.002
ashes-0.002
."-0.002
 He-0.001
 Let-0.001
Token The
Token ID383
Feature activation-4.78e-03

Pos logit contributions
ashes+0.161
.+0.153
 rider+0.152
ny+0.135
powers+0.133
Neg logit contributions
agg-0.380
ths-0.370
aman-0.356
Jess-0.348
prisingly-0.339
Token train
Token ID4512
Feature activation-2.59e-02

Pos logit contributions
.+0.005
."+0.004
ashes+0.004
 He+0.004
 rider+0.003
Neg logit contributions
ths-0.012
agg-0.012
eking-0.011
aman-0.011
Kevin-0.011
Token liked
Token ID8288
Feature activation-9.43e-03

Pos logit contributions
.+0.037
."+0.035
ashes+0.034
 He+0.032
 Let+0.030
Neg logit contributions
ths-0.051
agg-0.048
eking-0.048
aman-0.045
prisingly-0.044
Token to
Token ID284
Feature activation-4.30e-03

Pos logit contributions
.+0.009
."+0.008
ashes+0.006
 He+0.006
 They+0.006
Neg logit contributions
ths-0.024
agg-0.024
eking-0.023
aman-0.023
Kevin-0.022
Token go
Token ID467
Feature activation-5.06e-02

Pos logit contributions
ashes+0.004
.+0.004
powers+0.004
 pads+0.004
 Let+0.004
Neg logit contributions
eking-0.009
ths-0.009
agg-0.009
aman-0.008
prisingly-0.008
Token,
Token ID11
Feature activation+8.42e-02

Pos logit contributions
powers+0.122
ashes+0.106
 He+0.102
 Let+0.100
 rider+0.098
Neg logit contributions
ths-0.234
agg-0.228
eking-0.225
aman-0.224
prisingly-0.216
Token slide
Token ID10649
Feature activation-6.22e-02

Pos logit contributions
ths+0.218
agg+0.212
eking+0.209
aman+0.205
Kevin+0.198
Neg logit contributions
.-0.074
."-0.065
ashes-0.057
 He-0.055
 rider-0.050
Token and
Token ID290
Feature activation+4.36e-02

Pos logit contributions
powers+0.061
ashes+0.058
 He+0.055
.+0.055
."+0.055
Neg logit contributions
ths-0.138
aman-0.130
eking-0.128
agg-0.127
ering-0.121
Token see
Token ID766
Feature activation+1.11e-02

Pos logit contributions
ths+0.095
agg+0.092
eking+0.091
Jess+0.088
aman+0.087
Neg logit contributions
.-0.043
."-0.041
 He-0.038
ashes-0.037
powers-0.036
Token-
Token ID12
Feature activation+2.38e-02

Pos logit contributions
ths+0.015
aman+0.014
 impressed+0.014
eking+0.014
agg+0.014
Neg logit contributions
powers-0.020
ny-0.020
ashes-0.019
ro-0.019
five-0.019
Tokensaw
Token ID43439
Feature activation-1.68e-01

Pos logit contributions
ths+0.053
agg+0.051
eking+0.051
aman+0.049
Kevin+0.047
Neg logit contributions
.-0.029
."-0.026
ashes-0.024
 He-0.024
 rider-0.022
Token.
Token ID13
Feature activation-1.47e-01

Pos logit contributions
powers+0.099
 pedal+0.091
ray+0.080
 He+0.079
 name+0.077
Neg logit contributions
ths-0.409
eking-0.391
ering-0.376
Fore-0.366
agg-0.362
Token But
Token ID887
Feature activation+8.67e-02

Pos logit contributions
.+0.149
."+0.136
 rider+0.129
ashes+0.122
powers+0.115
Neg logit contributions
agg-0.339
ths-0.333
aman-0.329
eking-0.315
Jess-0.308
Token their
Token ID511
Feature activation+1.39e-02

Pos logit contributions
agg+0.216
ths+0.212
eking+0.210
Kevin+0.206
Jess+0.201
Neg logit contributions
.-0.101
."-0.083
 play-0.073
 like-0.073
 bar-0.072
Token favorite
Token ID4004
Feature activation+6.18e-02

Pos logit contributions
ths+0.026
agg+0.025
eking+0.024
aman+0.024
Kevin+0.022
Neg logit contributions
.-0.021
."-0.020
 He-0.019
ashes-0.019
 Let-0.018
Token thing
Token ID1517
Feature activation+1.15e-02

Pos logit contributions
ths+0.132
agg+0.127
aman+0.127
eking+0.124
Jane+0.117
Neg logit contributions
ashes-0.064
.-0.061
."-0.060
 He-0.059
powers-0.057
Tokenck
Token ID694
Feature activation-2.80e-03

Pos logit contributions
.+0.002
."+0.002
ashes+0.002
 He+0.002
 Let+0.001
Neg logit contributions
ths-0.003
agg-0.003
eking-0.003
aman-0.003
prisingly-0.003
Token"
Token ID1
Feature activation+2.04e-02

Pos logit contributions
ashes+0.003
 He+0.003
.+0.003
 rider+0.003
 Let+0.003
Neg logit contributions
ths-0.006
agg-0.006
eking-0.006
aman-0.005
ering-0.005
Token all
Token ID477
Feature activation-7.38e-02

Pos logit contributions
ths+0.045
agg+0.042
eking+0.042
prisingly+0.040
aman+0.040
Neg logit contributions
ashes-0.020
.-0.020
."-0.018
 He-0.017
five-0.017
Token day
Token ID1110
Feature activation+4.06e-02

Pos logit contributions
.+0.103
ashes+0.103
powers+0.102
 bone+0.100
 rider+0.100
Neg logit contributions
ths-0.125
agg-0.121
eking-0.119
aman-0.116
prisingly-0.114
Token long
Token ID890
Feature activation-4.89e-02

Pos logit contributions
ths+0.110
eking+0.108
agg+0.106
aman+0.102
ering+0.100
Neg logit contributions
 He-0.019
ashes-0.019
.-0.016
 rider-0.016
 Let-0.016
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
ashes+0.027
 He+0.024
 rider+0.021
 pedal+0.020
ny+0.020
Neg logit contributions
ths-0.132
eking-0.126
agg-0.121
aman-0.119
ering-0.118
Token
Token ID198
Feature activation+1.32e-01

Pos logit contributions
.+0.199
."+0.179
ashes+0.177
 rider+0.164
 He+0.159
Neg logit contributions
ths-0.366
agg-0.359
eking-0.344
aman-0.342
Jess-0.331
Token
Token ID198
Feature activation+1.33e-01

Pos logit contributions
ths+0.353
eking+0.344
aman+0.326
agg+0.324
ering+0.307
Neg logit contributions
.-0.147
."-0.123
 He-0.107
 They-0.102
 play-0.087
TokenOne
Token ID3198
Feature activation+1.89e-02

Pos logit contributions
ths+0.227
eking+0.220
agg+0.220
aman+0.209
Kevin+0.196
Neg logit contributions
.-0.246
."-0.227
 He-0.212
 They-0.209
ashes-0.205
Token day
Token ID1110
Feature activation+4.11e-02

Pos logit contributions
agg+0.028
ths+0.027
prisingly+0.024
eking+0.024
Jess+0.023
Neg logit contributions
ashes-0.033
.-0.032
."-0.031
 He-0.030
powers-0.030
Token,
Token ID11
Feature activation+8.22e-02

Pos logit contributions
ths+0.081
agg+0.078
eking+0.075
aman+0.073
prisingly+0.071
Neg logit contributions
.-0.057
ashes-0.054
."-0.054
 He-0.051
 rider-0.050
TokenOnce
Token ID7454
Feature activation+1.73e-01

Pos logit contributions
agg+0.165
ths+0.160
Jess+0.152
aman+0.150
eking+0.149
Neg logit contributions
ashes-0.163
 rider-0.158
.-0.156
."-0.153
five-0.150
Token there
Token ID612
Feature activation-2.17e-02

Pos logit contributions
ths+0.287
eking+0.269
agg+0.242
aman+0.236
prisingly+0.232
Neg logit contributions
.-0.388
."-0.340
 He-0.317
 They-0.306
 play-0.291
Token was
Token ID373
Feature activation+5.23e-02

Pos logit contributions
.+0.026
."+0.019
 He+0.018
 play+0.017
 They+0.016
Neg logit contributions
eking-0.057
ths-0.057
agg-0.053
prisingly-0.051
Kevin-0.051
Token a
Token ID257
Feature activation-3.45e-02

Pos logit contributions
ths+0.118
agg+0.116
eking+0.112
aman+0.111
Jess+0.107
Neg logit contributions
.-0.059
."-0.055
ashes-0.051
 He-0.048
 rider-0.047
Token bunny
Token ID44915
Feature activation-7.96e-03

Pos logit contributions
.+0.053
."+0.051
ashes+0.050
 He+0.048
 towards+0.047
Neg logit contributions
ths-0.061
agg-0.060
aman-0.056
eking-0.056
Kevin-0.054
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
ashes+0.015
five+0.015
 pedals+0.014
powers+0.014
 pedal+0.014
Neg logit contributions
agg-0.010
eking-0.010
ths-0.010
 sudden-0.009
Jess-0.009
Token The
Token ID383
Feature activation-6.59e-03

Pos logit contributions
ashes+0.164
.+0.155
."+0.147
 bars+0.138
 rider+0.138
Neg logit contributions
agg-0.374
ths-0.354
Jess-0.349
aman-0.347
Kevin-0.339
Token bunny
Token ID44915
Feature activation-7.41e-03

Pos logit contributions
.+0.007
ashes+0.006
."+0.006
five+0.006
 Let+0.005
Neg logit contributions
ths-0.015
agg-0.015
eking-0.014
aman-0.014
Jess-0.014
Token had
Token ID550
Feature activation-3.41e-02

Pos logit contributions
ashes+0.010
.+0.010
."+0.010
five+0.010
 rider+0.009
Neg logit contributions
agg-0.013
ths-0.013
eking-0.013
Jess-0.012
aman-0.012
Token two
Token ID734
Feature activation-3.44e-02

Pos logit contributions
.+0.042
."+0.039
ashes+0.038
 rider+0.035
 Let+0.034
Neg logit contributions
agg-0.071
ths-0.071
eking-0.070
aman-0.065
Jess-0.065
Token big
Token ID1263
Feature activation-3.77e-02

Pos logit contributions
.+0.051
."+0.050
ashes+0.048
 Let+0.046
five+0.046
Neg logit contributions
ths-0.063
agg-0.062
eking-0.061
aman-0.056
 sudden-0.055
Token were
Token ID547
Feature activation+1.00e-01

Pos logit contributions
.+0.064
ashes+0.061
."+0.061
 He+0.058
 Let+0.056
Neg logit contributions
ths-0.073
agg-0.071
eking-0.069
aman-0.067
Kevin-0.064
Token applauded
Token ID38911
Feature activation+2.84e-02

Pos logit contributions
ths+0.181
agg+0.177
eking+0.172
aman+0.171
Kevin+0.158
Neg logit contributions
.-0.174
."-0.158
 He-0.139
 like-0.136
 towards-0.135
Token for
Token ID329
Feature activation-3.98e-03

Pos logit contributions
ths+0.069
agg+0.067
eking+0.066
aman+0.064
Kevin+0.062
Neg logit contributions
.-0.025
ashes-0.025
."-0.024
 He-0.021
 rider-0.021
Token their
Token ID511
Feature activation+1.95e-02

Pos logit contributions
.+0.006
."+0.005
 He+0.005
 They+0.004
 play+0.004
Neg logit contributions
ths-0.008
agg-0.008
eking-0.008
aman-0.008
prisingly-0.007
Token brave
Token ID14802
Feature activation-1.57e-02

Pos logit contributions
ths+0.034
agg+0.033
eking+0.033
aman+0.032
prisingly+0.030
Neg logit contributions
.-0.034
."-0.031
ashes-0.029
 He-0.029
 rider-0.028
Token feats
Token ID35664
Feature activation-1.68e-01

Pos logit contributions
ashes+0.023
.+0.022
."+0.022
 Let+0.021
 He+0.021
Neg logit contributions
ths-0.027
agg-0.027
aman-0.025
eking-0.025
Kevin-0.024
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
ashes+0.079
 He+0.046
 rider+0.046
.+0.045
."+0.044
Neg logit contributions
ths-0.473
agg-0.462
eking-0.460
aman-0.452
Kevin-0.440
Token<|endoftext|>
Token ID50256
Feature activation+1.04e-01

Pos logit contributions
.+0.212
."+0.198
ashes+0.185
 He+0.184
 They+0.177
Neg logit contributions
ths-0.244
agg-0.234
eking-0.232
aman-0.223
prisingly-0.212
TokenOnce
Token ID7454
Feature activation+1.74e-01

Pos logit contributions
agg+0.148
ths+0.141
Jess+0.137
Kevin+0.135
aman+0.134
Neg logit contributions
ashes-0.187
 rider-0.177
powers-0.173
five-0.171
."-0.171
Token upon
Token ID2402
Feature activation+8.44e-02

Pos logit contributions
ths+0.296
eking+0.279
agg+0.251
aman+0.244
prisingly+0.242
Neg logit contributions
.-0.386
."-0.332
 He-0.321
 They-0.300
 play-0.288
Token a
Token ID257
Feature activation-3.21e-02

Pos logit contributions
ths+0.184
agg+0.184
eking+0.179
aman+0.173
Jess+0.170
Neg logit contributions
.-0.096
."-0.090
ashes-0.088
 He-0.079
 rider-0.079
Token "
Token ID366
Feature activation+6.19e-02

Pos logit contributions
ths+0.187
agg+0.181
eking+0.178
aman+0.174
Kevin+0.167
Neg logit contributions
.-0.103
."-0.094
ashes-0.086
 He-0.084
 rider-0.079
TokenBe
Token ID3856
Feature activation+1.60e-01

Pos logit contributions
ths+0.142
agg+0.141
eking+0.138
aman+0.132
Kevin+0.128
Neg logit contributions
.-0.073
."-0.066
ashes-0.060
 He-0.060
 Let-0.057
Token careful
Token ID8161
Feature activation+3.16e-02

Pos logit contributions
aman+0.299
ths+0.292
agg+0.286
Jess+0.263
Kevin+0.261
Neg logit contributions
.-0.286
."-0.260
 like-0.229
 play-0.226
ashes-0.217
Token,
Token ID11
Feature activation+8.20e-02

Pos logit contributions
ths+0.062
eking+0.059
agg+0.058
aman+0.054
ering+0.054
Neg logit contributions
.-0.042
ashes-0.042
."-0.039
 He-0.039
 rider-0.038
Token Tim
Token ID5045
Feature activation+3.50e-02

Pos logit contributions
ths+0.180
agg+0.176
eking+0.173
aman+0.169
Kevin+0.162
Neg logit contributions
.-0.105
."-0.096
ashes-0.086
 He-0.086
 They-0.081
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
eking+0.087
ths+0.086
ering+0.082
tha+0.080
aman+0.080
Neg logit contributions
ashes-0.029
powers-0.026
five-0.025
 pedals-0.022
 bars-0.019
Token This
Token ID770
Feature activation+2.70e-02

Pos logit contributions
.+0.181
ashes+0.158
."+0.146
 rider+0.143
 towards+0.136
Neg logit contributions
ths-0.377
agg-0.363
eking-0.346
aman-0.345
prisingly-0.344
Token box
Token ID3091
Feature activation+3.70e-03

Pos logit contributions
ths+0.051
agg+0.049
eking+0.047
prisingly+0.046
aman+0.046
Neg logit contributions
ashes-0.037
.-0.036
."-0.034
 rider-0.033
 He-0.033
Token may
Token ID743
Feature activation+3.92e-02

Pos logit contributions
ths+0.008
eking+0.008
agg+0.008
aman+0.007
prisingly+0.007
Neg logit contributions
ashes-0.004
.-0.004
five-0.004
 rider-0.004
."-0.004
Token have
Token ID423
Feature activation-2.04e-02

Pos logit contributions
ths+0.067
eking+0.066
agg+0.065
aman+0.061
prisingly+0.058
Neg logit contributions
.-0.059
ashes-0.058
five-0.056
."-0.055
 rider-0.055
Token a
Token ID257
Feature activation-2.89e-02

Pos logit contributions
.+0.028
ashes+0.027
."+0.027
 rider+0.026
 He+0.025
Neg logit contributions
ths-0.038
eking-0.037
agg-0.037
aman-0.035
prisingly-0.034
TokenNo
Token ID2949
Feature activation+8.74e-02

Pos logit contributions
agg+0.123
ths+0.123
eking+0.121
aman+0.113
Kevin+0.110
Neg logit contributions
.-0.087
."-0.080
 He-0.076
ashes-0.074
 rider-0.072
Token,
Token ID11
Feature activation+8.18e-02

Pos logit contributions
ths+0.163
aman+0.153
eking+0.150
agg+0.149
prisingly+0.137
Neg logit contributions
ashes-0.129
.-0.122
."-0.116
 He-0.116
 towards-0.114
Token it
Token ID340
Feature activation+1.89e-02

Pos logit contributions
ths+0.179
agg+0.174
eking+0.171
aman+0.167
Kevin+0.160
Neg logit contributions
.-0.104
."-0.095
ashes-0.087
 He-0.085
 rider-0.080
Token is
Token ID318
Feature activation+5.54e-02

Pos logit contributions
ths+0.040
eking+0.038
aman+0.035
agg+0.035
ering+0.034
Neg logit contributions
ashes-0.023
.-0.022
 He-0.021
five-0.021
 towards-0.021
Token fragile
Token ID21049
Feature activation-1.10e-02

Pos logit contributions
ths+0.085
eking+0.082
aman+0.074
agg+0.074
prisingly+0.073
Neg logit contributions
ashes-0.097
.-0.093
five-0.093
 He-0.090
 Let-0.087
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
five+0.014
ashes+0.013
powers+0.011
 pet+0.011
 stroke+0.010
Neg logit contributions
ths-0.019
ering-0.019
eking-0.018
 done-0.018
 unfortunately-0.018
Token You
Token ID921
Feature activation+2.27e-02

Pos logit contributions
.+0.214
ashes+0.198
 towards+0.176
 rider+0.171
five+0.170
Neg logit contributions
ths-0.319
 unfortunately-0.300
omm-0.300
mmm-0.298
agg-0.297
Token might
Token ID1244
Feature activation+1.50e-02

Pos logit contributions
ths+0.046
eking+0.044
agg+0.043
prisingly+0.042
aman+0.041
Neg logit contributions
.-0.027
ashes-0.026
 He-0.024
."-0.024
five-0.024
Token break
Token ID2270
Feature activation-4.04e-02

Pos logit contributions
eking+0.026
ths+0.026
agg+0.024
aman+0.024
prisingly+0.023
Neg logit contributions
.-0.021
ashes-0.020
 He-0.020
 Let-0.020
five-0.019
Token it
Token ID340
Feature activation+1.92e-02

Pos logit contributions
ashes+0.062
 He+0.057
.+0.057
five+0.056
 rider+0.056
Neg logit contributions
ths-0.072
eking-0.068
agg-0.062
aman-0.062
ering-0.061
Token."
Token ID526
Feature activation-8.94e-02

Pos logit contributions
ths+0.053
eking+0.053
aman+0.050
prisingly+0.050
agg+0.050
Neg logit contributions
ashes-0.007
five-0.006
 rider-0.005
 He-0.005
.-0.005
Token is
Token ID318
Feature activation+5.87e-02

Pos logit contributions
ths+0.160
eking+0.152
agg+0.150
aman+0.142
ering+0.141
Neg logit contributions
ashes-0.103
.-0.095
five-0.092
 towards-0.089
 rider-0.089
Token a
Token ID257
Feature activation-3.01e-02

Pos logit contributions
ths+0.099
agg+0.095
eking+0.092
aman+0.090
Kevin+0.085
Neg logit contributions
.-0.107
."-0.100
ashes-0.093
 He-0.093
 They-0.089
Token vest
Token ID19750
Feature activation-7.09e-02

Pos logit contributions
.+0.034
ashes+0.032
."+0.031
 They+0.027
 He+0.027
Neg logit contributions
ths-0.067
agg-0.065
eking-0.064
aman-0.063
Kevin-0.061
Token,
Token ID11
Feature activation+8.33e-02

Pos logit contributions
ashes+0.096
 pedals+0.083
 spots+0.080
powers+0.080
irms+0.078
Neg logit contributions
ths-0.124
lf-0.117
 unfortunately-0.114
eking-0.110
 done-0.109
Token Tim
Token ID5045
Feature activation+3.95e-02

Pos logit contributions
ths+0.196
agg+0.193
eking+0.189
aman+0.181
Kevin+0.180
Neg logit contributions
.-0.100
."-0.091
 He-0.082
 They-0.076
 Let-0.075
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
ma+0.092
aman+0.091
eking+0.090
ths+0.090
tha+0.087
Neg logit contributions
ashes-0.036
powers-0.031
five-0.029
 towards-0.024
 pedals-0.024
Token You
Token ID921
Feature activation+2.62e-02

Pos logit contributions
.+0.185
ashes+0.184
 rider+0.152
five+0.149
."+0.146
Neg logit contributions
ths-0.346
agg-0.332
 unfortunately-0.330
prisingly-0.325
mmm-0.325
Token wear
Token ID5806
Feature activation-9.57e-02

Pos logit contributions
ths+0.050
eking+0.049
agg+0.049
prisingly+0.047
Kevin+0.046
Neg logit contributions
ashes-0.034
.-0.032
 towards-0.029
five-0.029
."-0.029
Token it
Token ID340
Feature activation+1.99e-02

Pos logit contributions
ashes+0.163
.+0.160
 rider+0.150
."+0.150
ny+0.149
Neg logit contributions
ths-0.148
eking-0.143
agg-0.136
aman-0.127
prisingly-0.126
Token on
Token ID319
Feature activation-5.81e-02

Pos logit contributions
ths+0.044
eking+0.043
agg+0.042
aman+0.040
prisingly+0.040
Neg logit contributions
.-0.020
ashes-0.020
."-0.018
 He-0.018
five-0.017
Token your
Token ID534
Feature activation-4.62e-03

Pos logit contributions
ashes+0.104
.+0.098
 rider+0.094
 He+0.092
 Let+0.092
Neg logit contributions
ths-0.086
eking-0.084
agg-0.083
aman-0.082
Kevin-0.077
Token seat
Token ID5852
Feature activation-3.87e-02

Pos logit contributions
.+0.036
."+0.036
ashes+0.035
 Let+0.033
 He+0.033
Neg logit contributions
ths-0.063
aman-0.061
agg-0.060
eking-0.058
str-0.054
Token on
Token ID319
Feature activation-5.85e-02

Pos logit contributions
powers+0.049
ashes+0.048
 He+0.045
."+0.044
five+0.044
Neg logit contributions
eking-0.079
ths-0.078
ering-0.071
aman-0.070
 unfortunately-0.068
Token the
Token ID262
Feature activation-3.79e-02

Pos logit contributions
.+0.081
ashes+0.081
."+0.078
 He+0.073
 Let+0.073
Neg logit contributions
ths-0.114
agg-0.108
aman-0.107
eking-0.104
Jess-0.100
Token see
Token ID766
Feature activation+1.24e-02

Pos logit contributions
ashes+0.057
 They+0.055
powers+0.053
 Let+0.053
.+0.053
Neg logit contributions
ths-0.062
eking-0.062
aman-0.062
agg-0.058
str-0.056
Token-
Token ID12
Feature activation+2.45e-02

Pos logit contributions
ths+0.029
eking+0.029
agg+0.028
aman+0.028
Jane+0.028
Neg logit contributions
ashes-0.012
powers-0.010
 rider-0.009
ny-0.009
eer-0.009
Tokensaw
Token ID43439
Feature activation-1.67e-01

Pos logit contributions
ths+0.045
agg+0.043
eking+0.043
aman+0.043
Jane+0.042
Neg logit contributions
.-0.035
ashes-0.033
."-0.033
 He-0.031
 They-0.031
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
powers+0.068
ashes+0.065
 He+0.049
 rider+0.047
 pedal+0.043
Neg logit contributions
ths-0.453
eking-0.448
aman-0.430
ering-0.427
 unfortunately-0.423
Token She
Token ID1375
Feature activation-3.09e-02

Pos logit contributions
ashes+0.194
 rider+0.189
.+0.177
five+0.177
."+0.175
Neg logit contributions
ths-0.262
agg-0.262
aman-0.259
omm-0.244
mber-0.234
Token ran
Token ID4966
Feature activation-1.25e-01

Pos logit contributions
.+0.036
."+0.030
 He+0.029
 bar+0.026
 They+0.025
Neg logit contributions
ths-0.072
agg-0.071
eking-0.071
aman-0.070
prisingly-0.068
Token to
Token ID284
Feature activation-9.06e-04

Pos logit contributions
.+0.111
."+0.106
ashes+0.095
eer+0.087
 Let+0.086
Neg logit contributions
ths-0.302
agg-0.284
eking-0.283
aman-0.281
prisingly-0.270
Token it
Token ID340
Feature activation+2.08e-02

Pos logit contributions
.+0.001
."+0.001
ashes+0.001
 He+0.001
 rider+0.001
Neg logit contributions
ths-0.002
agg-0.002
eking-0.002
aman-0.002
Kevin-0.002
Token "
Token ID366
Feature activation+5.95e-02

Pos logit contributions
.+0.185
 rider+0.175
."+0.172
ashes+0.167
eer+0.166
Neg logit contributions
agg-0.307
aman-0.301
ths-0.298
Kevin-0.276
Jess-0.274
TokenBe
Token ID3856
Feature activation+1.61e-01

Pos logit contributions
ths+0.105
agg+0.101
eking+0.099
aman+0.095
Kevin+0.090
Neg logit contributions
.-0.101
."-0.095
ashes-0.090
 He-0.088
 rider-0.085
Token careful
Token ID8161
Feature activation+3.19e-02

Pos logit contributions
aman+0.304
ths+0.296
agg+0.282
Jess+0.266
Kevin+0.266
Neg logit contributions
.-0.282
."-0.253
 like-0.220
 fur-0.211
ashes-0.206
Token,
Token ID11
Feature activation+8.20e-02

Pos logit contributions
ths+0.070
agg+0.068
eking+0.067
aman+0.066
Kevin+0.063
Neg logit contributions
.-0.041
."-0.037
ashes-0.033
 He-0.033
 rider-0.031
Token Sara
Token ID24799
Feature activation+3.79e-02

Pos logit contributions
ths+0.191
eking+0.187
agg+0.185
prisingly+0.176
Kevin+0.176
Neg logit contributions
.-0.099
."-0.093
 He-0.076
 They-0.075
 bar-0.074
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
ths+0.082
agg+0.079
eking+0.078
aman+0.077
Jess+0.076
Neg logit contributions
ashes-0.043
five-0.036
powers-0.036
 pedals-0.034
 pedal-0.033
Token The
Token ID383
Feature activation-1.53e-03

Pos logit contributions
.+0.191
."+0.163
ashes+0.162
 rider+0.158
 towards+0.152
Neg logit contributions
ths-0.371
agg-0.363
aman-0.347
eking-0.346
Jess-0.333
Token onion
Token ID21670
Feature activation+5.20e-03

Pos logit contributions
.+0.002
."+0.002
 He+0.002
ashes+0.002
 They+0.002
Neg logit contributions
ths-0.003
agg-0.003
eking-0.003
aman-0.003
prisingly-0.003
Token can
Token ID460
Feature activation+3.89e-02

Pos logit contributions
ths+0.012
agg+0.011
eking+0.011
aman+0.011
prisingly+0.010
Neg logit contributions
.-0.006
."-0.005
ashes-0.005
 He-0.005
 rider-0.005
Token make
Token ID787
Feature activation-4.40e-02

Pos logit contributions
ths+0.083
agg+0.081
eking+0.079
aman+0.077
Kevin+0.074
Neg logit contributions
.-0.051
."-0.047
ashes-0.043
 He-0.042
 rider-0.040
Token your
Token ID534
Feature activation-3.87e-03

Pos logit contributions
.+0.067
."+0.062
 He+0.054
ashes+0.053
 They+0.052
Neg logit contributions
ths-0.089
agg-0.086
eking-0.084
aman-0.084
Kevin-0.080
Token,
Token ID11
Feature activation+8.49e-02

Pos logit contributions
powers+0.146
ashes+0.139
eer+0.129
 Let+0.125
five+0.123
Neg logit contributions
ths-0.208
aman-0.205
eking-0.197
agg-0.193
 unfortunately-0.188
Token slide
Token ID10649
Feature activation-6.03e-02

Pos logit contributions
ths+0.185
agg+0.180
eking+0.174
aman+0.171
prisingly+0.164
Neg logit contributions
.-0.114
."-0.104
ashes-0.095
 He-0.094
 They-0.089
Token and
Token ID290
Feature activation+4.41e-02

Pos logit contributions
ashes+0.077
powers+0.075
five+0.071
eer+0.070
."+0.070
Neg logit contributions
ths-0.120
aman-0.115
eking-0.111
agg-0.107
ering-0.105
Token see
Token ID766
Feature activation+1.04e-02

Pos logit contributions
ths+0.097
eking+0.095
agg+0.094
aman+0.090
Jess+0.089
Neg logit contributions
.-0.045
."-0.043
ashes-0.041
 He-0.038
powers-0.037
Token-
Token ID12
Feature activation+2.37e-02

Pos logit contributions
ths+0.014
aman+0.013
eking+0.013
agg+0.013
 exactly+0.012
Neg logit contributions
ashes-0.021
ny-0.020
powers-0.019
five-0.019
 Let-0.018
Tokensaw
Token ID43439
Feature activation-1.67e-01

Pos logit contributions
ths+0.051
agg+0.050
eking+0.049
aman+0.048
Kevin+0.046
Neg logit contributions
.-0.030
."-0.028
ashes-0.026
 He-0.025
 rider-0.024
Token.
Token ID13
Feature activation-1.46e-01

Pos logit contributions
powers+0.113
ashes+0.108
eer+0.101
ny+0.090
ray+0.090
Neg logit contributions
ths-0.401
eking-0.383
aman-0.368
ering-0.367
 exactly-0.358
Token
Token ID198
Feature activation+1.41e-01

Pos logit contributions
.+0.160
."+0.143
ashes+0.130
 He+0.128
 They+0.119
Neg logit contributions
ths-0.349
agg-0.339
eking-0.336
aman-0.326
Kevin-0.314
Token
Token ID198
Feature activation+1.41e-01

Pos logit contributions
ths+0.400
eking+0.392
agg+0.365
aman+0.358
ering+0.350
Neg logit contributions
.-0.139
."-0.112
 He-0.105
 They-0.100
 play-0.080
TokenBut
Token ID1537
Feature activation+9.36e-02

Pos logit contributions
ths+0.246
eking+0.242
agg+0.239
aman+0.222
Kevin+0.209
Neg logit contributions
.-0.249
."-0.227
 He-0.215
 They-0.211
 play-0.209
Token when
Token ID618
Feature activation-2.77e-02

Pos logit contributions
agg+0.223
eking+0.215
Kevin+0.211
ths+0.211
Jess+0.205
Neg logit contributions
.-0.120
."-0.093
 play-0.088
 like-0.086
 He-0.085
Token down
Token ID866
Feature activation-1.21e-01

Pos logit contributions
ths+0.119
eking+0.110
aman+0.107
agg+0.106
tha+0.104
Neg logit contributions
.-0.037
."-0.036
ashes-0.034
powers-0.032
eer-0.027
Token on
Token ID319
Feature activation-5.77e-02

Pos logit contributions
eer+0.119
ashes+0.117
powers+0.112
 rider+0.110
 pads+0.110
Neg logit contributions
ths-0.266
agg-0.254
aman-0.247
eking-0.245
Jess-0.237
Token the
Token ID262
Feature activation-3.58e-02

Pos logit contributions
.+0.080
ashes+0.078
."+0.078
 He+0.074
 rider+0.072
Neg logit contributions
ths-0.114
agg-0.107
aman-0.105
eking-0.104
Jess-0.099
Token see
Token ID766
Feature activation+1.21e-02

Pos logit contributions
ashes+0.041
.+0.039
 Let+0.039
."+0.038
 They+0.038
Neg logit contributions
ths-0.075
eking-0.075
agg-0.071
aman-0.070
ering-0.066
Token-
Token ID12
Feature activation+2.43e-02

Pos logit contributions
ths+0.024
agg+0.023
aman+0.022
eking+0.022
Jess+0.021
Neg logit contributions
ashes-0.016
ny-0.014
powers-0.014
 rider-0.014
eer-0.014
Tokensaw
Token ID43439
Feature activation-1.67e-01

Pos logit contributions
ths+0.048
agg+0.047
eking+0.046
aman+0.045
Jess+0.044
Neg logit contributions
.-0.032
."-0.030
ashes-0.029
 He-0.027
 They-0.027
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
ashes+0.066
powers+0.061
 He+0.052
."+0.051
 Let+0.048
Neg logit contributions
ths-0.465
eking-0.444
aman-0.434
agg-0.430
ering-0.427
Token
Token ID220
Feature activation+1.83e-01

Pos logit contributions
.+0.272
."+0.259
ashes+0.250
 rider+0.249
 He+0.235
Neg logit contributions
ths-0.197
agg-0.192
aman-0.181
eking-0.179
Jess-0.167
Token
Token ID198
Feature activation+1.47e-01

Pos logit contributions
ths+0.417
agg+0.401
eking+0.398
aman+0.386
Kevin+0.370
Neg logit contributions
.-0.228
."-0.207
 He-0.186
ashes-0.184
 They-0.178
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
ths+0.422
eking+0.410
agg+0.389
aman+0.386
ering+0.370
Neg logit contributions
.-0.143
."-0.126
 They-0.109
 He-0.104
 Let-0.081
TokenAfter
Token ID3260
Feature activation+5.81e-02

Pos logit contributions
ths+0.231
agg+0.229
eking+0.226
aman+0.214
Kevin+0.200
Neg logit contributions
.-0.279
."-0.264
 They-0.246
ashes-0.242
 He-0.242
TokenMax
Token ID11518
Feature activation+2.37e-02

Pos logit contributions
ths+0.113
agg+0.108
aman+0.104
eking+0.104
Jess+0.100
Neg logit contributions
.-0.102
."-0.095
ashes-0.090
 He-0.084
 towards-0.083
Token,
Token ID11
Feature activation+8.25e-02

Pos logit contributions
ths+0.036
agg+0.032
eking+0.031
aman+0.031
tha+0.030
Neg logit contributions
ashes-0.042
five-0.038
powers-0.037
 bars-0.037
 pedals-0.036
Token I
Token ID314
Feature activation-7.45e-02

Pos logit contributions
ths+0.176
agg+0.171
eking+0.168
aman+0.163
Kevin+0.157
Neg logit contributions
.-0.110
."-0.101
ashes-0.093
 He-0.091
 rider-0.086
Token am
Token ID716
Feature activation+7.56e-02

Pos logit contributions
.+0.078
."+0.072
 He+0.069
ashes+0.068
 towards+0.065
Neg logit contributions
agg-0.164
ths-0.162
eking-0.159
prisingly-0.154
aman-0.153
Token cold
Token ID4692
Feature activation-1.66e-02

Pos logit contributions
ths+0.143
agg+0.136
aman+0.132
eking+0.131
Kevin+0.124
Neg logit contributions
.-0.129
."-0.121
 He-0.108
ashes-0.107
 play-0.103
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
five+0.015
powers+0.014
ashes+0.013
 pedals+0.012
 name+0.012
Neg logit contributions
ths-0.037
eking-0.036
agg-0.035
aman-0.034
ering-0.033
Token Let
Token ID3914
Feature activation-4.68e-02

Pos logit contributions
.+0.226
ashes+0.222
 bars+0.203
 towards+0.186
v+0.184
Neg logit contributions
 unfortunately-0.283
agg-0.278
ths-0.270
mmm-0.265
hh-0.263
Token's
Token ID338
Feature activation+1.88e-02

Pos logit contributions
.+0.048
."+0.043
 He+0.036
ashes+0.036
 They+0.033
Neg logit contributions
ths-0.116
agg-0.114
eking-0.112
aman-0.109
Kevin-0.106
Token sit
Token ID1650
Feature activation-9.04e-03

Pos logit contributions
ths+0.041
agg+0.041
eking+0.040
aman+0.039
 unfortunately+0.037
Neg logit contributions
ashes-0.018
powers-0.017
five-0.017
.-0.017
 towards-0.016
Token closer
Token ID5699
Feature activation+9.23e-03

Pos logit contributions
.+0.009
."+0.008
ashes+0.008
 He+0.007
five+0.007
Neg logit contributions
ths-0.022
eking-0.021
agg-0.021
aman-0.020
prisingly-0.020
Token to
Token ID284
Feature activation-1.58e-03

Pos logit contributions
ths+0.022
agg+0.021
eking+0.021
aman+0.020
prisingly+0.020
Neg logit contributions
ashes-0.007
.-0.007
 rider-0.007
 He-0.007
 pedal-0.006
Token "
Token ID366
Feature activation+5.86e-02

Pos logit contributions
ths+0.183
agg+0.178
eking+0.175
aman+0.171
Kevin+0.164
Neg logit contributions
.-0.103
."-0.094
ashes-0.086
 He-0.084
 rider-0.079
TokenMy
Token ID3666
Feature activation+1.92e-02

Pos logit contributions
agg+0.113
ths+0.112
eking+0.110
aman+0.103
prisingly+0.099
Neg logit contributions
.-0.090
."-0.084
ashes-0.080
 He-0.078
 They-0.076
Token block
Token ID2512
Feature activation-1.37e-02

Pos logit contributions
ths+0.039
agg+0.037
eking+0.036
prisingly+0.034
iter+0.033
Neg logit contributions
ashes-0.023
.-0.022
ny-0.021
 rider-0.020
 towards-0.020
Token is
Token ID318
Feature activation+5.65e-02

Pos logit contributions
ashes+0.017
.+0.015
five+0.015
 towards+0.015
."+0.014
Neg logit contributions
ths-0.028
eking-0.025
agg-0.024
prisingly-0.024
ering-0.024
Token better
Token ID1365
Feature activation+3.86e-02

Pos logit contributions
ths+0.106
agg+0.101
eking+0.100
aman+0.096
prisingly+0.092
Neg logit contributions
.-0.088
."-0.082
ashes-0.079
 He-0.077
 rider-0.074
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
ths+0.089
eking+0.080
ering+0.078
prisingly+0.077
agg+0.077
Neg logit contributions
 pedals-0.036
 He-0.035
ashes-0.034
 bars-0.033
five-0.033
Token It
Token ID632
Feature activation+3.39e-02

Pos logit contributions
.+0.221
ashes+0.210
 bars+0.193
 rider+0.191
 towards+0.188
Neg logit contributions
ths-0.302
mmm-0.295
omm-0.293
agg-0.286
 unfortunately-0.283
Token is
Token ID318
Feature activation+5.81e-02

Pos logit contributions
ths+0.073
eking+0.068
agg+0.065
prisingly+0.064
aman+0.063
Neg logit contributions
.-0.039
ashes-0.038
five-0.035
."-0.034
 towards-0.034
Token red
Token ID2266
Feature activation-1.10e-02

Pos logit contributions
ths+0.106
agg+0.102
eking+0.101
aman+0.097
prisingly+0.092
Neg logit contributions
.-0.093
."-0.087
ashes-0.084
 He-0.081
 rider-0.078
Token like
Token ID588
Feature activation-4.64e-03

Pos logit contributions
five+0.016
powers+0.015
ashes+0.015
 pet+0.014
 rider+0.013
Neg logit contributions
ths-0.016
eking-0.015
ering-0.015
aman-0.015
omm-0.015
Token fire
Token ID2046
Feature activation+1.31e-02

Pos logit contributions
.+0.006
."+0.006
ashes+0.005
 He+0.005
 rider+0.005
Neg logit contributions
ths-0.010
agg-0.009
eking-0.009
aman-0.009
Kevin-0.009
Tokent
Token ID83
Feature activation+1.11e-01

Pos logit contributions
ths+0.005
agg+0.004
eking+0.004
aman+0.004
Jess+0.004
Neg logit contributions
.-0.005
."-0.005
 He-0.004
 rider-0.004
ashes-0.004
Token about
Token ID546
Feature activation+4.61e-02

Pos logit contributions
ths+0.248
agg+0.241
eking+0.237
aman+0.231
Kevin+0.222
Neg logit contributions
.-0.135
."-0.123
ashes-0.112
 He-0.110
 rider-0.103
Token the
Token ID262
Feature activation-3.47e-02

Pos logit contributions
ths+0.083
agg+0.082
eking+0.078
aman+0.076
prisingly+0.074
Neg logit contributions
.-0.078
."-0.072
 He-0.065
ashes-0.064
 They-0.062
Token see
Token ID766
Feature activation+1.24e-02

Pos logit contributions
.+0.046
."+0.043
ashes+0.041
 He+0.040
 They+0.039
Neg logit contributions
ths-0.072
eking-0.068
agg-0.068
aman-0.066
Kevin-0.062
Token-
Token ID12
Feature activation+2.39e-02

Pos logit contributions
ths+0.027
eking+0.025
agg+0.025
aman+0.025
Jess+0.023
Neg logit contributions
ashes-0.015
.-0.014
."-0.014
 He-0.013
five-0.012
Tokensaw
Token ID43439
Feature activation-1.67e-01

Pos logit contributions
ths+0.048
agg+0.046
eking+0.045
aman+0.044
Kevin+0.042
Neg logit contributions
.-0.035
."-0.032
ashes-0.030
 He-0.029
 rider-0.028
Token and
Token ID290
Feature activation+4.58e-02

Pos logit contributions
ashes+0.172
."+0.166
.+0.166
 He+0.153
powers+0.151
Neg logit contributions
ths-0.372
eking-0.351
agg-0.345
aman-0.344
 unfortunately-0.327
Token how
Token ID703
Feature activation-5.66e-02

Pos logit contributions
ths+0.081
agg+0.078
eking+0.076
aman+0.074
Kevin+0.070
Neg logit contributions
.-0.078
."-0.073
ashes-0.068
 He-0.067
 They-0.064
Token much
Token ID881
Feature activation-8.31e-03

Pos logit contributions
.+0.100
."+0.094
ashes+0.088
 He+0.087
 They+0.083
Neg logit contributions
ths-0.097
agg-0.093
eking-0.091
aman-0.089
Kevin-0.084
Token fun
Token ID1257
Feature activation+2.23e-02

Pos logit contributions
.+0.014
."+0.013
ashes+0.013
 He+0.012
 Let+0.012
Neg logit contributions
ths-0.015
agg-0.014
eking-0.013
aman-0.013
Jess-0.012
Token it
Token ID340
Feature activation+2.25e-02

Pos logit contributions
ths+0.031
agg+0.027
eking+0.026
aman+0.025
Jess+0.024
Neg logit contributions
ashes-0.044
ny-0.042
.-0.041
."-0.041
 He-0.041
Token Leo
Token ID19632
Feature activation+4.63e-02

Pos logit contributions
ths+0.175
eking+0.170
agg+0.170
aman+0.165
prisingly+0.153
Neg logit contributions
.-0.145
."-0.134
 He-0.127
ashes-0.122
 They-0.120
Token continued
Token ID3767
Feature activation-9.97e-02

Pos logit contributions
ths+0.098
agg+0.095
eking+0.094
aman+0.091
Kevin+0.087
Neg logit contributions
.-0.062
."-0.057
ashes-0.052
 He-0.052
 rider-0.049
Token to
Token ID284
Feature activation+2.14e-03

Pos logit contributions
.+0.085
."+0.077
ashes+0.069
 He+0.064
 rider+0.062
Neg logit contributions
ths-0.256
agg-0.247
eking-0.244
aman-0.237
Kevin-0.231
Token perform
Token ID1620
Feature activation-5.16e-02

Pos logit contributions
ths+0.005
agg+0.005
eking+0.005
aman+0.005
Kevin+0.004
Neg logit contributions
.-0.002
."-0.002
ashes-0.002
 He-0.002
 rider-0.002
Token amazing
Token ID4998
Feature activation+5.12e-02

Pos logit contributions
.+0.057
."+0.053
ashes+0.050
 He+0.047
 Let+0.046
Neg logit contributions
ths-0.118
agg-0.115
eking-0.113
aman-0.109
Kevin-0.106
Token feats
Token ID35664
Feature activation-1.67e-01

Pos logit contributions
ths+0.099
agg+0.093
eking+0.088
ering+0.084
 sudden+0.081
Neg logit contributions
."-0.070
ashes-0.069
 Let-0.069
.-0.069
 He-0.067
Token for
Token ID329
Feature activation-4.43e-03

Pos logit contributions
ashes+0.185
."+0.151
 Let+0.148
ny+0.147
 They+0.146
Neg logit contributions
ths-0.360
agg-0.349
eking-0.344
aman-0.329
prisingly-0.328
Token his
Token ID465
Feature activation-1.16e-02

Pos logit contributions
.+0.006
."+0.005
 He+0.004
 play+0.004
 bar+0.004
Neg logit contributions
aman-0.010
ths-0.010
agg-0.010
eking-0.010
str-0.009
Token friends
Token ID2460
Feature activation-7.71e-02

Pos logit contributions
.+0.018
."+0.017
ashes+0.017
 He+0.016
 They+0.016
Neg logit contributions
ths-0.021
agg-0.021
eking-0.020
aman-0.019
Kevin-0.018
Token in
Token ID287
Feature activation-5.34e-02

Pos logit contributions
ashes+0.068
powers+0.053
atters+0.053
 Let+0.053
five+0.052
Neg logit contributions
ths-0.180
eking-0.170
Kevin-0.169
agg-0.167
Jess-0.164
Token the
Token ID262
Feature activation-3.05e-02

Pos logit contributions
.+0.070
."+0.064
ashes+0.059
 He+0.058
 rider+0.055
Neg logit contributions
ths-0.115
agg-0.111
eking-0.109
aman-0.107
Kevin-0.102
Token to
Token ID284
Feature activation-4.38e-03

Pos logit contributions
.+0.069
ashes+0.066
 rider+0.065
 He+0.063
."+0.061
Neg logit contributions
ths-0.202
eking-0.192
agg-0.189
prisingly-0.181
aman-0.180
Token make
Token ID787
Feature activation-4.66e-02

Pos logit contributions
.+0.005
."+0.005
ashes+0.005
 He+0.005
 rider+0.004
Neg logit contributions
ths-0.010
agg-0.009
eking-0.009
aman-0.009
Kevin-0.009
Token a
Token ID257
Feature activation-3.28e-02

Pos logit contributions
.+0.066
."+0.061
ashes+0.052
 He+0.051
 They+0.050
Neg logit contributions
ths-0.098
agg-0.094
eking-0.094
aman-0.091
Kevin-0.087
Token delicious
Token ID12625
Feature activation+4.06e-02

Pos logit contributions
.+0.055
."+0.051
ashes+0.048
 He+0.046
 rider+0.045
Neg logit contributions
ths-0.059
agg-0.057
eking-0.056
aman-0.054
Kevin-0.051
Token cake
Token ID12187
Feature activation+2.81e-02

Pos logit contributions
ths+0.068
agg+0.065
eking+0.064
aman+0.062
Kevin+0.058
Neg logit contributions
.-0.072
."-0.068
ashes-0.064
 He-0.063
 rider-0.061
Token.
Token ID13
Feature activation-1.66e-01

Pos logit contributions
ths+0.067
agg+0.064
aman+0.062
eking+0.062
prisingly+0.060
Neg logit contributions
ashes-0.025
 He-0.023
powers-0.022
.-0.022
 pedal-0.021
Token I
Token ID314
Feature activation-7.37e-02

Pos logit contributions
.+0.175
ashes+0.152
."+0.145
 rider+0.135
powers+0.130
Neg logit contributions
ths-0.386
agg-0.375
aman-0.364
prisingly-0.355
Jess-0.354
Token can
Token ID460
Feature activation+3.73e-02

Pos logit contributions
.+0.085
."+0.077
ashes+0.072
 He+0.070
 rider+0.067
Neg logit contributions
ths-0.165
agg-0.162
eking-0.158
aman-0.154
prisingly-0.150
Token't
Token ID470
Feature activation+9.43e-02

Pos logit contributions
ths+0.082
agg+0.080
eking+0.078
aman+0.076
prisingly+0.073
Neg logit contributions
.-0.044
."-0.039
ashes-0.039
 He-0.037
 rider-0.037
Token wait
Token ID4043
Feature activation+2.97e-02

Pos logit contributions
ths+0.185
agg+0.180
eking+0.175
aman+0.168
prisingly+0.164
Neg logit contributions
.-0.131
."-0.122
ashes-0.121
 He-0.119
 rider-0.115
Token to
Token ID284
Feature activation-3.47e-03

Pos logit contributions
ths+0.073
agg+0.071
eking+0.070
aman+0.068
prisingly+0.066
Neg logit contributions
.-0.025
ashes-0.023
 rider-0.022
 He-0.022
."-0.022
Token their
Token ID511
Feature activation+2.11e-02

Pos logit contributions
.+0.027
."+0.025
ashes+0.024
 He+0.023
 rider+0.022
Neg logit contributions
ths-0.045
agg-0.044
eking-0.043
aman-0.042
Kevin-0.040
Token tasty
Token ID25103
Feature activation+3.46e-02

Pos logit contributions
ths+0.042
agg+0.040
eking+0.040
aman+0.039
Kevin+0.037
Neg logit contributions
.-0.032
."-0.029
ashes-0.027
 He-0.026
 They-0.025
Token home
Token ID1363
Feature activation-1.22e-02

Pos logit contributions
ths+0.062
agg+0.062
eking+0.058
aman+0.054
ering+0.053
Neg logit contributions
 He-0.048
.-0.047
 rider-0.046
 Let-0.046
."-0.045
Token.
Token ID13
Feature activation-1.37e-01

Pos logit contributions
ashes+0.007
 He+0.006
five+0.005
 Let+0.005
 pedal+0.005
Neg logit contributions
ths-0.033
eking-0.032
agg-0.031
ering-0.030
prisingly-0.030
Token
Token ID198
Feature activation+1.51e-01

Pos logit contributions
ashes+0.179
 rider+0.166
 pedal+0.166
.+0.163
 towards+0.161
Neg logit contributions
agg-0.258
ths-0.248
Jess-0.236
aman-0.236
Fore-0.232
Token
Token ID198
Feature activation+1.50e-01

Pos logit contributions
ths+0.305
eking+0.289
aman+0.281
agg+0.277
prisingly+0.253
Neg logit contributions
.-0.251
."-0.225
 He-0.214
 They-0.204
 play-0.200
TokenThen
Token ID6423
Feature activation+4.36e-02

Pos logit contributions
eking+0.283
ths+0.277
agg+0.274
aman+0.270
tha+0.249
Neg logit contributions
.-0.245
."-0.226
 He-0.221
 They-0.209
 play-0.205
Token one
Token ID530
Feature activation-1.79e-02

Pos logit contributions
ths+0.097
agg+0.095
eking+0.094
aman+0.092
Kevin+0.087
Neg logit contributions
.-0.056
."-0.050
 He-0.045
ashes-0.044
 They-0.042
Token day
Token ID1110
Feature activation+4.30e-02

Pos logit contributions
.+0.028
."+0.027
ashes+0.025
 He+0.024
 They+0.024
Neg logit contributions
ths-0.033
agg-0.032
eking-0.031
aman-0.030
prisingly-0.029
Token,
Token ID11
Feature activation+9.17e-02

Pos logit contributions
ths+0.085
agg+0.084
eking+0.079
aman+0.078
Jess+0.076
Neg logit contributions
.-0.059
."-0.056
ashes-0.056
 rider-0.051
 He-0.050
Token some
Token ID617
Feature activation-2.08e-02

Pos logit contributions
ths+0.197
agg+0.191
eking+0.186
aman+0.182
prisingly+0.175
Neg logit contributions
.-0.117
."-0.109
ashes-0.104
 He-0.097
 rider-0.094
Token using
Token ID1262
Feature activation-7.82e-02

Pos logit contributions
.+0.043
."+0.041
ashes+0.039
 He+0.038
 rider+0.037
Neg logit contributions
ths-0.044
agg-0.042
eking-0.041
aman-0.040
Kevin-0.038
Token the
Token ID262
Feature activation-3.32e-02

Pos logit contributions
.+0.110
."+0.104
ashes+0.102
 He+0.096
 rider+0.095
Neg logit contributions
ths-0.153
agg-0.146
eking-0.145
aman-0.141
prisingly-0.134
Token tools
Token ID4899
Feature activation-7.60e-02

Pos logit contributions
.+0.043
."+0.040
ashes+0.037
 He+0.035
 rider+0.034
Neg logit contributions
ths-0.072
agg-0.069
eking-0.069
aman-0.066
Kevin-0.064
Token.
Token ID13
Feature activation-1.41e-01

Pos logit contributions
ashes+0.044
 rider+0.038
."+0.035
five+0.034
 Let+0.033
Neg logit contributions
ths-0.201
eking-0.194
aman-0.185
ering-0.185
agg-0.183
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
.+0.202
 He+0.182
."+0.181
 They+0.174
 Let+0.163
Neg logit contributions
eking-0.293
ths-0.288
agg-0.287
aman-0.269
prisingly-0.262
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
eking+0.409
ths+0.398
agg+0.380
aman+0.373
ering+0.365
Neg logit contributions
.-0.139
 He-0.115
."-0.110
 They-0.105
 Let-0.078
TokenSteve
Token ID19206
Feature activation+3.39e-02

Pos logit contributions
eking+0.208
agg+0.204
ths+0.185
aman+0.183
ering+0.169
Neg logit contributions
.-0.307
 He-0.285
."-0.279
 They-0.275
 towards-0.264
Token worked
Token ID3111
Feature activation+2.48e-02

Pos logit contributions
ths+0.065
agg+0.061
eking+0.058
aman+0.057
prisingly+0.055
Neg logit contributions
.-0.050
ashes-0.049
."-0.049
 He-0.043
 towards-0.043
Token on
Token ID319
Feature activation-5.64e-02

Pos logit contributions
agg+0.052
ths+0.050
aman+0.049
eking+0.049
Jess+0.048
Neg logit contributions
.-0.039
."-0.033
 He-0.031
 They-0.028
 towards-0.028
Token the
Token ID262
Feature activation-3.36e-02

Pos logit contributions
.+0.073
."+0.064
 He+0.059
ashes+0.056
 They+0.055
Neg logit contributions
ths-0.125
agg-0.123
eking-0.120
aman-0.117
Kevin-0.113
Token black
Token ID2042
Feature activation-3.63e-02

Pos logit contributions
.+0.044
."+0.041
ashes+0.039
 He+0.037
 rider+0.036
Neg logit contributions
ths-0.071
eking-0.068
agg-0.068
aman-0.065
Kevin-0.063
Token had
Token ID550
Feature activation-2.11e-02

Pos logit contributions
ashes+0.008
.+0.008
."+0.008
five+0.007
powers+0.007
Neg logit contributions
ths-0.014
eking-0.013
agg-0.013
aman-0.013
Jess-0.012
Token ever
Token ID1683
Feature activation+5.54e-02

Pos logit contributions
.+0.034
."+0.032
ashes+0.031
 He+0.030
 rider+0.029
Neg logit contributions
ths-0.038
agg-0.037
eking-0.036
aman-0.035
Kevin-0.033
Token seen
Token ID1775
Feature activation+1.55e-02

Pos logit contributions
ths+0.101
agg+0.097
eking+0.093
aman+0.092
prisingly+0.087
Neg logit contributions
.-0.094
."-0.087
ashes-0.080
 He-0.079
 towards-0.076
Token.
Token ID13
Feature activation-1.41e-01

Pos logit contributions
ths+0.036
eking+0.036
agg+0.035
aman+0.034
ering+0.033
Neg logit contributions
ashes-0.015
 They-0.013
 He-0.012
.-0.012
powers-0.012
Token
Token ID220
Feature activation+1.83e-01

Pos logit contributions
.+0.208
ashes+0.195
."+0.194
 rider+0.183
five+0.168
Neg logit contributions
ths-0.261
agg-0.259
aman-0.247
eking-0.239
Kevin-0.239
Token
Token ID198
Feature activation+1.48e-01

Pos logit contributions
ths+0.383
agg+0.374
eking+0.365
aman+0.357
Kevin+0.343
Neg logit contributions
.-0.240
."-0.222
ashes-0.208
 He-0.198
 rider-0.195
Token
Token ID198
Feature activation+1.47e-01

Pos logit contributions
ths+0.396
eking+0.383
agg+0.366
aman+0.364
ering+0.344
Neg logit contributions
.-0.153
."-0.137
 He-0.127
 They-0.111
 Let-0.099
TokenHe
Token ID1544
Feature activation-1.48e-02

Pos logit contributions
ths+0.234
agg+0.225
eking+0.220
aman+0.212
Kevin+0.199
Neg logit contributions
.-0.277
."-0.261
ashes-0.247
 He-0.244
 rider-0.236
Token began
Token ID2540
Feature activation-1.07e-01

Pos logit contributions
.+0.020
."+0.017
 He+0.017
 play+0.016
 bar+0.016
Neg logit contributions
ths-0.031
eking-0.030
agg-0.030
aman-0.030
prisingly-0.028
Token to
Token ID284
Feature activation+1.14e-03

Pos logit contributions
.+0.079
."+0.063
ashes+0.053
 He+0.053
 towards+0.047
Neg logit contributions
ths-0.296
agg-0.289
eking-0.285
aman-0.280
prisingly-0.271
Token gra
Token ID7933
Feature activation-8.90e-03

Pos logit contributions
ths+0.002
agg+0.002
eking+0.002
aman+0.002
Kevin+0.002
Neg logit contributions
.-0.001
."-0.001
ashes-0.001
 He-0.001
 rider-0.001
Token replied
Token ID8712
Feature activation+1.03e-01

Pos logit contributions
eking+0.066
agg+0.064
ths+0.063
aman+0.060
iter+0.059
Neg logit contributions
.-0.050
."-0.042
 He-0.042
 They-0.039
 play-0.038
Token his
Token ID465
Feature activation-1.43e-02

Pos logit contributions
ths+0.204
agg+0.198
eking+0.190
aman+0.188
Jess+0.180
Neg logit contributions
.-0.139
ashes-0.134
."-0.133
 He-0.121
 rider-0.120
Token mom
Token ID1995
Feature activation+1.18e-02

Pos logit contributions
.+0.025
."+0.024
ashes+0.024
 He+0.022
 Let+0.022
Neg logit contributions
ths-0.024
agg-0.023
eking-0.021
aman-0.021
Kevin-0.020
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
ths+0.035
eking+0.034
agg+0.034
aman+0.033
ering+0.033
Neg logit contributions
ashes-0.005
."-0.003
.-0.003
powers-0.003
 rider-0.002
Token
Token ID198
Feature activation+1.48e-01

Pos logit contributions
.+0.167
."+0.151
 He+0.144
 They+0.134
 Let+0.128
Neg logit contributions
ths-0.324
eking-0.319
agg-0.314
aman-0.298
prisingly-0.291
Token
Token ID198
Feature activation+1.47e-01

Pos logit contributions
ths+0.419
eking+0.417
agg+0.388
aman+0.380
ering+0.373
Neg logit contributions
.-0.142
."-0.121
 He-0.110
 They-0.100
 Let-0.082
TokenThe
Token ID464
Feature activation+1.45e-02

Pos logit contributions
ths+0.260
agg+0.257
eking+0.257
aman+0.240
ering+0.223
Neg logit contributions
.-0.251
."-0.236
 He-0.223
 They-0.212
 Let-0.211
Token little
Token ID1310
Feature activation+3.70e-02

Pos logit contributions
agg+0.032
ths+0.032
eking+0.031
aman+0.031
prisingly+0.030
Neg logit contributions
.-0.019
."-0.017
 He-0.015
 rider-0.014
 ride-0.014
Token owl
Token ID39610
Feature activation+1.24e-02

Pos logit contributions
ths+0.080
agg+0.075
eking+0.075
aman+0.074
Jess+0.071
Neg logit contributions
.-0.046
ashes-0.044
."-0.043
 He-0.038
 They-0.038
Token was
Token ID373
Feature activation+6.42e-02

Pos logit contributions
ths+0.023
agg+0.023
eking+0.023
aman+0.022
Kevin+0.021
Neg logit contributions
.-0.020
."-0.018
 He-0.016
 play-0.016
 rider-0.015
Token so
Token ID523
Feature activation+8.01e-02

Pos logit contributions
ths+0.126
aman+0.118
agg+0.118
eking+0.114
Kevin+0.108
Neg logit contributions
.-0.109
."-0.094
 like-0.089
 He-0.086
 pet-0.083
Token kind
Token ID1611
Feature activation-6.94e-03

Pos logit contributions
ths+0.133
agg+0.128
eking+0.126
aman+0.120
Kevin+0.116
Neg logit contributions
.-0.132
."-0.125
ashes-0.120
 He-0.117
 rider-0.113
Token to
Token ID284
Feature activation-6.79e-04

Pos logit contributions
ashes+0.006
 pedal+0.006
 play+0.005
 rider+0.005
 bar+0.005
Neg logit contributions
ths-0.016
agg-0.015
eking-0.014
Jess-0.014
prisingly-0.014
Token each
Token ID1123
Feature activation-5.45e-02

Pos logit contributions
.+0.001
."+0.001
ashes+0.001
 He+0.001
 rider+0.001
Neg logit contributions
ths-0.001
agg-0.001
eking-0.001
aman-0.001
Kevin-0.001
Token other
Token ID584
Feature activation-6.41e-02

Pos logit contributions
.+0.067
."+0.062
ashes+0.061
 He+0.059
 rider+0.055
Neg logit contributions
ths-0.116
agg-0.113
eking-0.111
aman-0.108
Jess-0.105
Token."
Token ID526
Feature activation-7.15e-02

Pos logit contributions
ashes+0.033
.+0.033
 He+0.028
 rider+0.025
."+0.025
Neg logit contributions
ths-0.174
eking-0.169
agg-0.169
aman-0.163
Kevin-0.161
Token
Token ID198
Feature activation+1.51e-01

Pos logit contributions
.+0.095
."+0.087
ashes+0.080
 He+0.079
 rider+0.074
Neg logit contributions
ths-0.152
agg-0.148
eking-0.145
aman-0.141
Kevin-0.135
Token
Token ID198
Feature activation+1.50e-01

Pos logit contributions
ths+0.371
eking+0.365
agg+0.352
aman+0.348
ering+0.328
Neg logit contributions
.-0.173
."-0.153
 He-0.139
 They-0.129
ashes-0.121
TokenThe
Token ID464
Feature activation+1.77e-02

Pos logit contributions
eking+0.268
ths+0.266
agg+0.263
aman+0.251
ering+0.232
Neg logit contributions
.-0.252
."-0.235
 He-0.224
 They-0.214
 Let-0.213
Token two
Token ID734
Feature activation-2.62e-02

Pos logit contributions
ths+0.033
agg+0.031
eking+0.030
aman+0.029
prisingly+0.028
Neg logit contributions
.-0.028
."-0.027
ashes-0.025
 He-0.025
 They-0.024
Token friends
Token ID2460
Feature activation-7.59e-02

Pos logit contributions
.+0.035
."+0.031
ashes+0.029
 He+0.028
 rider+0.027
Neg logit contributions
ths-0.056
agg-0.055
eking-0.054
aman-0.053
Kevin-0.051
Token were
Token ID547
Feature activation+9.99e-02

Pos logit contributions
.+0.125
."+0.114
 He+0.106
ashes+0.105
 They+0.102
Neg logit contributions
ths-0.138
agg-0.133
eking-0.132
aman-0.128
Kevin-0.121
Token liked
Token ID8288
Feature activation-1.11e-02

Pos logit contributions
.+0.048
."+0.046
ashes+0.044
 He+0.042
 rider+0.040
Neg logit contributions
ths-0.071
agg-0.070
eking-0.067
aman-0.065
Kevin-0.064
Token to
Token ID284
Feature activation-5.74e-03

Pos logit contributions
.+0.009
."+0.009
ashes+0.008
 He+0.008
 rider+0.008
Neg logit contributions
ths-0.027
agg-0.026
eking-0.026
aman-0.025
Kevin-0.025
Token slide
Token ID10649
Feature activation-6.27e-02

Pos logit contributions
powers+0.006
ray+0.006
.+0.006
."+0.006
eer+0.006
Neg logit contributions
agg-0.011
eking-0.011
ths-0.011
Kevin-0.010
Jane-0.010
Token,
Token ID11
Feature activation+7.70e-02

Pos logit contributions
powers+0.075
five+0.072
ashes+0.071
 Let+0.071
eer+0.070
Neg logit contributions
ths-0.129
eking-0.116
aman-0.116
agg-0.114
ering-0.111
Token swing
Token ID9628
Feature activation-1.18e-01

Pos logit contributions
ths+0.184
eking+0.182
agg+0.181
aman+0.172
Kevin+0.170
Neg logit contributions
.-0.067
."-0.061
ashes-0.055
 He-0.052
 rider-0.052
Token,
Token ID11
Feature activation+7.71e-02

Pos logit contributions
powers+0.123
ashes+0.121
."+0.118
 rider+0.116
 Let+0.115
Neg logit contributions
ths-0.246
agg-0.234
eking-0.232
aman-0.229
prisingly-0.215
Token and
Token ID290
Feature activation+3.77e-02

Pos logit contributions
ths+0.202
agg+0.196
eking+0.196
aman+0.190
Kevin+0.184
Neg logit contributions
.-0.059
."-0.052
ashes-0.045
 He-0.043
 rider-0.040
Token run
Token ID1057
Feature activation-1.14e-01

Pos logit contributions
ths+0.085
agg+0.082
eking+0.082
Jess+0.079
Kevin+0.079
Neg logit contributions
.-0.037
."-0.035
ashes-0.032
 He-0.031
 rider-0.029
Token.
Token ID13
Feature activation-1.55e-01

Pos logit contributions
ray+0.119
 Let+0.118
eer+0.115
 fixes+0.107
 rider+0.107
Neg logit contributions
h-0.192
eking-0.192
ering-0.192
 done-0.191
ths-0.191
Token One
Token ID1881
Feature activation+1.81e-03

Pos logit contributions
.+0.165
."+0.155
 rider+0.149
ashes+0.138
 pedal+0.131
Neg logit contributions
agg-0.352
ths-0.344
aman-0.330
eking-0.326
Kevin-0.321
Token day
Token ID1110
Feature activation+3.90e-02

Pos logit contributions
agg+0.003
ths+0.003
aman+0.003
eking+0.003
prisingly+0.002
Neg logit contributions
."-0.003
.-0.003
ashes-0.003
powers-0.003
 He-0.003
TokenHe
Token ID1544
Feature activation-1.48e-02

Pos logit contributions
agg+0.245
eking+0.241
ths+0.239
aman+0.224
ering+0.207
Neg logit contributions
.-0.280
."-0.264
 He-0.258
 They-0.243
 Let-0.239
Token planted
Token ID18969
Feature activation-1.34e-02

Pos logit contributions
.+0.021
."+0.019
 He+0.018
ashes+0.017
 They+0.017
Neg logit contributions
ths-0.030
eking-0.029
agg-0.029
aman-0.029
Kevin-0.027
Token the
Token ID262
Feature activation-3.43e-02

Pos logit contributions
.+0.015
."+0.013
 He+0.012
 like+0.010
 They+0.010
Neg logit contributions
ths-0.034
eking-0.032
aman-0.032
agg-0.032
Kevin-0.030
Token flowers
Token ID12734
Feature activation-9.35e-02

Pos logit contributions
.+0.047
."+0.042
ashes+0.038
 He+0.036
 towards+0.035
Neg logit contributions
ths-0.075
agg-0.071
eking-0.071
aman-0.069
prisingly-0.067
Token and
Token ID290
Feature activation+4.88e-02

Pos logit contributions
.+0.088
."+0.068
 He+0.056
 towards+0.054
ashes+0.052
Neg logit contributions
ths-0.249
agg-0.242
aman-0.240
eking-0.238
Kevin-0.231
Token waited
Token ID13488
Feature activation+5.97e-02

Pos logit contributions
ths+0.103
eking+0.101
aman+0.100
agg+0.098
Kevin+0.093
Neg logit contributions
.-0.069
."-0.060
 play-0.054
 He-0.054
 They-0.053
Token for
Token ID329
Feature activation-4.67e-03

Pos logit contributions
ths+0.124
agg+0.122
eking+0.120
aman+0.115
Kevin+0.111
Neg logit contributions
.-0.076
."-0.072
ashes-0.069
 rider-0.066
 He-0.066
Token them
Token ID606
Feature activation+3.06e-02

Pos logit contributions
.+0.006
."+0.005
 play+0.004
 He+0.004
 fur+0.004
Neg logit contributions
ths-0.012
eking-0.011
aman-0.011
agg-0.011
mber-0.010
Token to
Token ID284
Feature activation+6.60e-04

Pos logit contributions
ths+0.074
agg+0.072
eking+0.071
prisingly+0.067
Jess+0.066
Neg logit contributions
 rider-0.026
ashes-0.025
."-0.025
.-0.024
 pedal-0.023
Token grow
Token ID1663
Feature activation+3.39e-02

Pos logit contributions
ths+0.002
agg+0.001
eking+0.001
aman+0.001
Kevin+0.001
Neg logit contributions
.-0.001
."-0.001
 play-0.001
 He-0.001
 like-0.001
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
agg+0.093
ths+0.093
eking+0.091
aman+0.088
Jess+0.086
Neg logit contributions
.-0.019
."-0.016
 rider-0.016
ashes-0.016
 He-0.014
Token would
Token ID561
Feature activation-8.21e-03

Pos logit contributions
.+0.043
ashes+0.042
."+0.041
five+0.038
 towards+0.038
Neg logit contributions
ths-0.057
agg-0.055
eking-0.053
aman-0.051
Jess-0.050
Token sleep
Token ID3993
Feature activation-2.34e-02

Pos logit contributions
.+0.011
."+0.010
ashes+0.010
 He+0.009
 Let+0.009
Neg logit contributions
ths-0.017
agg-0.016
eking-0.016
aman-0.016
Kevin-0.015
Token all
Token ID477
Feature activation-7.66e-02

Pos logit contributions
.+0.023
."+0.020
 He+0.016
ashes+0.015
 rider+0.015
Neg logit contributions
ths-0.060
agg-0.060
aman-0.058
eking-0.057
Kevin-0.056
Token day
Token ID1110
Feature activation+4.27e-02

Pos logit contributions
.+0.117
."+0.109
ashes+0.105
 He+0.101
 rider+0.098
Neg logit contributions
ths-0.143
agg-0.138
eking-0.136
aman-0.131
prisingly-0.125
Token and
Token ID290
Feature activation+4.51e-02

Pos logit contributions
ths+0.107
agg+0.104
eking+0.102
aman+0.100
prisingly+0.097
Neg logit contributions
.-0.044
."-0.038
ashes-0.033
 He-0.032
 They-0.030
Token never
Token ID1239
Feature activation+8.75e-02

Pos logit contributions
ths+0.085
agg+0.083
eking+0.081
aman+0.078
Kevin+0.075
Neg logit contributions
.-0.070
."-0.065
ashes-0.061
 He-0.060
 rider-0.057
Token play
Token ID711
Feature activation-1.17e-01

Pos logit contributions
eking+0.147
ths+0.141
agg+0.133
ering+0.126
aman+0.124
Neg logit contributions
ashes-0.126
.-0.123
."-0.121
 They-0.119
 He-0.118
Token with
Token ID351
Feature activation-1.36e-02

Pos logit contributions
ashes+0.134
 Let+0.124
ny+0.121
 pads+0.119
 pedal+0.118
Neg logit contributions
ths-0.233
eking-0.219
agg-0.210
 unfortunately-0.208
prisingly-0.207
Token the
Token ID262
Feature activation-3.69e-02

Pos logit contributions
.+0.020
ashes+0.020
."+0.019
 rider+0.018
 Let+0.018
Neg logit contributions
ths-0.025
eking-0.024
agg-0.024
aman-0.023
Jess-0.021
Token other
Token ID584
Feature activation-7.01e-02

Pos logit contributions
.+0.047
ashes+0.045
."+0.044
five+0.044
 He+0.042
Neg logit contributions
ths-0.069
agg-0.067
eking-0.067
aman-0.066
 sudden-0.064
Token cats
Token ID11875
Feature activation-6.82e-02

Pos logit contributions
 He+0.079
five+0.075
ashes+0.074
.+0.072
."+0.071
Neg logit contributions
ths-0.141
eking-0.134
agg-0.131
 sudden-0.129
aman-0.128
Token it
Token ID340
Feature activation+1.81e-02

Pos logit contributions
ths+0.217
agg+0.216
eking+0.209
aman+0.208
Jess+0.200
Neg logit contributions
.-0.119
."-0.101
 He-0.097
 towards-0.087
 They-0.086
Token is
Token ID318
Feature activation+6.03e-02

Pos logit contributions
ths+0.041
eking+0.039
agg+0.038
aman+0.036
prisingly+0.036
Neg logit contributions
.-0.020
."-0.020
ashes-0.018
five-0.017
 rider-0.017
Token too
Token ID1165
Feature activation+2.75e-02

Pos logit contributions
ths+0.115
eking+0.109
agg+0.107
aman+0.103
prisingly+0.101
Neg logit contributions
.-0.088
ashes-0.086
."-0.085
five-0.079
 He-0.077
Token hard
Token ID1327
Feature activation-1.86e-02

Pos logit contributions
ths+0.050
agg+0.048
eking+0.047
aman+0.046
prisingly+0.044
Neg logit contributions
.-0.042
."-0.040
ashes-0.039
 He-0.037
 Let-0.037
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
ashes+0.012
 rider+0.010
five+0.009
 pet+0.009
 player+0.009
Neg logit contributions
eking-0.046
ths-0.046
ering-0.045
aman-0.043
 done-0.042
Token
Token ID198
Feature activation+1.41e-01

Pos logit contributions
.+0.118
."+0.097
 He+0.095
 They+0.087
ashes+0.083
Neg logit contributions
ths-0.394
eking-0.384
agg-0.378
prisingly-0.362
aman-0.362
Token
Token ID198
Feature activation+1.41e-01

Pos logit contributions
ths+0.401
eking+0.394
agg+0.364
aman+0.361
ering+0.353
Neg logit contributions
.-0.140
."-0.112
 He-0.110
 They-0.102
 Let-0.070
Token"
Token ID1
Feature activation+2.05e-02

Pos logit contributions
ths+0.272
eking+0.261
agg+0.257
aman+0.247
prisingly+0.236
Neg logit contributions
.-0.225
."-0.205
 He-0.194
ashes-0.190
 They-0.186
TokenNo
Token ID2949
Feature activation+8.58e-02

Pos logit contributions
eking+0.042
ths+0.041
agg+0.041
aman+0.039
ering+0.038
Neg logit contributions
.-0.028
ashes-0.026
."-0.025
 He-0.025
 bar-0.025
Token,
Token ID11
Feature activation+8.67e-02

Pos logit contributions
ths+0.158
agg+0.153
aman+0.151
eking+0.148
ering+0.136
Neg logit contributions
ashes-0.127
.-0.120
."-0.116
 He-0.116
 rider-0.115
Token Sara
Token ID24799
Feature activation+3.77e-02

Pos logit contributions
ths+0.199
agg+0.191
eking+0.189
aman+0.183
Kevin+0.178
Neg logit contributions
.-0.109
."-0.100
 He-0.087
ashes-0.083
 They-0.082
Tokenmy
Token ID1820
Feature activation+2.01e-02

Pos logit contributions
ths+0.093
agg+0.088
eking+0.088
aman+0.084
prisingly+0.081
Neg logit contributions
.-0.095
."-0.090
ashes-0.090
 He-0.084
 They-0.082
Token said
Token ID531
Feature activation+7.33e-02

Pos logit contributions
ths+0.037
agg+0.036
eking+0.036
aman+0.035
Jess+0.033
Neg logit contributions
.-0.034
."-0.031
 He-0.029
ashes-0.027
 They-0.027
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
ths+0.179
agg+0.178
 pleased+0.178
 impressed+0.178
eking+0.176
Neg logit contributions
ashes-0.052
 bars-0.047
eer-0.043
 spots-0.043
 pads-0.042
Token His
Token ID2399
Feature activation+3.21e-02

Pos logit contributions
 rider+0.180
ashes+0.178
 bars+0.172
.+0.171
."+0.169
Neg logit contributions
ths-0.258
agg-0.255
Kevin-0.233
Jane-0.230
mber-0.227
Token friends
Token ID2460
Feature activation-7.92e-02

Pos logit contributions
ths+0.058
agg+0.054
eking+0.053
aman+0.050
Kevin+0.049
Neg logit contributions
.-0.051
."-0.049
ashes-0.046
 Let-0.044
 He-0.044
Token were
Token ID547
Feature activation+9.34e-02

Pos logit contributions
.+0.132
."+0.119
 He+0.110
ashes+0.108
 They+0.106
Neg logit contributions
ths-0.148
agg-0.144
eking-0.140
aman-0.137
Jess-0.130
Token amazed
Token ID24562
Feature activation+9.04e-02

Pos logit contributions
ths+0.182
agg+0.180
aman+0.179
eking+0.170
prisingly+0.162
Neg logit contributions
.-0.166
."-0.144
 He-0.134
 like-0.133
 They-0.132
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
ths+0.239
eking+0.227
agg+0.226
aman+0.222
Kevin+0.215
Neg logit contributions
ashes-0.061
."-0.059
.-0.057
five-0.051
 Let-0.050
Token "
Token ID366
Feature activation+6.57e-02

Pos logit contributions
.+0.143
 rider+0.136
."+0.133
ashes+0.132
five+0.119
Neg logit contributions
ths-0.323
agg-0.312
aman-0.298
eking-0.292
Kevin-0.288
TokenWow
Token ID22017
Feature activation+1.43e-01

Pos logit contributions
ths+0.119
agg+0.113
eking+0.110
aman+0.108
Jess+0.104
Neg logit contributions
.-0.108
."-0.100
ashes-0.095
 He-0.091
 rider-0.088
Token,
Token ID11
Feature activation+8.37e-02

Pos logit contributions
ths+0.295
eking+0.278
agg+0.273
aman+0.262
ering+0.256
Neg logit contributions
ashes-0.183
.-0.174
."-0.165
 rider-0.164
 He-0.162
Token see
Token ID766
Feature activation+1.53e-02

Pos logit contributions
ashes+0.005
.+0.005
."+0.004
 rider+0.004
powers+0.004
Neg logit contributions
agg-0.007
ths-0.007
Kevin-0.006
eking-0.006
Jess-0.006
Token the
Token ID262
Feature activation-3.25e-02

Pos logit contributions
ths+0.024
aman+0.022
agg+0.022
eking+0.022
Jess+0.021
Neg logit contributions
ashes-0.027
.-0.024
powers-0.024
ny-0.024
."-0.024
Token big
Token ID1263
Feature activation-2.99e-02

Pos logit contributions
.+0.028
."+0.025
ashes+0.021
 He+0.021
 rider+0.019
Neg logit contributions
ths-0.085
agg-0.083
eking-0.082
aman-0.080
Kevin-0.077
Token,
Token ID11
Feature activation+9.15e-02

Pos logit contributions
ashes+0.031
.+0.030
."+0.028
 Let+0.026
powers+0.026
Neg logit contributions
ths-0.065
eking-0.063
aman-0.062
agg-0.062
ering-0.058
Token gray
Token ID12768
Feature activation-2.38e-02

Pos logit contributions
ths+0.188
agg+0.182
eking+0.181
aman+0.175
Kevin+0.169
Neg logit contributions
.-0.121
."-0.113
ashes-0.108
 He-0.100
 Let-0.097
Token animal
Token ID5044
Feature activation+2.60e-02

Pos logit contributions
ashes+0.032
 Let+0.027
."+0.026
powers+0.026
.+0.025
Neg logit contributions
ths-0.044
aman-0.044
agg-0.042
eking-0.041
 sudden-0.041
Token with
Token ID351
Feature activation-1.21e-02

Pos logit contributions
ths+0.062
eking+0.061
ering+0.058
agg+0.057
 impressed+0.057
Neg logit contributions
ashes-0.023
five-0.021
."-0.020
 Let-0.020
ny-0.019
Token the
Token ID262
Feature activation-3.28e-02

Pos logit contributions
.+0.016
."+0.015
ashes+0.014
 He+0.013
 Let+0.013
Neg logit contributions
ths-0.025
agg-0.025
eking-0.024
aman-0.023
Kevin-0.023
Token point
Token ID966
Feature activation-2.20e-02

Pos logit contributions
.+0.040
."+0.037
ashes+0.037
 He+0.033
 Let+0.033
Neg logit contributions
ths-0.069
eking-0.067
agg-0.067
aman-0.065
Kevin-0.062
Tokeny
Token ID88
Feature activation+3.47e-03

Pos logit contributions
ashes+0.026
five+0.025
powers+0.025
 rider+0.024
."+0.024
Neg logit contributions
eking-0.045
ths-0.043
ering-0.042
agg-0.042
aman-0.041
Token horn
Token ID12718
Feature activation-1.23e-02

Pos logit contributions
ths+0.006
eking+0.006
agg+0.006
 sudden+0.006
aman+0.006
Neg logit contributions
ashes-0.004
 Let-0.004
."-0.004
 They-0.003
.-0.003
Token got
Token ID1392
Feature activation-5.02e-03

Pos logit contributions
.+0.071
."+0.068
ashes+0.066
 He+0.062
 rider+0.060
Neg logit contributions
ths-0.098
agg-0.094
eking-0.088
prisingly-0.085
aman-0.084
Token a
Token ID257
Feature activation-2.85e-02

Pos logit contributions
.+0.006
."+0.006
 rider+0.006
ashes+0.006
 He+0.006
Neg logit contributions
ths-0.011
agg-0.010
eking-0.010
prisingly-0.009
aman-0.009
Token bucket
Token ID19236
Feature activation-2.54e-02

Pos logit contributions
.+0.038
."+0.035
ashes+0.033
 He+0.032
 rider+0.030
Neg logit contributions
ths-0.060
agg-0.058
eking-0.057
aman-0.056
Kevin-0.053
Token and
Token ID290
Feature activation+4.51e-02

Pos logit contributions
ashes+0.028
 rider+0.028
eer+0.027
powers+0.027
."+0.026
Neg logit contributions
ths-0.051
eking-0.048
aman-0.048
agg-0.047
prisingly-0.047
Token filled
Token ID5901
Feature activation-1.76e-02

Pos logit contributions
ths+0.083
agg+0.081
prisingly+0.073
 sudden+0.073
aman+0.071
Neg logit contributions
ashes-0.066
 rider-0.065
.-0.064
."-0.064
ny-0.061
Token it
Token ID340
Feature activation+2.24e-02

Pos logit contributions
.+0.024
."+0.021
 They+0.018
 towards+0.018
 He+0.018
Neg logit contributions
ths-0.040
agg-0.038
eking-0.038
aman-0.038
Kevin-0.036
Token with
Token ID351
Feature activation-1.41e-02

Pos logit contributions
ths+0.044
eking+0.044
agg+0.041
ering+0.040
 impressed+0.039
Neg logit contributions
 rider-0.029
eer-0.028
ashes-0.026
five-0.026
 zone-0.025
Token pe
Token ID613
Feature activation+1.10e-01

Pos logit contributions
 rider+0.017
."+0.017
.+0.016
ashes+0.016
ny+0.016
Neg logit contributions
ths-0.028
agg-0.028
eking-0.027
aman-0.027
 sudden-0.025
Tokenb
Token ID65
Feature activation+9.73e-02

Pos logit contributions
ths+0.146
aman+0.142
agg+0.137
Jess+0.131
Kevin+0.125
Neg logit contributions
.-0.234
."-0.217
ashes-0.206
 bars-0.192
 He-0.192
Tokenbles
Token ID7689
Feature activation-4.87e-02

Pos logit contributions
ths+0.118
agg+0.116
eking+0.116
aman+0.103
Kevin+0.098
Neg logit contributions
.-0.206
."-0.200
ashes-0.195
 rider-0.193
 He-0.191
Token.
Token ID13
Feature activation-1.45e-01

Pos logit contributions
 rider+0.036
eer+0.029
 Let+0.026
 He+0.026
ny+0.025
Neg logit contributions
ths-0.122
agg-0.121
eking-0.121
ering-0.117
 impressed-0.113
Token there
Token ID612
Feature activation-1.73e-02

Pos logit contributions
ths+0.149
eking+0.140
agg+0.140
aman+0.139
Kevin+0.128
Neg logit contributions
.-0.151
."-0.136
 He-0.129
 They-0.125
 Let-0.121
Token was
Token ID373
Feature activation+5.75e-02

Pos logit contributions
.+0.020
."+0.016
 He+0.016
 They+0.014
 play+0.014
Neg logit contributions
ths-0.044
eking-0.044
agg-0.042
aman-0.041
Kevin-0.040
Token a
Token ID257
Feature activation-3.13e-02

Pos logit contributions
ths+0.152
eking+0.148
agg+0.144
aman+0.141
ering+0.137
Neg logit contributions
.-0.054
."-0.046
 He-0.040
 They-0.038
ashes-0.037
Token battery
Token ID6555
Feature activation-1.55e-02

Pos logit contributions
.+0.046
."+0.043
ashes+0.041
 He+0.040
 Let+0.038
Neg logit contributions
ths-0.060
agg-0.059
eking-0.057
aman-0.056
Kevin-0.053
Token.
Token ID13
Feature activation-1.51e-01

Pos logit contributions
ashes+0.022
five+0.020
irms+0.019
powers+0.019
 pads+0.017
Neg logit contributions
ths-0.028
lf-0.027
eking-0.026
 unfortunately-0.026
 nowhere-0.025
Token It
Token ID632
Feature activation+3.76e-02

Pos logit contributions
ashes+0.196
.+0.163
 pads+0.156
."+0.146
powers+0.145
Neg logit contributions
agg-0.290
ths-0.289
Jess-0.279
mmm-0.276
 unfortunately-0.276
Token had
Token ID550
Feature activation-2.78e-02

Pos logit contributions
ths+0.053
agg+0.050
eking+0.050
prisingly+0.046
 nowhere+0.045
Neg logit contributions
ashes-0.069
five-0.064
.-0.062
."-0.062
 rider-0.059
Token a
Token ID257
Feature activation-3.08e-02

Pos logit contributions
ashes+0.040
.+0.039
."+0.036
 rider+0.035
five+0.034
Neg logit contributions
agg-0.048
ths-0.048
eking-0.048
 sudden-0.045
prisingly-0.044
Token very
Token ID845
Feature activation+6.65e-02

Pos logit contributions
ashes+0.046
.+0.043
."+0.042
five+0.042
 Let+0.039
Neg logit contributions
ths-0.055
 sudden-0.053
agg-0.051
eking-0.050
aman-0.050
Token important
Token ID1593
Feature activation+2.25e-02

Pos logit contributions
agg+0.111
ths+0.105
eking+0.104
 sudden+0.095
 impressed+0.094
Neg logit contributions
.-0.106
 Let-0.103
."-0.101
ashes-0.101
five-0.098
Token job
Token ID1693
Feature activation-2.04e-02

Pos logit contributions
ths+0.034
agg+0.033
 sudden+0.033
prisingly+0.032
aman+0.032
Neg logit contributions
ashes-0.035
 pads-0.031
 Let-0.029
."-0.029
 They-0.029
Token She
Token ID1375
Feature activation-3.36e-02

Pos logit contributions
ashes+0.197
 rider+0.197
eer+0.190
."+0.173
.+0.172
Neg logit contributions
agg-0.247
ths-0.235
omm-0.233
Jane-0.231
 unfortunately-0.230
Token opened
Token ID4721
Feature activation-3.90e-02

Pos logit contributions
.+0.045
."+0.039
 He+0.037
 They+0.034
 Let+0.034
Neg logit contributions
ths-0.073
agg-0.071
eking-0.071
aman-0.070
Kevin-0.066
Token the
Token ID262
Feature activation-3.60e-02

Pos logit contributions
.+0.059
."+0.053
 He+0.048
ashes+0.046
 towards+0.046
Neg logit contributions
ths-0.079
agg-0.077
eking-0.075
aman-0.073
Kevin-0.070
Token door
Token ID3420
Feature activation-4.28e-02

Pos logit contributions
.+0.056
ashes+0.056
."+0.055
 rider+0.053
 He+0.052
Neg logit contributions
ths-0.061
eking-0.059
agg-0.058
aman-0.057
prisingly-0.053
Token and
Token ID290
Feature activation+4.64e-02

Pos logit contributions
ashes+0.042
eer+0.038
."+0.037
 rider+0.037
powers+0.035
Neg logit contributions
ths-0.100
agg-0.094
eking-0.094
aman-0.094
prisingly-0.090
Token saw
Token ID2497
Feature activation+2.23e-02

Pos logit contributions
ths+0.085
agg+0.082
eking+0.081
aman+0.078
Kevin+0.074
Neg logit contributions
.-0.074
."-0.070
ashes-0.066
 He-0.064
 rider-0.062
Token stairs
Token ID16046
Feature activation-9.17e-02

Pos logit contributions
ths+0.047
agg+0.045
eking+0.044
aman+0.043
Jess+0.041
Neg logit contributions
.-0.028
."-0.027
ashes-0.026
 rider-0.024
ny-0.024
Token.
Token ID13
Feature activation-1.42e-01

Pos logit contributions
ashes+0.065
powers+0.058
."+0.054
eer+0.053
five+0.053
Neg logit contributions
ths-0.242
eking-0.238
aman-0.222
ering-0.221
agg-0.218
Token She
Token ID1375
Feature activation-3.35e-02

Pos logit contributions
 rider+0.196
eer+0.193
ashes+0.182
ny+0.174
.+0.170
Neg logit contributions
agg-0.252
ths-0.251
aman-0.235
Jane-0.232
Jess-0.232
Token climbed
Token ID19952
Feature activation-3.00e-02

Pos logit contributions
.+0.045
."+0.039
 He+0.037
 They+0.034
 Let+0.034
Neg logit contributions
ths-0.072
aman-0.072
eking-0.071
agg-0.071
Kevin-0.067
Token the
Token ID262
Feature activation-3.54e-02

Pos logit contributions
ashes+0.036
powers+0.032
 rider+0.032
eer+0.032
."+0.031
Neg logit contributions
ths-0.064
eking-0.059
agg-0.059
aman-0.057
prisingly-0.055
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
.+0.179
."+0.163
 He+0.149
ashes+0.149
 They+0.142
Neg logit contributions
ths-0.322
agg-0.311
eking-0.310
aman-0.297
prisingly-0.287
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
ths+0.351
eking+0.342
agg+0.330
aman+0.319
prisingly+0.310
Neg logit contributions
.-0.171
."-0.152
 He-0.138
 They-0.132
ashes-0.130
TokenTom
Token ID13787
Feature activation+6.55e-02

Pos logit contributions
ths+0.249
eking+0.248
agg+0.244
aman+0.225
ering+0.215
Neg logit contributions
.-0.252
."-0.235
ashes-0.222
 He-0.218
 They-0.214
Token che
Token ID1125
Feature activation+3.68e-02

Pos logit contributions
ths+0.134
agg+0.129
eking+0.126
aman+0.123
Kevin+0.118
Neg logit contributions
.-0.090
."-0.085
ashes-0.080
 He-0.076
 rider-0.073
Tokenwed
Token ID19103
Feature activation-3.05e-02

Pos logit contributions
ths+0.083
agg+0.078
aman+0.078
eking+0.077
Kevin+0.076
Neg logit contributions
.-0.043
."-0.039
ashes-0.038
ny-0.035
 bars-0.033
Token his
Token ID465
Feature activation-1.50e-02

Pos logit contributions
.+0.034
."+0.031
ashes+0.029
 He+0.028
 rider+0.026
Neg logit contributions
ths-0.071
agg-0.069
eking-0.068
aman-0.066
Kevin-0.063
Token gum
Token ID27142
Feature activation-1.07e-02

Pos logit contributions
.+0.022
."+0.021
ashes+0.020
 They+0.019
 towards+0.019
Neg logit contributions
ths-0.028
eking-0.027
agg-0.026
aman-0.025
ering-0.024
Token too
Token ID1165
Feature activation+2.98e-02

Pos logit contributions
.+0.011
."+0.010
ashes+0.010
 He+0.009
 rider+0.009
Neg logit contributions
ths-0.025
agg-0.024
eking-0.024
aman-0.023
prisingly-0.022
Token.
Token ID13
Feature activation-1.43e-01

Pos logit contributions
ths+0.060
agg+0.058
eking+0.057
aman+0.055
Kevin+0.053
Neg logit contributions
.-0.038
."-0.037
ashes-0.037
 Let-0.035
 rider-0.034
Token He
Token ID679
Feature activation-1.88e-02

Pos logit contributions
.+0.115
."+0.102
 rider+0.095
ashes+0.094
eer+0.088
Neg logit contributions
ths-0.358
agg-0.355
aman-0.343
Kevin-0.331
eking-0.327
Token smiled
Token ID13541
Feature activation+3.33e-02

Pos logit contributions
.+0.030
."+0.028
ashes+0.027
 He+0.026
 rider+0.025
Neg logit contributions
ths-0.034
agg-0.033
eking-0.032
aman-0.031
Kevin-0.030
Token her
Token ID607
Feature activation-4.20e-02

Pos logit contributions
.+0.015
."+0.014
ashes+0.013
 He+0.013
 They+0.012
Neg logit contributions
ths-0.019
agg-0.018
eking-0.018
aman-0.017
prisingly-0.017
Token mom
Token ID1995
Feature activation+2.17e-03

Pos logit contributions
ashes+0.073
.+0.071
."+0.070
 He+0.068
ny+0.067
Neg logit contributions
ths-0.065
agg-0.063
aman-0.059
eking-0.058
Kevin-0.056
Token what
Token ID644
Feature activation-3.60e-02

Pos logit contributions
ths+0.005
agg+0.005
eking+0.004
aman+0.004
prisingly+0.004
Neg logit contributions
.-0.003
."-0.002
ashes-0.002
 He-0.002
 rider-0.002
Token was
Token ID373
Feature activation+5.79e-02

Pos logit contributions
.+0.060
ashes+0.060
."+0.058
 He+0.054
 towards+0.053
Neg logit contributions
ths-0.060
agg-0.058
aman-0.054
eking-0.054
Jess-0.053
Token inside
Token ID2641
Feature activation-6.00e-02

Pos logit contributions
ths+0.108
agg+0.104
eking+0.101
aman+0.098
Kevin+0.094
Neg logit contributions
.-0.095
."-0.088
ashes-0.081
 He-0.080
 rider-0.077
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
.+0.056
ashes+0.052
."+0.052
 He+0.048
 rider+0.046
Neg logit contributions
ths-0.144
agg-0.141
eking-0.139
aman-0.137
Kevin-0.131
Token Her
Token ID2332
Feature activation+2.32e-02

Pos logit contributions
.+0.171
."+0.153
 He+0.144
 They+0.138
 Let+0.132
Neg logit contributions
ths-0.319
eking-0.312
agg-0.306
aman-0.290
prisingly-0.286
Token mom
Token ID1995
Feature activation+5.12e-03

Pos logit contributions
ths+0.040
agg+0.039
eking+0.038
aman+0.037
Kevin+0.035
Neg logit contributions
.-0.039
."-0.037
ashes-0.036
 He-0.035
 rider-0.033
Token said
Token ID531
Feature activation+7.57e-02

Pos logit contributions
agg+0.011
eking+0.011
ths+0.011
Kevin+0.011
Jess+0.011
Neg logit contributions
.-0.007
."-0.006
 play-0.005
 likes-0.005
 bar-0.005
Token it
Token ID340
Feature activation+1.77e-02

Pos logit contributions
ths+0.176
eking+0.170
aman+0.168
agg+0.166
Kevin+0.161
Neg logit contributions
.-0.109
."-0.089
 He-0.077
 like-0.075
 They-0.072
Token was
Token ID373
Feature activation+6.02e-02

Pos logit contributions
ths+0.034
agg+0.033
eking+0.032
aman+0.031
prisingly+0.030
Neg logit contributions
.-0.026
."-0.025
ashes-0.024
 He-0.022
 rider-0.022
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
ths+0.232
eking+0.225
agg+0.223
aman+0.217
ering+0.213
Neg logit contributions
ashes-0.053
."-0.048
 rider-0.046
.-0.046
powers-0.045
Token They
Token ID1119
Feature activation-2.71e-02

Pos logit contributions
eer+0.163
 rider+0.160
raid+0.150
ashes+0.150
five+0.148
Neg logit contributions
ths-0.259
 sudden-0.252
Da-0.248
 July-0.243
Finally-0.241
Token loved
Token ID6151
Feature activation+6.25e-03

Pos logit contributions
."+0.044
ashes+0.044
.+0.043
 Let+0.041
powers+0.040
Neg logit contributions
agg-0.045
ths-0.042
aman-0.040
Kevin-0.040
eking-0.039
Token the
Token ID262
Feature activation-3.21e-02

Pos logit contributions
ths+0.014
agg+0.014
eking+0.014
aman+0.013
Kevin+0.013
Neg logit contributions
.-0.007
."-0.007
ashes-0.006
 He-0.006
 rider-0.006
Token snow
Token ID6729
Feature activation+1.52e-02

Pos logit contributions
.+0.032
."+0.029
ashes+0.027
 He+0.025
 rider+0.024
Neg logit contributions
ths-0.078
agg-0.076
eking-0.075
aman-0.073
Kevin-0.070
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
ths+0.028
agg+0.026
eking+0.026
aman+0.024
ering+0.024
Neg logit contributions
ashes-0.021
."-0.021
.-0.020
powers-0.020
five-0.020
Token They
Token ID1119
Feature activation-2.72e-02

Pos logit contributions
 rider+0.141
eer+0.138
ny+0.125
five+0.123
ashes+0.123
Neg logit contributions
agg-0.290
 unfortunately-0.286
ths-0.285
Finally-0.280
 sudden-0.278
Token put
Token ID1234
Feature activation-5.06e-02

Pos logit contributions
ashes+0.042
."+0.041
.+0.040
 Let+0.039
 towards+0.039
Neg logit contributions
agg-0.047
ths-0.043
Kevin-0.041
aman-0.040
eking-0.040
Token on
Token ID319
Feature activation-5.80e-02

Pos logit contributions
.+0.050
."+0.045
ashes+0.040
 He+0.039
 rider+0.036
Neg logit contributions
ths-0.125
agg-0.122
eking-0.120
aman-0.117
Kevin-0.113
Token their
Token ID511
Feature activation+1.75e-02

Pos logit contributions
.+0.088
."+0.084
ashes+0.079
 He+0.077
 rider+0.075
Neg logit contributions
ths-0.110
agg-0.107
eking-0.104
aman-0.102
Kevin-0.096
Token coats
Token ID30720
Feature activation-6.04e-02

Pos logit contributions
ths+0.039
agg+0.038
eking+0.037
aman+0.036
Kevin+0.035
Neg logit contributions
.-0.020
."-0.019
ashes-0.018
 He-0.017
 rider-0.016
Token he
Token ID339
Feature activation-3.34e-02

Pos logit contributions
ths+0.043
agg+0.042
eking+0.042
aman+0.041
prisingly+0.039
Neg logit contributions
.-0.026
."-0.023
 He-0.021
ashes-0.020
 They-0.020
Token will
Token ID481
Feature activation+3.75e-02

Pos logit contributions
.+0.043
 towards+0.043
 He+0.042
ashes+0.042
."+0.041
Neg logit contributions
ths-0.060
eking-0.057
agg-0.055
Fore-0.052
aman-0.052
Token come
Token ID1282
Feature activation+4.38e-02

Pos logit contributions
ths+0.068
agg+0.068
eking+0.066
aman+0.064
Kevin+0.062
Neg logit contributions
.-0.055
."-0.051
ashes-0.051
 He-0.049
 rider-0.048
Token back
Token ID736
Feature activation-5.16e-02

Pos logit contributions
eking+0.086
ths+0.085
agg+0.084
prisingly+0.082
Jess+0.079
Neg logit contributions
 rider-0.047
ashes-0.046
 bar-0.045
powers-0.045
five-0.045
Token and
Token ID290
Feature activation+4.39e-02

Pos logit contributions
ashes+0.056
 rider+0.053
.+0.051
 He+0.051
 pedal+0.051
Neg logit contributions
ths-0.107
agg-0.104
eking-0.098
Jess-0.098
aman-0.097
Token play
Token ID711
Feature activation-1.15e-01

Pos logit contributions
ths+0.109
agg+0.105
eking+0.104
aman+0.101
prisingly+0.099
Neg logit contributions
.-0.037
."-0.033
ashes-0.032
 He-0.029
 rider-0.028
Token with
Token ID351
Feature activation-1.58e-02

Pos logit contributions
 rider+0.136
 pedal+0.129
 He+0.129
ashes+0.127
powers+0.126
Neg logit contributions
agg-0.219
ths-0.218
eking-0.218
prisingly-0.208
Jess-0.201
Token them
Token ID606
Feature activation+3.15e-02

Pos logit contributions
.+0.025
."+0.023
ashes+0.021
 He+0.020
 They+0.020
Neg logit contributions
ths-0.031
agg-0.030
eking-0.029
aman-0.029
prisingly-0.027
Token another
Token ID1194
Feature activation-3.68e-02

Pos logit contributions
ths+0.065
eking+0.063
agg+0.061
prisingly+0.060
 unfortunately+0.058
Neg logit contributions
ashes-0.034
powers-0.030
 He-0.030
five-0.029
 Let-0.029
Token day
Token ID1110
Feature activation+4.15e-02

Pos logit contributions
 He+0.054
.+0.053
ashes+0.052
 rider+0.052
five+0.051
Neg logit contributions
ths-0.062
agg-0.061
eking-0.057
Jess-0.056
aman-0.056
Token.
Token ID13
Feature activation-1.43e-01

Pos logit contributions
ths+0.111
agg+0.109
eking+0.109
Jess+0.105
Kevin+0.104
Neg logit contributions
 pedal-0.017
 rider-0.016
ashes-0.016
 tire-0.014
 pedals-0.014
Token a
Token ID257
Feature activation-3.11e-02

Pos logit contributions
ths+0.165
eking+0.156
aman+0.153
agg+0.152
Kevin+0.146
Neg logit contributions
.-0.057
."-0.046
 He-0.038
 They-0.038
ashes-0.037
Token little
Token ID1310
Feature activation+3.64e-02

Pos logit contributions
.+0.049
."+0.047
ashes+0.046
 He+0.043
 towards+0.043
Neg logit contributions
ths-0.055
agg-0.054
eking-0.050
aman-0.050
Kevin-0.049
Token girl
Token ID2576
Feature activation+1.45e-02

Pos logit contributions
ths+0.071
agg+0.070
aman+0.066
Jess+0.065
mber+0.065
Neg logit contributions
.-0.045
."-0.044
ashes-0.043
 Let-0.040
 He-0.040
Token named
Token ID3706
Feature activation-2.82e-02

Pos logit contributions
ths+0.022
agg+0.021
eking+0.021
Jess+0.020
aman+0.020
Neg logit contributions
ashes-0.026
 He-0.024
powers-0.024
five-0.024
 pedals-0.023
Token Daisy
Token ID40355
Feature activation+2.62e-02

Pos logit contributions
.+0.030
."+0.028
ashes+0.023
 They+0.022
 He+0.022
Neg logit contributions
ths-0.071
agg-0.068
eking-0.067
aman-0.066
Kevin-0.064
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
Jess+0.061
agg+0.061
aman+0.059
Fore+0.058
Mill+0.058
Neg logit contributions
ashes-0.026
powers-0.023
five-0.021
 puck-0.019
 pedals-0.019
Token Daisy
Token ID40355
Feature activation+2.51e-02

Pos logit contributions
.+0.222
."+0.204
 He+0.188
ashes+0.187
 They+0.181
Neg logit contributions
ths-0.319
eking-0.305
agg-0.304
aman-0.293
prisingly-0.280
Token wanted
Token ID2227
Feature activation-4.63e-02

Pos logit contributions
agg+0.043
ths+0.043
eking+0.040
Jess+0.039
aman+0.039
Neg logit contributions
ashes-0.040
five-0.036
."-0.036
.-0.035
 towards-0.034
Token to
Token ID284
Feature activation-4.72e-03

Pos logit contributions
.+0.032
."+0.027
ashes+0.022
 He+0.021
 They+0.018
Neg logit contributions
ths-0.129
agg-0.126
eking-0.125
aman-0.122
Kevin-0.118
Token learn
Token ID2193
Feature activation-4.20e-02

Pos logit contributions
ashes+0.006
ny+0.005
eer+0.005
.+0.005
 rider+0.005
Neg logit contributions
agg-0.010
ths-0.009
Kevin-0.009
Jess-0.009
aman-0.008
Token how
Token ID703
Feature activation-6.01e-02

Pos logit contributions
ashes+0.068
ny+0.064
 He+0.061
 rider+0.061
five+0.060
Neg logit contributions
ths-0.072
eking-0.068
agg-0.066
aman-0.066
prisingly-0.062
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
ths+0.029
lf+0.027
eking+0.027
 nowhere+0.027
 unfortunately+0.026
Neg logit contributions
ashes-0.010
five-0.008
round-0.007
 pedal-0.007
powers-0.007
Token He
Token ID679
Feature activation-2.44e-02

Pos logit contributions
 rider+0.113
 ride+0.111
tie+0.111
five+0.107
 towards+0.106
Neg logit contributions
agg-0.311
omm-0.295
ths-0.287
Kevin-0.285
 unfortunately-0.279
Token wonders
Token ID19294
Feature activation+3.91e-03

Pos logit contributions
.+0.030
."+0.030
round+0.028
ashes+0.028
 rider+0.028
Neg logit contributions
ths-0.046
eking-0.046
agg-0.044
eling-0.042
 End-0.040
Token where
Token ID810
Feature activation-6.34e-02

Pos logit contributions
eking+0.006
ths+0.006
agg+0.006
ering+0.005
aman+0.005
Neg logit contributions
ashes-0.007
powers-0.006
."-0.006
 rider-0.006
ny-0.006
Token they
Token ID484
Feature activation-3.67e-02

Pos logit contributions
ashes+0.095
.+0.094
."+0.091
 rider+0.085
five+0.084
Neg logit contributions
ths-0.111
agg-0.107
eking-0.103
Kevin-0.097
Jess-0.096
Token went
Token ID1816
Feature activation-8.59e-02

Pos logit contributions
.+0.044
."+0.043
ashes+0.043
 Let+0.042
 rider+0.041
Neg logit contributions
eking-0.073
ths-0.072
agg-0.069
aman-0.066
Kevin-0.064
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
five+0.058
powers+0.056
 rider+0.055
ashes+0.053
 likes+0.049
Neg logit contributions
eking-0.209
ths-0.203
aman-0.197
ering-0.195
agg-0.192
Token He
Token ID679
Feature activation-2.41e-02

Pos logit contributions
.+0.089
."+0.087
ashes+0.087
 rider+0.082
five+0.080
Neg logit contributions
agg-0.356
ths-0.349
Kevin-0.331
 sudden-0.325
 unfortunately-0.324
Token hopes
Token ID7176
Feature activation+8.66e-04

Pos logit contributions
.+0.030
."+0.029
ashes+0.027
 rider+0.026
five+0.025
Neg logit contributions
ths-0.049
eking-0.048
agg-0.048
aman-0.045
Kevin-0.042
Token they
Token ID484
Feature activation-3.63e-02

Pos logit contributions
ths+0.002
agg+0.002
eking+0.002
aman+0.002
Kevin+0.002
Neg logit contributions
.-0.001
."-0.001
ashes-0.001
 He-0.001
 rider-0.001
Token are
Token ID389
Feature activation+1.04e-01

Pos logit contributions
ashes+0.045
.+0.045
."+0.042
five+0.042
 He+0.041
Neg logit contributions
ths-0.069
eking-0.068
agg-0.063
prisingly-0.062
aman-0.061