TOP ACTIVATIONS
MAX = 0.464

. There were many fun rides and games . Lucy and
Mary loved to go for rides on her bike . She
saw lots of animals and rides . She even got to
would even give the frog rides on its back .
always take Anna for special rides in his car . Anna
fun things . There were rides and games and food !
. They would go for rides in the sunshine , and
eyes and think about the rides and games she would play
in the park or for rides in their car .
loved to go on car rides with her mom my and
fun . Lucy went on rides and met new friends .
she would go on nice rides around the neighbourhood , always
It loved taking people for rides . One day , the
his sc ooter . He rides it every day in the
by would go for long rides . Even though the man
now invites everyone to hey rides and even gives them a
fair . She went on rides , ate tasty food and
day and they enjoyed the rides . They brought a huge
and all the other fun rides . Her mom said ,
excited to pay for the rides and she played for a

MIN ACTIVATIONS
MIN = -0.539

She packed up the nap kin and they both marched back
so she took a nap kin and tried to polish the
gave her a new nap kin . Then she said :
. He used the nap kin and wiped his mouth .
to give back his nap kin . The beautiful bunny agreed
So she took the nap kin , dipped it into her
eyes , took the nap kin and smiled . She said
it up . The nap kin had a sandwich inside !
it up in a nap kin . This sandwich was so
, he saw a nap kin on the floor . The
. The nap kin looked nice and tidy .
. They use the nap kin to keep their hands clean
You need a clean nap kin . And you need to
grateful for the special nap kin . Tom
The bear saw a nap kin on the ground and lifted
wanted to get the nap kin so she jumped . She
ished it with a nap kin . Tim my felt bad
it off with a nap kin ," Mom said .
covers them with the nap kin . " Here
Tom used the nap kin to clean up the apple

INTERVAL 0.213 - 0.464
CONTAINS 3.305%

and said : " It 's a net . It 's
their ball back . They thanked Leo . They said ,
?" Sam nodded . He said , " Yes , please
if he could have some ice cream , but she said
Jim , " Now it 's perfect !"

INTERVAL -0.037 - 0.213
CONTAINS 69.677%

sweep , a spider sc ur ried out ! He jumped
, a princess costume and a doctor costume . She likes
little child . She was very curious and loved to collect
me happy !" The little boy smiled and
hug and a kiss , and a cookie each .

INTERVAL -0.288 - -0.037
CONTAINS 26.071%

, mom . Let 's dance together . And then we
. After a while , they finish the puzzle
" Look , Sam , that star is so
clock to Sus ie 's bedroom wall . Sus
cr ay on ! He felt excited and grabbed it .

INTERVAL -0.539 - -0.288
CONTAINS 0.946%

in it . But over time , the bin began to
said , " It 's time for bed now ." As
to keep the tw ig if you don 't like it
were happy . <|endoftext|> L ila and Ben were playing in
loyal dog ." Jack cheer fully said , " Yes !"
Token.
Token ID13
Feature activation-2.90e-03

Pos logit contributions
rob+0.191
ons+0.180
 rides+0.176
opl+0.174
cream+0.164
Neg logit contributions
kin-0.175
 upon-0.162
 moment-0.153
 particular-0.143
isel-0.140
Token There
Token ID1318
Feature activation-5.85e-02

Pos logit contributions
kin+0.005
isel+0.005
 upon+0.005
rated+0.004
 moment+0.004
Neg logit contributions
rob-0.005
 rides-0.005
ons-0.005
opl-0.005
 cand-0.005
Token were
Token ID547
Feature activation+4.20e-02

Pos logit contributions
kin+0.113
isel+0.104
rated+0.099
 loser+0.096
 upon+0.096
Neg logit contributions
 rides-0.099
ons-0.098
rob-0.097
opl-0.085
 cand-0.085
Token many
Token ID867
Feature activation+1.23e-01

Pos logit contributions
rob+0.084
opl+0.079
ons+0.077
cream+0.073
 rides+0.071
Neg logit contributions
kin-0.068
 upon-0.067
 moment-0.060
 loser-0.057
 particular-0.056
Token fun
Token ID1257
Feature activation+1.82e-01

Pos logit contributions
rob+0.238
opl+0.217
 rides+0.212
ons+0.211
cream+0.205
Neg logit contributions
kin-0.210
 upon-0.192
 moment-0.172
 particular-0.170
ac-0.170
Token rides
Token ID17445
Feature activation+4.64e-01

Pos logit contributions
rob+0.376
 rides+0.349
ons+0.342
opl+0.339
cream+0.323
Neg logit contributions
kin-0.295
 upon-0.260
 moment-0.246
isel-0.240
rated-0.226
Token and
Token ID290
Feature activation+1.04e-02

Pos logit contributions
rob+0.973
 rides+0.924
ons+0.919
opl+0.886
 cand+0.840
Neg logit contributions
kin-0.733
 upon-0.637
 moment-0.595
isel-0.581
rated-0.566
Token games
Token ID1830
Feature activation+1.76e-01

Pos logit contributions
rob+0.017
opl+0.016
ons+0.015
 rides+0.015
cream+0.014
Neg logit contributions
kin-0.021
 moment-0.019
 upon-0.019
rated-0.018
 particular-0.017
Token.
Token ID13
Feature activation-2.57e-03

Pos logit contributions
rob+0.350
 rides+0.338
ons+0.331
opl+0.315
 cand+0.299
Neg logit contributions
kin-0.296
 upon-0.257
isel-0.250
 moment-0.243
rated-0.238
Token Lucy
Token ID22162
Feature activation-2.90e-02

Pos logit contributions
kin+0.005
isel+0.004
 upon+0.004
rated+0.004
 moment+0.004
Neg logit contributions
rob-0.005
 rides-0.005
ons-0.005
opl-0.004
 cand-0.004
Token and
Token ID290
Feature activation+1.09e-02

Pos logit contributions
kin+0.040
 upon+0.039
 moment+0.034
 don+0.031
cca+0.031
Neg logit contributions
rob-0.064
ons-0.060
opl-0.060
 rides-0.058
 cand-0.055
Token Mary
Token ID5335
Feature activation-1.38e-01

Pos logit contributions
kin+0.023
isel+0.020
 upon+0.019
rated+0.019
 loser+0.018
Neg logit contributions
 rides-0.022
rob-0.022
ons-0.021
opl-0.020
 kisses-0.019
Token loved
Token ID6151
Feature activation+5.54e-02

Pos logit contributions
kin+0.206
 upon+0.169
 moment+0.164
rated+0.153
 particular+0.152
Neg logit contributions
rob-0.313
 rides-0.285
opl-0.285
ons-0.276
pill-0.261
Token to
Token ID284
Feature activation+6.80e-02

Pos logit contributions
rob+0.139
handed+0.129
opl+0.128
odic+0.120
 course+0.114
Neg logit contributions
 upon-0.057
 thing-0.048
 moment-0.048
 particular-0.044
 time-0.043
Token go
Token ID467
Feature activation+3.89e-03

Pos logit contributions
rob+0.139
opl+0.116
ons+0.114
 rides+0.114
pill+0.112
Neg logit contributions
kin-0.123
 particular-0.108
isel-0.104
 moment-0.103
 upon-0.102
Token for
Token ID329
Feature activation-7.84e-03

Pos logit contributions
rob+0.009
pill+0.009
opl+0.009
handed+0.009
ons+0.009
Neg logit contributions
 upon-0.005
 moment-0.004
 particular-0.004
kin-0.003
 halfway-0.003
Token rides
Token ID17445
Feature activation+4.60e-01

Pos logit contributions
kin+0.016
 moment+0.015
 upon+0.015
 particular+0.015
isel+0.014
Neg logit contributions
rob-0.011
ons-0.010
opl-0.010
cream-0.009
handed-0.009
Token on
Token ID319
Feature activation-1.59e-02

Pos logit contributions
rob+0.978
ons+0.933
 rides+0.918
opl+0.912
pill+0.870
Neg logit contributions
kin-0.706
 upon-0.609
 moment-0.570
 particular-0.546
inn-0.535
Token her
Token ID607
Feature activation+4.78e-02

Pos logit contributions
kin+0.026
 upon+0.026
 particular+0.024
 moment+0.024
 halfway+0.022
Neg logit contributions
rob-0.029
ons-0.027
cream-0.026
opl-0.026
handed-0.025
Token bike
Token ID7161
Feature activation+6.68e-02

Pos logit contributions
ons+0.095
rob+0.093
pill+0.085
 course+0.084
opl+0.082
Neg logit contributions
kin-0.076
 upon-0.072
 moment-0.069
 particular-0.068
 footing-0.065
Token.
Token ID13
Feature activation-1.23e-02

Pos logit contributions
rob+0.157
ons+0.150
pill+0.150
 kisses+0.147
 cand+0.145
Neg logit contributions
 upon-0.077
kin-0.072
 particular-0.066
 moment-0.063
inn-0.057
Token She
Token ID1375
Feature activation+1.21e-01

Pos logit contributions
kin+0.024
 upon+0.021
isel+0.021
 moment+0.020
rated+0.020
Neg logit contributions
rob-0.021
 rides-0.021
ons-0.020
opl-0.019
 cand-0.018
Token saw
Token ID2497
Feature activation-5.96e-02

Pos logit contributions
 upon+0.147
kin+0.131
 moment+0.119
rated+0.111
isel+0.109
Neg logit contributions
rob-0.261
opl-0.252
ons-0.247
 cand-0.234
cream-0.230
Token lots
Token ID6041
Feature activation+1.39e-01

Pos logit contributions
kin+0.078
 upon+0.072
 moment+0.063
isel+0.063
 disaster+0.060
Neg logit contributions
rob-0.135
opl-0.129
ons-0.126
 rides-0.126
grand-0.116
Token of
Token ID286
Feature activation+6.97e-02

Pos logit contributions
rob+0.309
opl+0.276
 rides+0.272
ridge+0.268
ons+0.268
Neg logit contributions
kin-0.194
 upon-0.174
 thing-0.155
 particular-0.154
isel-0.151
Token animals
Token ID4695
Feature activation+1.12e-01

Pos logit contributions
rob+0.127
ons+0.121
 rides+0.119
opl+0.118
cream+0.108
Neg logit contributions
kin-0.120
 upon-0.112
isel-0.105
 moment-0.104
 loser-0.099
Token and
Token ID290
Feature activation+2.26e-03

Pos logit contributions
rob+0.269
opl+0.242
ons+0.242
 rides+0.233
cream+0.231
Neg logit contributions
 upon-0.144
kin-0.137
 moment-0.115
ges-0.112
 don-0.112
Token rides
Token ID17445
Feature activation+4.59e-01

Pos logit contributions
rob+0.004
ons+0.004
opl+0.004
 rides+0.004
 course+0.004
Neg logit contributions
kin-0.004
 upon-0.004
isel-0.003
 moment-0.003
rated-0.003
Token.
Token ID13
Feature activation-1.53e-02

Pos logit contributions
 rides+0.836
rob+0.810
ons+0.782
opl+0.700
 cand+0.697
Neg logit contributions
kin-0.854
isel-0.786
 upon-0.719
 loser-0.709
rated-0.709
Token She
Token ID1375
Feature activation+1.21e-01

Pos logit contributions
kin+0.034
isel+0.031
 upon+0.030
rated+0.030
 moment+0.029
Neg logit contributions
 rides-0.022
rob-0.021
ons-0.020
 cand-0.018
opl-0.018
Token even
Token ID772
Feature activation-5.72e-02

Pos logit contributions
rob+0.233
 rides+0.231
ons+0.224
opl+0.209
 cand+0.201
Neg logit contributions
kin-0.207
isel-0.179
 upon-0.178
rated-0.170
 moment-0.169
Token got
Token ID1392
Feature activation+8.90e-03

Pos logit contributions
kin+0.117
isel+0.104
 upon+0.102
rated+0.098
 moment+0.098
Neg logit contributions
rob-0.093
 rides-0.092
ons-0.088
opl-0.080
 cand-0.077
Token to
Token ID284
Feature activation+7.20e-02

Pos logit contributions
rob+0.017
ons+0.016
opl+0.016
 rides+0.016
 course+0.014
Neg logit contributions
kin-0.015
 upon-0.015
isel-0.013
 moment-0.013
cca-0.013
Token would
Token ID561
Feature activation-9.77e-02

Pos logit contributions
rob+0.196
 rides+0.182
ons+0.176
opl+0.169
 cand+0.168
Neg logit contributions
kin-0.142
 upon-0.127
 moment-0.125
ac-0.119
isel-0.112
Token even
Token ID772
Feature activation-5.81e-02

Pos logit contributions
kin+0.151
 upon+0.137
 particular+0.133
 moment+0.133
isel+0.129
Neg logit contributions
rob-0.213
ons-0.203
cream-0.188
 rides-0.187
pill-0.181
Token give
Token ID1577
Feature activation+2.71e-02

Pos logit contributions
kin+0.105
 upon+0.092
isel+0.092
 moment+0.088
rated+0.087
Neg logit contributions
rob-0.107
 rides-0.105
ons-0.102
opl-0.096
 cand-0.091
Token the
Token ID262
Feature activation-1.62e-02

Pos logit contributions
rob+0.056
 rides+0.053
ons+0.051
opl+0.051
 cand+0.046
Neg logit contributions
kin-0.043
 upon-0.039
 moment-0.038
isel-0.037
rated-0.036
Token frog
Token ID21264
Feature activation-9.00e-02

Pos logit contributions
kin+0.030
isel+0.026
 upon+0.025
rated+0.025
 moment+0.024
Neg logit contributions
rob-0.030
 rides-0.030
ons-0.029
opl-0.027
 cand-0.026
Token rides
Token ID17445
Feature activation+4.59e-01

Pos logit contributions
kin+0.134
 upon+0.125
 moment+0.118
ac+0.108
 thing+0.106
Neg logit contributions
rob-0.209
opl-0.182
 rides-0.181
ons-0.180
odic-0.164
Token on
Token ID319
Feature activation-1.31e-02

Pos logit contributions
rob+0.923
 rides+0.886
ons+0.874
opl+0.832
 cand+0.790
Neg logit contributions
kin-0.763
 upon-0.659
isel-0.631
 moment-0.631
rated-0.612
Token its
Token ID663
Feature activation-7.86e-02

Pos logit contributions
kin+0.022
 upon+0.019
isel+0.019
 moment+0.018
rated+0.018
Neg logit contributions
rob-0.026
 rides-0.025
ons-0.025
opl-0.023
 cand-0.022
Token back
Token ID736
Feature activation+6.25e-02

Pos logit contributions
kin+0.112
 moment+0.110
 upon+0.106
 footing+0.101
 particular+0.098
Neg logit contributions
rob-0.185
ons-0.179
pill-0.159
cream-0.157
 rides-0.154
Token.
Token ID13
Feature activation-1.47e-02

Pos logit contributions
rob+0.138
ons+0.128
 rides+0.128
 cand+0.118
cream+0.116
Neg logit contributions
kin-0.094
 upon-0.086
 moment-0.082
isel-0.078
 particular-0.075
Token
Token ID220
Feature activation+1.03e-01

Pos logit contributions
kin+0.022
 upon+0.021
 moment+0.020
isel+0.019
inn+0.019
Neg logit contributions
rob-0.029
 rides-0.029
ons-0.028
 cand-0.026
odic-0.026
Token always
Token ID1464
Feature activation+7.15e-02

Pos logit contributions
kin+0.146
 upon+0.137
 moment+0.131
 don+0.130
 particular+0.125
Neg logit contributions
rob-0.210
ons-0.190
pill-0.181
cream-0.180
 rides-0.179
Token take
Token ID1011
Feature activation-1.82e-02

Pos logit contributions
rob+0.154
ons+0.137
pill+0.134
 rides+0.128
opl+0.128
Neg logit contributions
kin-0.110
 upon-0.101
 moment-0.100
 don-0.099
isel-0.094
Token Anna
Token ID11735
Feature activation-1.56e-01

Pos logit contributions
kin+0.031
 upon+0.027
isel+0.027
 moment+0.026
 loser+0.025
Neg logit contributions
rob-0.036
 rides-0.033
ons-0.032
opl-0.032
cream-0.029
Token for
Token ID329
Feature activation-7.50e-03

Pos logit contributions
kin+0.332
 upon+0.306
 moment+0.293
ac+0.283
rated+0.281
Neg logit contributions
rob-0.251
 rides-0.223
ons-0.218
opl-0.211
odic-0.189
Token special
Token ID2041
Feature activation+1.01e-01

Pos logit contributions
kin+0.012
 upon+0.010
 moment+0.010
isel+0.010
 loser+0.010
Neg logit contributions
rob-0.015
ons-0.014
 rides-0.014
opl-0.014
cream-0.013
Token rides
Token ID17445
Feature activation+4.59e-01

Pos logit contributions
rob+0.168
ons+0.156
 rides+0.154
opl+0.150
pill+0.136
Neg logit contributions
kin-0.203
 moment-0.180
isel-0.175
 upon-0.174
 loser-0.169
Token in
Token ID287
Feature activation-9.21e-02

Pos logit contributions
rob+0.900
 rides+0.886
ons+0.861
opl+0.810
 cand+0.776
Neg logit contributions
kin-0.771
 upon-0.664
isel-0.661
 moment-0.630
rated-0.629
Token his
Token ID465
Feature activation+3.11e-02

Pos logit contributions
kin+0.167
isel+0.150
 upon+0.144
rated+0.143
 moment+0.136
Neg logit contributions
 rides-0.169
rob-0.166
ons-0.163
opl-0.151
 cand-0.144
Token car
Token ID1097
Feature activation+9.32e-02

Pos logit contributions
rob+0.065
ons+0.061
 rides+0.055
odic+0.055
pill+0.055
Neg logit contributions
kin-0.052
 moment-0.044
 upon-0.044
 loser-0.042
 particular-0.041
Token.
Token ID13
Feature activation-1.82e-02

Pos logit contributions
rob+0.217
ons+0.203
 rides+0.197
pill+0.192
opl+0.192
Neg logit contributions
kin-0.129
 upon-0.106
 moment-0.101
 loser-0.096
rated-0.096
Token Anna
Token ID11735
Feature activation-1.56e-01

Pos logit contributions
 upon+0.023
kin+0.022
 moment+0.021
 particular+0.020
rated+0.019
Neg logit contributions
rob-0.041
ons-0.039
 rides-0.038
opl-0.036
odic-0.036
Token fun
Token ID1257
Feature activation+1.73e-01

Pos logit contributions
rob+0.124
ons+0.114
 rides+0.113
opl+0.112
cream+0.102
Neg logit contributions
kin-0.111
 upon-0.107
 moment-0.099
isel-0.099
rated-0.095
Token things
Token ID1243
Feature activation-4.19e-02

Pos logit contributions
rob+0.365
 rides+0.347
ons+0.339
opl+0.333
cream+0.310
Neg logit contributions
kin-0.264
 upon-0.234
isel-0.224
 moment-0.222
rated-0.210
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
kin+0.060
 upon+0.056
 moment+0.052
isel+0.047
rated+0.046
Neg logit contributions
rob-0.094
opl-0.086
 rides-0.086
ons-0.085
grand-0.078
Token There
Token ID1318
Feature activation-6.42e-02

Pos logit contributions
kin+0.034
isel+0.030
 upon+0.030
rated+0.029
 moment+0.029
Neg logit contributions
 rides-0.020
rob-0.019
ons-0.018
opl-0.017
 cand-0.016
Token were
Token ID547
Feature activation+3.47e-02

Pos logit contributions
kin+0.116
 upon+0.102
isel+0.101
 moment+0.097
rated+0.096
Neg logit contributions
rob-0.118
 rides-0.116
ons-0.112
opl-0.106
 cand-0.101
Token rides
Token ID17445
Feature activation+4.59e-01

Pos logit contributions
rob+0.065
ons+0.060
opl+0.059
 rides+0.056
cream+0.054
Neg logit contributions
kin-0.061
 upon-0.059
 moment-0.054
 particular-0.051
isel-0.051
Token and
Token ID290
Feature activation+2.01e-03

Pos logit contributions
 rides+0.874
rob+0.874
ons+0.843
opl+0.786
 cand+0.758
Neg logit contributions
kin-0.790
isel-0.693
 upon-0.677
rated-0.652
 moment-0.644
Token games
Token ID1830
Feature activation+1.71e-01

Pos logit contributions
rob+0.004
opl+0.003
ons+0.003
cream+0.003
assy+0.003
Neg logit contributions
 upon-0.003
kin-0.003
 moment-0.003
 don-0.003
isel-0.003
Token and
Token ID290
Feature activation+2.32e-03

Pos logit contributions
rob+0.354
 rides+0.331
ons+0.327
opl+0.318
cream+0.298
Neg logit contributions
kin-0.280
 upon-0.247
 moment-0.232
isel-0.229
rated-0.216
Token food
Token ID2057
Feature activation+2.22e-01

Pos logit contributions
rob+0.004
ons+0.004
opl+0.004
 rides+0.003
cream+0.003
Neg logit contributions
kin-0.004
 upon-0.004
 moment-0.004
rated-0.004
isel-0.004
Token!
Token ID0
Feature activation+4.49e-02

Pos logit contributions
rob+0.499
 rides+0.458
ons+0.457
opl+0.452
cream+0.417
Neg logit contributions
kin-0.337
 upon-0.291
 moment-0.266
isel-0.247
rated-0.237
Token.
Token ID13
Feature activation-1.63e-02

Pos logit contributions
 rides+0.195
rob+0.192
ons+0.187
opl+0.173
 cand+0.167
Neg logit contributions
kin-0.185
isel-0.166
 upon-0.160
rated-0.156
 moment-0.152
Token They
Token ID1119
Feature activation+1.95e-02

Pos logit contributions
kin+0.029
 upon+0.026
isel+0.025
 moment+0.025
rated+0.024
Neg logit contributions
rob-0.030
 rides-0.029
ons-0.029
opl-0.026
 cand-0.026
Token would
Token ID561
Feature activation-9.88e-02

Pos logit contributions
rob+0.040
 rides+0.038
ons+0.038
opl+0.037
 cand+0.035
Neg logit contributions
kin-0.031
 upon-0.027
isel-0.026
 moment-0.025
rated-0.024
Token go
Token ID467
Feature activation+3.47e-03

Pos logit contributions
kin+0.162
 upon+0.146
isel+0.143
 particular+0.141
 moment+0.139
Neg logit contributions
rob-0.202
ons-0.189
 rides-0.175
opl-0.170
pill-0.169
Token for
Token ID329
Feature activation-8.11e-03

Pos logit contributions
rob+0.007
ons+0.007
opl+0.007
 rides+0.007
grand+0.007
Neg logit contributions
 upon-0.005
kin-0.005
 moment-0.005
isel-0.004
inn-0.004
Token rides
Token ID17445
Feature activation+4.58e-01

Pos logit contributions
kin+0.012
 moment+0.011
 upon+0.010
isel+0.010
 particular+0.010
Neg logit contributions
rob-0.016
ons-0.016
opl-0.015
grand-0.015
cream-0.014
Token in
Token ID287
Feature activation-9.22e-02

Pos logit contributions
rob+0.868
 rides+0.862
ons+0.831
opl+0.776
 cand+0.745
Neg logit contributions
kin-0.802
isel-0.704
 upon-0.693
rated-0.663
 moment-0.657
Token the
Token ID262
Feature activation-1.58e-02

Pos logit contributions
kin+0.156
isel+0.136
 upon+0.134
rated+0.129
 moment+0.127
Neg logit contributions
rob-0.180
 rides-0.179
ons-0.174
opl-0.163
 cand-0.156
Token sunshine
Token ID34488
Feature activation+1.54e-01

Pos logit contributions
 moment+0.025
 upon+0.025
 particular+0.024
 time+0.023
 thing+0.022
Neg logit contributions
ons-0.031
rob-0.029
grand-0.027
cream-0.026
 cand-0.026
Token,
Token ID11
Feature activation+6.70e-04

Pos logit contributions
rob+0.337
ons+0.323
 rides+0.322
opl+0.308
cream+0.295
Neg logit contributions
kin-0.230
 upon-0.198
 moment-0.193
 particular-0.170
isel-0.170
Token and
Token ID290
Feature activation+2.67e-03

Pos logit contributions
rob+0.001
ons+0.001
opl+0.001
 rides+0.001
cream+0.001
Neg logit contributions
kin-0.001
 upon-0.001
 moment-0.001
isel-0.001
rated-0.001
Token eyes
Token ID2951
Feature activation-7.66e-02

Pos logit contributions
rob+0.124
ons+0.113
 rides+0.112
opl+0.110
 course+0.105
Neg logit contributions
kin-0.064
 upon-0.058
 moment-0.050
isel-0.050
 particular-0.045
Token and
Token ID290
Feature activation+3.96e-03

Pos logit contributions
kin+0.117
 upon+0.105
 moment+0.099
isel+0.098
rated+0.095
Neg logit contributions
rob-0.167
 rides-0.155
ons-0.155
opl-0.147
 cand-0.139
Token think
Token ID892
Feature activation-1.04e-01

Pos logit contributions
rob+0.008
ons+0.008
 rides+0.008
opl+0.007
pill+0.007
Neg logit contributions
kin-0.006
 upon-0.006
isel-0.005
 moment-0.005
rated-0.005
Token about
Token ID546
Feature activation+3.32e-02

Pos logit contributions
kin+0.241
isel+0.224
rated+0.223
 loser+0.221
cca+0.211
Neg logit contributions
 rides-0.141
ons-0.135
 kisses-0.111
 cand-0.107
opl-0.106
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
rob+0.065
 rides+0.063
ons+0.062
opl+0.058
 cand+0.055
Neg logit contributions
kin-0.056
 upon-0.049
isel-0.049
 moment-0.047
rated-0.046
Token rides
Token ID17445
Feature activation+4.58e-01

Pos logit contributions
kin+0.022
 upon+0.020
isel+0.019
 moment+0.019
rated+0.018
Neg logit contributions
rob-0.024
ons-0.023
 rides-0.023
opl-0.021
 cand-0.020
Token and
Token ID290
Feature activation+4.02e-03

Pos logit contributions
rob+0.892
 rides+0.865
ons+0.843
opl+0.800
 cand+0.764
Neg logit contributions
kin-0.789
 upon-0.682
isel-0.661
 moment-0.650
rated-0.642
Token games
Token ID1830
Feature activation+1.72e-01

Pos logit contributions
rob+0.008
ons+0.007
 rides+0.007
opl+0.007
cream+0.007
Neg logit contributions
 upon-0.007
kin-0.007
 moment-0.006
 particular-0.006
isel-0.006
Token she
Token ID673
Feature activation+1.05e-01

Pos logit contributions
rob+0.340
 rides+0.327
ons+0.321
opl+0.306
 cand+0.290
Neg logit contributions
kin-0.290
 upon-0.253
isel-0.243
 moment-0.239
rated-0.232
Token would
Token ID561
Feature activation-9.53e-02

Pos logit contributions
rob+0.226
 rides+0.222
ons+0.217
opl+0.206
 cand+0.198
Neg logit contributions
kin-0.158
 upon-0.135
isel-0.133
 moment-0.127
rated-0.126
Token play
Token ID711
Feature activation+1.56e-01

Pos logit contributions
kin+0.162
 upon+0.147
isel+0.141
 moment+0.140
rated+0.134
Neg logit contributions
rob-0.187
ons-0.179
 rides-0.175
opl-0.160
 cand-0.160
Token in
Token ID287
Feature activation-9.12e-02

Pos logit contributions
rob+0.478
 rides+0.467
ons+0.457
opl+0.433
 cand+0.413
Neg logit contributions
kin-0.408
 upon-0.356
isel-0.347
 moment-0.337
rated-0.333
Token the
Token ID262
Feature activation-1.68e-02

Pos logit contributions
kin+0.155
isel+0.135
 upon+0.134
rated+0.128
 moment+0.127
Neg logit contributions
rob-0.178
 rides-0.176
ons-0.171
opl-0.160
 cand-0.154
Token park
Token ID3952
Feature activation+2.27e-01

Pos logit contributions
 particular+0.028
 upon+0.027
 moment+0.027
 thing+0.025
 time+0.025
Neg logit contributions
ons-0.034
rob-0.033
odic-0.028
cream-0.027
grand-0.027
Token or
Token ID393
Feature activation-1.64e-01

Pos logit contributions
rob+0.460
 rides+0.443
ons+0.436
opl+0.413
 cand+0.393
Neg logit contributions
kin-0.374
 upon-0.329
isel-0.312
 moment-0.311
rated-0.301
Token for
Token ID329
Feature activation-6.69e-03

Pos logit contributions
kin+0.275
 upon+0.247
 moment+0.235
isel+0.232
rated+0.224
Neg logit contributions
rob-0.324
 rides-0.309
ons-0.307
opl-0.294
 cand-0.272
Token rides
Token ID17445
Feature activation+4.58e-01

Pos logit contributions
kin+0.011
 upon+0.010
 moment+0.010
isel+0.010
 particular+0.009
Neg logit contributions
rob-0.013
ons-0.012
 rides-0.012
opl-0.012
cream-0.011
Token in
Token ID287
Feature activation-9.07e-02

Pos logit contributions
rob+0.877
 rides+0.873
ons+0.842
opl+0.787
 cand+0.757
Neg logit contributions
kin-0.790
isel-0.694
 upon-0.683
rated-0.652
 moment-0.647
Token their
Token ID511
Feature activation-4.65e-02

Pos logit contributions
kin+0.164
isel+0.147
rated+0.141
 upon+0.140
 moment+0.132
Neg logit contributions
 rides-0.170
rob-0.167
ons-0.162
opl-0.151
 kisses-0.144
Token car
Token ID1097
Feature activation+9.38e-02

Pos logit contributions
kin+0.076
 moment+0.074
 upon+0.074
 particular+0.070
 time+0.065
Neg logit contributions
rob-0.091
ons-0.088
odic-0.080
cream-0.079
opl-0.077
Token.
Token ID13
Feature activation-1.39e-02

Pos logit contributions
rob+0.229
ons+0.214
opl+0.205
pill+0.204
odic+0.199
Neg logit contributions
kin-0.112
 upon-0.103
 moment-0.090
 particular-0.087
ac-0.083
Token
Token ID220
Feature activation+1.02e-01

Pos logit contributions
kin+0.026
isel+0.023
 upon+0.023
rated+0.022
 moment+0.022
Neg logit contributions
rob-0.025
 rides-0.024
ons-0.023
opl-0.022
 cand-0.021
Token loved
Token ID6151
Feature activation+5.79e-02

Pos logit contributions
rob+0.240
 rides+0.231
ons+0.226
opl+0.224
 cand+0.207
Neg logit contributions
kin-0.210
 upon-0.178
 moment-0.174
rated-0.168
isel-0.164
Token to
Token ID284
Feature activation+7.30e-02

Pos logit contributions
rob+0.146
opl+0.143
handed+0.140
odic+0.129
 course+0.127
Neg logit contributions
 upon-0.055
 moment-0.046
 thing-0.044
 time-0.040
 particular-0.037
Token go
Token ID467
Feature activation+6.37e-03

Pos logit contributions
rob+0.154
opl+0.133
pill+0.128
ons+0.128
handed+0.127
Neg logit contributions
kin-0.125
 particular-0.113
 moment-0.104
isel-0.103
 upon-0.102
Token on
Token ID319
Feature activation-1.20e-02

Pos logit contributions
rob+0.015
opl+0.014
pill+0.014
handed+0.014
ons+0.014
Neg logit contributions
 upon-0.008
 moment-0.007
 particular-0.006
kin-0.006
inn-0.005
Token car
Token ID1097
Feature activation+9.50e-02

Pos logit contributions
 upon+0.021
 moment+0.020
 particular+0.020
kin+0.019
 time+0.018
Neg logit contributions
rob-0.019
ons-0.019
opl-0.019
cream-0.018
grand-0.017
Token rides
Token ID17445
Feature activation+4.58e-01

Pos logit contributions
pill+0.226
 kisses+0.212
ridge+0.209
odic+0.209
opl+0.209
Neg logit contributions
 upon-0.083
 particular-0.075
 thing-0.075
 if-0.072
kin-0.072
Token with
Token ID351
Feature activation+3.43e-02

Pos logit contributions
rob+0.927
 rides+0.894
ons+0.893
opl+0.858
 cand+0.811
Neg logit contributions
kin-0.739
 upon-0.646
 moment-0.609
isel-0.596
rated-0.587
Token her
Token ID607
Feature activation+5.13e-02

Pos logit contributions
rob+0.078
opl+0.070
 rides+0.068
ons+0.066
cream+0.066
Neg logit contributions
kin-0.045
 upon-0.041
 particular-0.040
 moment-0.036
isel-0.036
Token mom
Token ID1995
Feature activation-1.78e-01

Pos logit contributions
rob+0.112
 rides+0.110
ons+0.108
opl+0.102
 cand+0.098
Neg logit contributions
kin-0.076
 upon-0.065
isel-0.064
 moment-0.061
rated-0.059
Tokenmy
Token ID1820
Feature activation+1.67e-01

Pos logit contributions
 upon+0.316
kin+0.300
 moment+0.291
ac+0.275
 particular+0.267
Neg logit contributions
rob-0.326
 rides-0.311
opl-0.294
ons-0.290
pill-0.287
Token and
Token ID290
Feature activation+4.26e-03

Pos logit contributions
rob+0.367
 rides+0.354
ons+0.345
opl+0.342
pill+0.317
Neg logit contributions
kin-0.241
 upon-0.223
 moment-0.204
inn-0.190
ac-0.187
Token fun
Token ID1257
Feature activation+1.75e-01

Pos logit contributions
rob+0.104
ons+0.104
opl+0.097
 rides+0.092
ridge+0.085
Neg logit contributions
kin-0.137
 upon-0.129
 moment-0.124
isel-0.119
rated-0.118
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
rob+0.348
 rides+0.337
ons+0.332
opl+0.316
 cand+0.301
Neg logit contributions
kin-0.290
 upon-0.254
isel-0.248
 moment-0.241
rated-0.236
Token Lucy
Token ID22162
Feature activation-3.23e-02

Pos logit contributions
kin+0.020
 upon+0.017
isel+0.017
 moment+0.016
rated+0.016
Neg logit contributions
rob-0.024
 rides-0.024
ons-0.023
opl-0.022
 cand-0.021
Token went
Token ID1816
Feature activation+2.92e-02

Pos logit contributions
kin+0.046
 upon+0.046
 moment+0.039
isel+0.038
cca+0.037
Neg logit contributions
rob-0.070
opl-0.066
ons-0.064
 rides-0.062
 cand-0.059
Token on
Token ID319
Feature activation-1.53e-02

Pos logit contributions
rob+0.056
ons+0.055
 rides+0.053
opl+0.052
 cand+0.049
Neg logit contributions
kin-0.049
 upon-0.047
 moment-0.044
isel-0.042
inn-0.041
Token rides
Token ID17445
Feature activation+4.58e-01

Pos logit contributions
kin+0.026
 upon+0.023
isel+0.022
 moment+0.021
rated+0.020
Neg logit contributions
rob-0.030
 rides-0.029
ons-0.029
opl-0.028
 cand-0.026
Token and
Token ID290
Feature activation+1.45e-03

Pos logit contributions
 rides+0.822
rob+0.794
ons+0.757
opl+0.691
 cand+0.673
Neg logit contributions
kin-0.869
isel-0.804
rated-0.745
 upon-0.735
 loser-0.718
Token met
Token ID1138
Feature activation+1.60e-01

Pos logit contributions
opl+0.003
rob+0.003
ons+0.002
 rides+0.002
cream+0.002
Neg logit contributions
kin-0.003
 upon-0.002
 moment-0.002
rated-0.002
 halfway-0.002
Token new
Token ID649
Feature activation+8.43e-02

Pos logit contributions
 rides+0.238
rob+0.224
ons+0.218
 kisses+0.195
 cand+0.194
Neg logit contributions
kin-0.351
isel-0.326
rated-0.310
 upon-0.301
 loser-0.297
Token friends
Token ID2460
Feature activation+1.34e-01

Pos logit contributions
rob+0.118
 rides+0.116
ons+0.111
opl+0.101
 cand+0.095
Neg logit contributions
kin-0.191
isel-0.172
 upon-0.171
rated-0.165
 moment-0.164
Token.
Token ID13
Feature activation-1.19e-02

Pos logit contributions
rob+0.254
 rides+0.254
ons+0.244
opl+0.227
 cand+0.219
Neg logit contributions
kin-0.234
isel-0.205
 upon-0.200
rated-0.194
 moment-0.191
Token she
Token ID673
Feature activation+1.02e-01

Pos logit contributions
kin+0.102
isel+0.090
 upon+0.088
rated+0.086
 moment+0.084
Neg logit contributions
 rides-0.091
rob-0.091
ons-0.088
opl-0.080
 cand-0.079
Token would
Token ID561
Feature activation-9.74e-02

Pos logit contributions
rob+0.223
opl+0.212
ons+0.208
 rides+0.201
handed+0.193
Neg logit contributions
kin-0.144
 upon-0.131
isel-0.123
 moment-0.118
rated-0.115
Token go
Token ID467
Feature activation+1.67e-03

Pos logit contributions
kin+0.167
 upon+0.153
isel+0.150
 particular+0.147
 moment+0.145
Neg logit contributions
rob-0.201
ons-0.176
pill-0.168
 rides-0.165
cream-0.163
Token on
Token ID319
Feature activation-1.80e-02

Pos logit contributions
rob+0.003
ons+0.003
opl+0.003
pill+0.003
 rides+0.003
Neg logit contributions
 upon-0.003
kin-0.002
 moment-0.002
 particular-0.002
inn-0.002
Token nice
Token ID3621
Feature activation+6.41e-02

Pos logit contributions
kin+0.028
 upon+0.026
 moment+0.025
isel+0.024
 particular+0.023
Neg logit contributions
rob-0.036
ons-0.034
 rides-0.034
opl-0.033
cream-0.032
Token rides
Token ID17445
Feature activation+4.57e-01

Pos logit contributions
rob+0.103
ons+0.089
cream+0.089
opl+0.089
pill+0.086
Neg logit contributions
kin-0.124
 moment-0.118
 upon-0.117
isel-0.113
 particular-0.108
Token around
Token ID1088
Feature activation-4.95e-02

Pos logit contributions
rob+0.912
 rides+0.881
ons+0.868
opl+0.825
 cand+0.786
Neg logit contributions
kin-0.762
 upon-0.662
isel-0.632
 moment-0.630
rated-0.606
Token the
Token ID262
Feature activation-1.72e-02

Pos logit contributions
kin+0.093
isel+0.085
rated+0.081
 upon+0.079
 loser+0.076
Neg logit contributions
 rides-0.090
rob-0.088
ons-0.086
opl-0.078
 course-0.076
Token neighbourhood
Token ID19495
Feature activation+9.84e-02

Pos logit contributions
kin+0.036
 upon+0.033
 moment+0.032
isel+0.031
 loser+0.030
Neg logit contributions
rob-0.028
ons-0.025
 rides-0.025
opl-0.024
pill-0.022
Token,
Token ID11
Feature activation-2.43e-03

Pos logit contributions
rob+0.232
ons+0.214
opl+0.210
 rides+0.202
 kisses+0.197
Neg logit contributions
kin-0.123
 upon-0.115
 moment-0.110
 particular-0.092
 runner-0.091
Token always
Token ID1464
Feature activation+7.03e-02

Pos logit contributions
 upon+0.004
kin+0.004
 moment+0.004
isel+0.003
 particular+0.003
Neg logit contributions
rob-0.005
ons-0.005
 rides-0.004
opl-0.004
cream-0.004
Token It
Token ID632
Feature activation-1.14e-01

Pos logit contributions
kin+0.027
 upon+0.025
isel+0.024
 moment+0.024
 particular+0.022
Neg logit contributions
rob-0.033
 rides-0.032
ons-0.031
opl-0.029
 cand-0.029
Token loved
Token ID6151
Feature activation+5.51e-02

Pos logit contributions
kin+0.167
 upon+0.142
 moment+0.138
rated+0.135
isel+0.134
Neg logit contributions
rob-0.244
ons-0.239
 rides-0.236
opl-0.228
 cand-0.217
Token taking
Token ID2263
Feature activation+7.84e-02

Pos logit contributions
rob+0.110
ons+0.103
 rides+0.102
opl+0.099
handed+0.095
Neg logit contributions
kin-0.085
 upon-0.079
 moment-0.078
isel-0.074
 particular-0.070
Token people
Token ID661
Feature activation+2.46e-02

Pos logit contributions
rob+0.142
ons+0.129
 rides+0.127
opl+0.124
odic+0.116
Neg logit contributions
kin-0.139
isel-0.124
 upon-0.123
 moment-0.122
rated-0.117
Token for
Token ID329
Feature activation-6.34e-03

Pos logit contributions
rob+0.053
opl+0.047
pill+0.045
 course+0.044
ons+0.044
Neg logit contributions
 upon-0.036
kin-0.035
 moment-0.034
 don-0.031
art-0.031
Token rides
Token ID17445
Feature activation+4.57e-01

Pos logit contributions
kin+0.010
isel+0.009
 moment+0.009
 upon+0.009
 loser+0.008
Neg logit contributions
rob-0.012
ons-0.012
 rides-0.011
opl-0.011
pill-0.011
Token.
Token ID13
Feature activation-1.59e-02

Pos logit contributions
rob+0.867
 rides+0.865
ons+0.833
opl+0.778
 cand+0.745
Neg logit contributions
kin-0.797
isel-0.701
 upon-0.689
rated-0.659
 moment-0.653
Token One
Token ID1881
Feature activation-3.49e-02

Pos logit contributions
kin+0.027
 upon+0.024
isel+0.023
 moment+0.023
rated+0.022
Neg logit contributions
rob-0.030
 rides-0.030
ons-0.029
opl-0.027
 cand-0.026
Token day
Token ID1110
Feature activation-5.21e-02

Pos logit contributions
kin+0.060
isel+0.054
 upon+0.051
rated+0.049
inn+0.048
Neg logit contributions
 rides-0.067
rob-0.066
ons-0.064
opl-0.061
 cand-0.057
Token,
Token ID11
Feature activation+1.56e-03

Pos logit contributions
kin+0.125
rated+0.118
isel+0.114
ac+0.109
uzz+0.108
Neg logit contributions
 rides-0.070
ons-0.068
rob-0.059
 cand-0.055
 course-0.054
Token the
Token ID262
Feature activation-1.53e-02

Pos logit contributions
 rides+0.003
ons+0.002
rob+0.002
 course+0.002
 cand+0.002
Neg logit contributions
kin-0.003
isel-0.003
rated-0.003
inn-0.003
ac-0.003
Token his
Token ID465
Feature activation+3.58e-02

Pos logit contributions
rob+0.174
opl+0.164
odic+0.149
ons+0.148
 rides+0.147
Neg logit contributions
 upon-0.111
kin-0.106
 moment-0.098
 thing-0.093
 particular-0.093
Token sc
Token ID629
Feature activation+3.23e-01

Pos logit contributions
rob+0.083
 rides+0.081
ons+0.080
opl+0.076
 cand+0.071
Neg logit contributions
kin-0.049
 upon-0.041
isel-0.039
 moment-0.039
 particular-0.036
Tokenooter
Token ID25141
Feature activation+2.01e-01

Pos logit contributions
rob+0.660
 rides+0.572
ons+0.551
 course+0.537
 cand+0.512
Neg logit contributions
kin-0.578
 upon-0.572
uzz-0.520
isel-0.514
inn-0.509
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
rob+0.516
ons+0.489
pill+0.460
opl+0.456
odic+0.447
Neg logit contributions
kin-0.207
 upon-0.169
 moment-0.154
 thing-0.153
 particular-0.148
Token He
Token ID679
Feature activation+3.49e-02

Pos logit contributions
kin+0.025
 upon+0.022
rated+0.022
isel+0.021
 footing+0.021
Neg logit contributions
 rides-0.016
rob-0.014
opl-0.013
ons-0.013
 course-0.012
Token rides
Token ID17445
Feature activation+4.57e-01

Pos logit contributions
rob+0.070
ons+0.068
 rides+0.067
opl+0.064
 cand+0.062
Neg logit contributions
kin-0.055
 upon-0.050
isel-0.046
 moment-0.045
 particular-0.044
Token it
Token ID340
Feature activation-1.86e-01

Pos logit contributions
 rides+0.888
rob+0.844
ons+0.808
opl+0.728
 cand+0.713
Neg logit contributions
kin-0.836
isel-0.754
rated-0.713
 upon-0.689
 loser-0.670
Token every
Token ID790
Feature activation+2.80e-02

Pos logit contributions
kin+0.329
isel+0.291
 upon+0.277
rated+0.270
 moment+0.264
Neg logit contributions
 rides-0.352
rob-0.350
ons-0.334
opl-0.313
 cand-0.297
Token day
Token ID1110
Feature activation-4.80e-02

Pos logit contributions
 rides+0.052
rob+0.051
ons+0.048
opl+0.046
 course+0.044
Neg logit contributions
kin-0.050
isel-0.046
 upon-0.044
rated-0.041
 loser-0.040
Token in
Token ID287
Feature activation-8.56e-02

Pos logit contributions
kin+0.069
 upon+0.063
 moment+0.057
isel+0.056
inn+0.055
Neg logit contributions
rob-0.108
ons-0.100
 rides-0.099
opl-0.095
 cand-0.092
Token the
Token ID262
Feature activation-1.15e-02

Pos logit contributions
kin+0.163
isel+0.147
rated+0.146
 upon+0.139
inn+0.132
Neg logit contributions
 rides-0.153
rob-0.148
ons-0.143
opl-0.137
 course-0.129
Tokenby
Token ID1525
Feature activation-1.64e-01

Pos logit contributions
rob+0.170
 rides+0.168
ons+0.162
opl+0.157
 cand+0.151
Neg logit contributions
kin-0.076
 upon-0.062
isel-0.059
 moment-0.056
rated-0.055
Token would
Token ID561
Feature activation-9.83e-02

Pos logit contributions
kin+0.252
 upon+0.218
ac+0.203
isel+0.202
 moment+0.200
Neg logit contributions
rob-0.339
 rides-0.315
opl-0.305
ons-0.301
 cand-0.292
Token go
Token ID467
Feature activation+3.74e-03

Pos logit contributions
kin+0.152
 upon+0.134
isel+0.133
 particular+0.133
 moment+0.128
Neg logit contributions
rob-0.218
ons-0.198
pill-0.184
 rides-0.182
cream-0.180
Token for
Token ID329
Feature activation-8.72e-03

Pos logit contributions
rob+0.008
ons+0.008
opl+0.008
pill+0.008
 cand+0.008
Neg logit contributions
 upon-0.005
 moment-0.005
kin-0.004
inn-0.004
 particular-0.004
Token long
Token ID890
Feature activation-5.83e-02

Pos logit contributions
kin+0.013
 moment+0.012
isel+0.011
 upon+0.011
 disaster+0.011
Neg logit contributions
ons-0.017
rob-0.017
opl-0.016
grand-0.015
 rides-0.015
Token rides
Token ID17445
Feature activation+4.57e-01

Pos logit contributions
kin+0.116
 moment+0.112
 upon+0.111
isel+0.106
rated+0.105
Neg logit contributions
rob-0.084
ons-0.075
cream-0.073
odic-0.073
opl-0.072
Token.
Token ID13
Feature activation-1.54e-02

Pos logit contributions
rob+0.904
 rides+0.871
ons+0.867
opl+0.822
 cand+0.786
Neg logit contributions
kin-0.758
 upon-0.659
isel-0.634
 moment-0.627
rated-0.608
Token Even
Token ID3412
Feature activation-8.47e-03

Pos logit contributions
kin+0.024
isel+0.022
 upon+0.022
 moment+0.021
inn+0.020
Neg logit contributions
rob-0.031
ons-0.030
 rides-0.029
opl-0.027
 cand-0.026
Token though
Token ID996
Feature activation-2.36e-01

Pos logit contributions
kin+0.013
isel+0.011
rated+0.010
 upon+0.010
OO+0.010
Neg logit contributions
 rides-0.019
rob-0.018
ons-0.017
opl-0.016
 cand-0.016
Token the
Token ID262
Feature activation-1.24e-02

Pos logit contributions
kin+0.471
isel+0.418
rated+0.409
 upon+0.398
inn+0.386
Neg logit contributions
 rides-0.411
rob-0.394
ons-0.377
opl-0.344
 cand-0.343
Token man
Token ID582
Feature activation+2.10e-02

Pos logit contributions
kin+0.025
 upon+0.023
 moment+0.023
rated+0.022
isel+0.022
Neg logit contributions
rob-0.020
ons-0.020
 rides-0.018
opl-0.017
cream-0.016
Token now
Token ID783
Feature activation+4.57e-03

Pos logit contributions
rob+0.240
 rides+0.220
ons+0.216
opl+0.215
 cand+0.196
Neg logit contributions
kin-0.190
 upon-0.162
 moment-0.155
isel-0.152
ac-0.145
Token invites
Token ID27671
Feature activation+1.33e-01

Pos logit contributions
rob+0.009
 rides+0.008
ons+0.008
opl+0.008
 cand+0.008
Neg logit contributions
kin-0.008
 upon-0.007
isel-0.007
 moment-0.007
rated-0.007
Token everyone
Token ID2506
Feature activation-5.42e-02

Pos logit contributions
rob+0.281
 rides+0.260
ons+0.252
opl+0.250
cream+0.233
Neg logit contributions
kin-0.210
 upon-0.193
 moment-0.180
isel-0.175
rated-0.167
Token to
Token ID284
Feature activation+6.36e-02

Pos logit contributions
kin+0.092
 upon+0.086
 moment+0.080
isel+0.076
ac+0.074
Neg logit contributions
rob-0.108
 rides-0.100
ons-0.097
opl-0.096
 cand-0.089
Token hey
Token ID17207
Feature activation-1.35e-01

Pos logit contributions
rob+0.131
 rides+0.114
ons+0.112
opl+0.109
cream+0.108
Neg logit contributions
kin-0.110
 upon-0.101
 moment-0.096
isel-0.093
 particular-0.091
Token rides
Token ID17445
Feature activation+4.57e-01

Pos logit contributions
kin+0.243
isel+0.215
 upon+0.208
rated+0.202
 moment+0.200
Neg logit contributions
 rides-0.247
rob-0.246
ons-0.241
opl-0.221
 cand-0.213
Token and
Token ID290
Feature activation-5.65e-03

Pos logit contributions
rob+0.891
 rides+0.879
ons+0.853
opl+0.802
 cand+0.768
Neg logit contributions
kin-0.773
 upon-0.667
isel-0.667
 moment-0.633
rated-0.632
Token even
Token ID772
Feature activation-6.38e-02

Pos logit contributions
kin+0.009
 upon+0.009
 moment+0.009
isel+0.008
 don+0.008
Neg logit contributions
rob-0.012
opl-0.010
 rides-0.010
ons-0.010
cream-0.010
Token gives
Token ID3607
Feature activation+1.52e-01

Pos logit contributions
kin+0.111
 upon+0.098
isel+0.096
 moment+0.093
rated+0.091
Neg logit contributions
rob-0.123
 rides-0.119
ons-0.116
opl-0.111
 cand-0.104
Token them
Token ID606
Feature activation-1.42e-01

Pos logit contributions
rob+0.316
 rides+0.308
ons+0.296
opl+0.287
 cand+0.270
Neg logit contributions
kin-0.240
 upon-0.208
isel-0.204
 moment-0.197
rated-0.193
Token a
Token ID257
Feature activation-1.77e-02

Pos logit contributions
kin+0.207
 upon+0.204
 moment+0.181
ac+0.171
 particular+0.160
Neg logit contributions
rob-0.332
opl-0.299
ons-0.278
 rides-0.277
odic-0.258
Token fair
Token ID3148
Feature activation+8.77e-02

Pos logit contributions
kin+0.088
 moment+0.078
 upon+0.076
rated+0.073
 particular+0.070
Neg logit contributions
rob-0.117
ons-0.112
 rides-0.111
opl-0.105
 cand-0.101
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
 rides+0.163
rob+0.160
ons+0.156
opl+0.145
 cand+0.141
Neg logit contributions
kin-0.156
isel-0.138
 upon-0.132
rated-0.129
 moment-0.126
Token She
Token ID1375
Feature activation+1.14e-01

Pos logit contributions
kin+0.035
isel+0.031
 upon+0.030
rated+0.030
 moment+0.029
Neg logit contributions
 rides-0.028
rob-0.028
ons-0.027
opl-0.025
 cand-0.024
Token went
Token ID1816
Feature activation+2.30e-02

Pos logit contributions
rob+0.227
 rides+0.216
ons+0.215
opl+0.204
 cand+0.194
Neg logit contributions
kin-0.191
 upon-0.169
isel-0.164
 moment-0.159
rated-0.157
Token on
Token ID319
Feature activation-2.01e-02

Pos logit contributions
rob+0.046
ons+0.044
 rides+0.043
opl+0.042
 cand+0.040
Neg logit contributions
kin-0.038
 upon-0.035
 moment-0.033
isel-0.032
inn-0.031
Token rides
Token ID17445
Feature activation+4.56e-01

Pos logit contributions
kin+0.034
 upon+0.032
 moment+0.030
isel+0.029
 particular+0.028
Neg logit contributions
rob-0.039
ons-0.036
 rides-0.036
opl-0.035
cream-0.033
Token,
Token ID11
Feature activation-4.90e-03

Pos logit contributions
 rides+0.830
rob+0.802
ons+0.767
opl+0.702
 cand+0.682
Neg logit contributions
kin-0.850
isel-0.787
rated-0.724
 upon-0.717
 loser-0.703
Token ate
Token ID15063
Feature activation+2.69e-01

Pos logit contributions
kin+0.008
 upon+0.008
 moment+0.008
isel+0.007
rated+0.007
Neg logit contributions
rob-0.009
ons-0.009
opl-0.009
 rides-0.009
 cand-0.008
Token tasty
Token ID25103
Feature activation+1.78e-01

Pos logit contributions
rob+0.463
 rides+0.442
ons+0.434
opl+0.415
grand+0.378
Neg logit contributions
kin-0.521
 upon-0.463
 moment-0.446
isel-0.445
rated-0.425
Token food
Token ID2057
Feature activation+2.20e-01

Pos logit contributions
rob+0.223
opl+0.212
grand+0.205
yard+0.200
handed+0.199
Neg logit contributions
kin-0.372
 moment-0.359
 thing-0.344
 upon-0.343
isel-0.330
Token and
Token ID290
Feature activation-8.30e-04

Pos logit contributions
rob+0.523
ons+0.483
 rides+0.479
opl+0.476
grand+0.445
Neg logit contributions
kin-0.315
 upon-0.248
 moment-0.242
 particular-0.218
inn-0.206
Token day
Token ID1110
Feature activation-5.36e-02

Pos logit contributions
 rides+0.112
rob+0.108
ons+0.100
opl+0.095
 cand+0.095
Neg logit contributions
kin-0.144
isel-0.136
 upon-0.127
rated-0.127
 loser-0.125
Token and
Token ID290
Feature activation-1.47e-03

Pos logit contributions
kin+0.089
 upon+0.078
isel+0.075
 moment+0.074
rated+0.071
Neg logit contributions
rob-0.109
 rides-0.104
ons-0.102
opl-0.097
 cand-0.093
Token they
Token ID484
Feature activation-7.60e-03

Pos logit contributions
kin+0.002
isel+0.002
 loser+0.002
inn+0.002
rated+0.002
Neg logit contributions
 rides-0.003
ons-0.003
rob-0.003
opl-0.003
 course-0.003
Token enjoyed
Token ID8359
Feature activation+9.70e-02

Pos logit contributions
kin+0.014
isel+0.013
 loser+0.012
rated+0.012
 moment+0.012
Neg logit contributions
 rides-0.013
rob-0.013
ons-0.013
opl-0.011
 cand-0.011
Token the
Token ID262
Feature activation-1.91e-02

Pos logit contributions
rob+0.159
 rides+0.157
ons+0.151
opl+0.139
 cand+0.133
Neg logit contributions
kin-0.196
isel-0.174
 upon-0.173
rated-0.168
 moment-0.165
Token rides
Token ID17445
Feature activation+4.56e-01

Pos logit contributions
kin+0.035
 upon+0.031
 moment+0.031
isel+0.029
rated+0.029
Neg logit contributions
rob-0.035
ons-0.034
 rides-0.033
opl-0.032
pill-0.030
Token.
Token ID13
Feature activation-1.79e-02

Pos logit contributions
rob+0.927
 rides+0.894
ons+0.884
opl+0.842
 cand+0.801
Neg logit contributions
kin-0.747
 upon-0.641
isel-0.613
 moment-0.611
rated-0.596
Token They
Token ID1119
Feature activation+1.65e-02

Pos logit contributions
kin+0.043
 loser+0.037
isel+0.036
rated+0.035
ac+0.034
Neg logit contributions
 rides-0.025
ons-0.023
rob-0.022
opl-0.020
 kisses-0.020
Token brought
Token ID3181
Feature activation+9.90e-02

Pos logit contributions
 rides+0.029
rob+0.029
ons+0.028
opl+0.026
 cand+0.025
Neg logit contributions
kin-0.031
isel-0.027
 upon-0.027
rated-0.026
 moment-0.026
Token a
Token ID257
Feature activation-1.35e-02

Pos logit contributions
rob+0.201
 rides+0.187
ons+0.187
opl+0.186
pill+0.169
Neg logit contributions
kin-0.161
 upon-0.144
isel-0.138
 moment-0.137
rated-0.128
Token huge
Token ID3236
Feature activation+2.50e-02

Pos logit contributions
kin+0.024
 upon+0.022
 moment+0.021
isel+0.020
 particular+0.019
Neg logit contributions
rob-0.027
ons-0.025
 rides-0.025
opl-0.025
pill-0.023
Token and
Token ID290
Feature activation-8.25e-04

Pos logit contributions
kin+0.004
 upon+0.003
 moment+0.003
rated+0.003
isel+0.003
Neg logit contributions
rob-0.006
 rides-0.006
 kisses-0.006
ons-0.006
opl-0.006
Token all
Token ID477
Feature activation+9.09e-02

Pos logit contributions
kin+0.001
isel+0.001
 upon+0.001
rated+0.001
 moment+0.001
Neg logit contributions
rob-0.002
 rides-0.002
ons-0.001
opl-0.001
 cand-0.001
Token the
Token ID262
Feature activation-1.88e-02

Pos logit contributions
rob+0.182
 rides+0.176
ons+0.169
opl+0.162
 cand+0.155
Neg logit contributions
kin-0.152
 upon-0.136
isel-0.132
 moment-0.130
rated-0.128
Token other
Token ID584
Feature activation+1.09e-01

Pos logit contributions
kin+0.038
isel+0.034
 upon+0.033
rated+0.032
 moment+0.032
Neg logit contributions
rob-0.031
 rides-0.031
ons-0.029
opl-0.027
 cand-0.026
Token fun
Token ID1257
Feature activation+1.72e-01

Pos logit contributions
rob+0.187
 rides+0.186
ons+0.179
opl+0.165
 cand+0.159
Neg logit contributions
kin-0.211
isel-0.186
 upon-0.184
rated-0.178
 moment-0.176
Token rides
Token ID17445
Feature activation+4.56e-01

Pos logit contributions
rob+0.318
 rides+0.312
ons+0.302
opl+0.285
 cand+0.270
Neg logit contributions
kin-0.311
 upon-0.272
isel-0.271
 moment-0.259
rated-0.258
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
 rides+0.853
rob+0.836
ons+0.811
opl+0.742
 cand+0.719
Neg logit contributions
kin-0.815
isel-0.739
 upon-0.698
rated-0.677
 moment-0.662
Token Her
Token ID2332
Feature activation+1.63e-01

Pos logit contributions
kin+0.040
isel+0.035
rated+0.034
 upon+0.034
 moment+0.034
Neg logit contributions
 rides-0.022
ons-0.021
rob-0.021
opl-0.019
 kisses-0.018
Token mom
Token ID1995
Feature activation-1.84e-01

Pos logit contributions
 rides+0.361
ons+0.329
rob+0.327
 cand+0.317
opl+0.312
Neg logit contributions
kin-0.233
rated-0.216
isel-0.211
inn-0.195
 upon-0.194
Token said
Token ID531
Feature activation+2.16e-01

Pos logit contributions
 upon+0.328
kin+0.314
 moment+0.283
cca+0.274
ac+0.271
Neg logit contributions
rob-0.349
opl-0.327
 rides-0.314
pill-0.284
ons-0.283
Token,
Token ID11
Feature activation-7.73e-04

Pos logit contributions
 rides+0.349
ons+0.347
rob+0.325
 cand+0.318
 kisses+0.300
Neg logit contributions
kin-0.423
isel-0.394
rated-0.390
 upon-0.373
inn-0.368
Token excited
Token ID6568
Feature activation-7.57e-02

Pos logit contributions
kin+0.002
 upon+0.002
 moment+0.002
rated+0.002
 don+0.002
Neg logit contributions
rob-0.003
opl-0.003
ons-0.003
pill-0.002
 course-0.002
Token to
Token ID284
Feature activation+6.79e-02

Pos logit contributions
kin+0.124
 upon+0.115
 moment+0.108
isel+0.105
rated+0.105
Neg logit contributions
rob-0.155
 rides-0.145
ons-0.142
opl-0.139
 cand-0.126
Token pay
Token ID1414
Feature activation+1.77e-01

Pos logit contributions
rob+0.139
ons+0.127
 rides+0.124
pill+0.122
 cand+0.118
Neg logit contributions
kin-0.115
isel-0.100
 particular-0.097
 moment-0.097
 upon-0.095
Token for
Token ID329
Feature activation-9.48e-03

Pos logit contributions
rob+0.334
 rides+0.331
ons+0.320
opl+0.299
 cand+0.287
Neg logit contributions
kin-0.312
isel-0.272
 upon-0.270
rated-0.258
 moment-0.257
Token the
Token ID262
Feature activation-1.61e-02

Pos logit contributions
kin+0.015
 upon+0.013
isel+0.013
 moment+0.013
 particular+0.012
Neg logit contributions
rob-0.019
ons-0.018
 rides-0.018
opl-0.017
cream-0.016
Token rides
Token ID17445
Feature activation+4.56e-01

Pos logit contributions
kin+0.033
 moment+0.031
 upon+0.031
isel+0.029
 loser+0.029
Neg logit contributions
rob-0.025
ons-0.025
 rides-0.022
opl-0.021
cream-0.021
Token and
Token ID290
Feature activation-1.92e-03

Pos logit contributions
rob+0.959
 rides+0.899
ons+0.893
opl+0.859
 cand+0.814
Neg logit contributions
kin-0.731
 upon-0.624
 moment-0.600
rated-0.570
isel-0.566
Token she
Token ID673
Feature activation+1.03e-01

Pos logit contributions
kin+0.003
 upon+0.003
 moment+0.003
 don+0.003
 halfway+0.003
Neg logit contributions
rob-0.004
ons-0.003
opl-0.003
pill-0.003
odic-0.003
Token played
Token ID2826
Feature activation+2.30e-01

Pos logit contributions
rob+0.205
ons+0.192
opl+0.189
 rides+0.178
 cand+0.172
Neg logit contributions
kin-0.170
 upon-0.148
isel-0.137
 moment-0.135
rated-0.133
Token for
Token ID329
Feature activation-8.90e-03

Pos logit contributions
 rides+0.414
rob+0.408
ons+0.386
opl+0.357
 cand+0.343
Neg logit contributions
kin-0.430
isel-0.392
 upon-0.379
rated-0.374
 moment-0.360
Token a
Token ID257
Feature activation-1.39e-02

Pos logit contributions
kin+0.015
 upon+0.012
isel+0.012
 moment+0.012
rated+0.012
Neg logit contributions
rob-0.018
 rides-0.017
ons-0.017
opl-0.016
 cand-0.015
Token She
Token ID1375
Feature activation+9.82e-02

Pos logit contributions
kin+0.062
 upon+0.056
isel+0.054
 moment+0.053
rated+0.052
Neg logit contributions
rob-0.062
 rides-0.060
ons-0.058
opl-0.054
 cand-0.052
Token packed
Token ID11856
Feature activation+5.51e-02

Pos logit contributions
rob+0.199
 rides+0.184
ons+0.184
opl+0.177
 cand+0.168
Neg logit contributions
kin-0.161
 upon-0.147
isel-0.138
 moment-0.134
rated-0.133
Token up
Token ID510
Feature activation-7.07e-02

Pos logit contributions
rob+0.106
 rides+0.100
ons+0.097
opl+0.097
pill+0.089
Neg logit contributions
kin-0.096
 upon-0.086
isel-0.081
 moment-0.081
rated-0.077
Token the
Token ID262
Feature activation-3.15e-02

Pos logit contributions
kin+0.121
 upon+0.113
 moment+0.104
isel+0.100
 particular+0.098
Neg logit contributions
rob-0.134
opl-0.124
ons-0.123
 rides-0.122
odic-0.112
Token nap
Token ID25422
Feature activation+5.41e-02

Pos logit contributions
kin+0.061
 upon+0.056
 moment+0.054
isel+0.051
rated+0.050
Neg logit contributions
rob-0.054
ons-0.051
 rides-0.050
opl-0.049
odic-0.043
Tokenkin
Token ID5116
Feature activation-5.16e-01

Pos logit contributions
rob+0.163
 rides+0.162
ons+0.159
opl+0.152
 cand+0.149
Neg logit contributions
kin-0.034
isel-0.022
 upon-0.022
rated-0.018
 moment-0.018
Token and
Token ID290
Feature activation-9.73e-03

Pos logit contributions
kin+0.825
 upon+0.700
 moment+0.619
inn+0.567
ac+0.555
Neg logit contributions
rob-1.210
 rides-1.125
opl-1.119
ons-1.063
pill-1.025
Token they
Token ID484
Feature activation-1.47e-02

Pos logit contributions
kin+0.017
 upon+0.015
 moment+0.014
rated+0.013
isel+0.013
Neg logit contributions
opl-0.019
rob-0.019
ons-0.018
 rides-0.017
pill-0.017
Token both
Token ID1111
Feature activation+7.89e-02

Pos logit contributions
kin+0.027
 upon+0.024
isel+0.022
 moment+0.022
rated+0.021
Neg logit contributions
rob-0.028
opl-0.026
ons-0.026
 rides-0.026
pill-0.024
Token marched
Token ID23558
Feature activation-8.22e-02

Pos logit contributions
rob+0.148
 rides+0.138
ons+0.138
opl+0.135
 cand+0.122
Neg logit contributions
kin-0.148
 upon-0.128
isel-0.123
 moment-0.121
rated-0.121
Token back
Token ID736
Feature activation+4.74e-02

Pos logit contributions
kin+0.155
isel+0.139
 upon+0.131
rated+0.131
 loser+0.126
Neg logit contributions
 rides-0.148
rob-0.144
ons-0.137
opl-0.125
 cand-0.123
Token so
Token ID523
Feature activation+1.83e-01

Pos logit contributions
kin+0.025
 upon+0.025
isel+0.023
 moment+0.023
 particular+0.021
Neg logit contributions
rob-0.032
 rides-0.028
opl-0.028
ons-0.028
handed-0.025
Token she
Token ID673
Feature activation+9.28e-02

Pos logit contributions
 rides+0.231
ons+0.227
rob+0.222
 cand+0.192
opl+0.188
Neg logit contributions
kin-0.431
isel-0.400
rated-0.393
 upon-0.382
 moment-0.373
Token took
Token ID1718
Feature activation+2.24e-02

Pos logit contributions
rob+0.170
 rides+0.166
ons+0.160
opl+0.154
 cand+0.143
Neg logit contributions
kin-0.171
isel-0.149
 upon-0.149
rated-0.141
 moment-0.141
Token a
Token ID257
Feature activation-2.51e-02

Pos logit contributions
 rides+0.041
ons+0.039
rob+0.039
 cand+0.035
 kisses+0.035
Neg logit contributions
kin-0.042
rated-0.037
 upon-0.037
isel-0.037
 moment-0.035
Token nap
Token ID25422
Feature activation+5.97e-02

Pos logit contributions
kin+0.045
rated+0.039
isel+0.039
 loser+0.038
ac+0.037
Neg logit contributions
ons-0.046
 rides-0.045
rob-0.044
 cand-0.040
 kisses-0.039
Tokenkin
Token ID5116
Feature activation-5.12e-01

Pos logit contributions
rob+0.114
ons+0.114
 rides+0.113
 cand+0.103
 course+0.100
Neg logit contributions
isel-0.090
kin-0.084
rated-0.084
 upon-0.083
 loser-0.078
Token and
Token ID290
Feature activation-1.70e-02

Pos logit contributions
kin+0.801
 upon+0.679
 moment+0.608
inn+0.592
isel+0.560
Neg logit contributions
rob-1.187
 rides-1.111
opl-1.086
ons-1.063
pill-1.016
Token tried
Token ID3088
Feature activation-5.20e-02

Pos logit contributions
kin+0.031
 upon+0.027
isel+0.026
 moment+0.025
rated+0.025
Neg logit contributions
rob-0.032
 rides-0.031
ons-0.030
opl-0.029
 cand-0.027
Token to
Token ID284
Feature activation+5.74e-02

Pos logit contributions
kin+0.112
isel+0.100
rated+0.097
 upon+0.097
 loser+0.094
Neg logit contributions
 rides-0.079
rob-0.077
ons-0.076
opl-0.067
 cand-0.067
Token polish
Token ID25245
Feature activation-7.06e-02

Pos logit contributions
 rides+0.101
rob+0.098
ons+0.096
opl+0.088
 cand+0.086
Neg logit contributions
kin-0.106
isel-0.094
 upon-0.094
rated-0.091
 moment-0.090
Token the
Token ID262
Feature activation-2.89e-02

Pos logit contributions
kin+0.132
isel+0.131
rated+0.125
 upon+0.117
 loser+0.117
Neg logit contributions
rob-0.121
ons-0.121
 rides-0.120
 cand-0.108
 kisses-0.104
Token gave
Token ID2921
Feature activation+1.68e-01

Pos logit contributions
rob+0.172
opl+0.168
 rides+0.160
ons+0.153
rell+0.136
Neg logit contributions
kin-0.229
 upon-0.212
 moment-0.192
cca-0.192
isel-0.190
Token her
Token ID607
Feature activation+3.65e-02

Pos logit contributions
 rides+0.290
ons+0.285
rob+0.282
 cand+0.260
 kisses+0.255
Neg logit contributions
kin-0.331
isel-0.295
rated-0.282
 upon-0.274
 loser-0.270
Token a
Token ID257
Feature activation-2.38e-02

Pos logit contributions
 rides+0.065
rob+0.064
ons+0.063
 kisses+0.058
 cand+0.057
Neg logit contributions
kin-0.067
isel-0.061
rated-0.058
 upon-0.057
 loser-0.056
Token new
Token ID649
Feature activation+7.06e-02

Pos logit contributions
kin+0.046
 upon+0.042
 moment+0.040
isel+0.039
 particular+0.037
Neg logit contributions
rob-0.042
 rides-0.041
ons-0.039
opl-0.038
cream-0.034
Token nap
Token ID25422
Feature activation+6.25e-02

Pos logit contributions
 rides+0.116
rob+0.113
ons+0.111
 kisses+0.103
 cand+0.101
Neg logit contributions
kin-0.135
isel-0.127
rated-0.124
 upon-0.116
 loser-0.113
Tokenkin
Token ID5116
Feature activation-5.10e-01

Pos logit contributions
rob+0.203
ons+0.203
 rides+0.202
 cand+0.192
 kisses+0.189
Neg logit contributions
isel-0.012
 upon-0.005
kin-0.004
rated-0.004
 moment+0.003
Token.
Token ID13
Feature activation-2.44e-02

Pos logit contributions
kin+0.833
 upon+0.680
 moment+0.624
inn+0.574
ac+0.566
Neg logit contributions
rob-1.173
 rides-1.094
opl-1.049
ons-1.036
pill-0.973
Token Then
Token ID3244
Feature activation-1.81e-02

Pos logit contributions
kin+0.056
rated+0.051
isel+0.050
 upon+0.048
ac+0.048
Neg logit contributions
 rides-0.034
ons-0.031
rob-0.031
 kisses-0.030
opl-0.028
Token she
Token ID673
Feature activation+9.49e-02

Pos logit contributions
kin+0.039
isel+0.037
rated+0.036
 upon+0.035
inn+0.035
Neg logit contributions
 rides-0.026
ons-0.025
rob-0.024
 cand-0.022
 kisses-0.022
Token said
Token ID531
Feature activation+2.08e-01

Pos logit contributions
rob+0.157
 rides+0.148
opl+0.147
ons+0.145
 course+0.127
Neg logit contributions
kin-0.197
 upon-0.174
isel-0.165
 moment-0.161
rated-0.160
Token:
Token ID25
Feature activation+5.24e-03

Pos logit contributions
 rides+0.340
ons+0.334
rob+0.321
 cand+0.309
 kisses+0.304
Neg logit contributions
kin-0.399
rated-0.376
isel-0.370
 upon-0.356
 particular-0.342
Token.
Token ID13
Feature activation-2.63e-02

Pos logit contributions
 rides+0.318
ons+0.313
rob+0.300
 kisses+0.283
opl+0.273
Neg logit contributions
kin-0.378
isel-0.349
 upon-0.338
rated-0.338
 loser-0.321
Token He
Token ID679
Feature activation+1.91e-02

Pos logit contributions
kin+0.056
rated+0.053
isel+0.051
 footing+0.048
 upon+0.048
Neg logit contributions
 rides-0.039
rob-0.038
ons-0.036
opl-0.034
 kisses-0.034
Token used
Token ID973
Feature activation+2.48e-02

Pos logit contributions
rob+0.035
 rides+0.034
ons+0.033
opl+0.032
 cand+0.029
Neg logit contributions
kin-0.035
 upon-0.030
isel-0.030
 moment-0.029
rated-0.028
Token the
Token ID262
Feature activation-1.93e-02

Pos logit contributions
 rides+0.044
rob+0.044
ons+0.043
opl+0.039
 cand+0.038
Neg logit contributions
kin-0.046
isel-0.040
 upon-0.040
rated-0.039
 moment-0.038
Token nap
Token ID25422
Feature activation+6.22e-02

Pos logit contributions
kin+0.037
isel+0.033
 upon+0.033
 moment+0.031
rated+0.031
Neg logit contributions
rob-0.033
 rides-0.033
ons-0.031
opl-0.029
 cand-0.028
Tokenkin
Token ID5116
Feature activation-5.09e-01

Pos logit contributions
rob+0.180
ons+0.180
 rides+0.180
 cand+0.168
opl+0.166
Neg logit contributions
kin-0.034
isel-0.032
rated-0.028
 upon-0.028
 moment-0.022
Token and
Token ID290
Feature activation-8.99e-03

Pos logit contributions
kin+0.901
 upon+0.794
 moment+0.731
isel+0.710
ac+0.684
Neg logit contributions
rob-1.050
 rides-0.965
opl-0.930
ons-0.928
pill-0.840
Token wiped
Token ID21122
Feature activation+1.89e-03

Pos logit contributions
kin+0.017
 upon+0.014
isel+0.014
 moment+0.014
rated+0.013
Neg logit contributions
rob-0.017
 rides-0.016
ons-0.016
opl-0.015
 cand-0.014
Token his
Token ID465
Feature activation+2.04e-02

Pos logit contributions
 rides+0.003
rob+0.003
ons+0.003
 kisses+0.003
 hugs+0.003
Neg logit contributions
kin-0.004
 upon-0.003
isel-0.003
rated-0.003
 loser-0.003
Token mouth
Token ID5422
Feature activation+1.89e-02

Pos logit contributions
rob+0.042
 rides+0.040
ons+0.039
opl+0.037
 cand+0.035
Neg logit contributions
kin-0.034
 upon-0.029
isel-0.029
 moment-0.028
rated-0.027
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
rob+0.036
 rides+0.036
ons+0.035
opl+0.033
 cand+0.031
Neg logit contributions
kin-0.032
isel-0.028
 upon-0.028
rated-0.027
 moment-0.027
Token to
Token ID284
Feature activation+5.58e-02

Pos logit contributions
rob+0.024
opl+0.021
 rides+0.021
ons+0.021
grand+0.020
Neg logit contributions
kin-0.016
 upon-0.015
 moment-0.015
isel-0.014
 disaster-0.013
Token give
Token ID1577
Feature activation+1.42e-02

Pos logit contributions
rob+0.111
 rides+0.104
ons+0.103
opl+0.097
 cand+0.092
Neg logit contributions
kin-0.097
isel-0.083
 upon-0.082
 moment-0.079
rated-0.077
Token back
Token ID736
Feature activation+4.80e-02

Pos logit contributions
rob+0.027
 rides+0.027
ons+0.026
opl+0.025
 cand+0.023
Neg logit contributions
kin-0.025
 upon-0.021
isel-0.021
 moment-0.020
rated-0.020
Token his
Token ID465
Feature activation+2.07e-02

Pos logit contributions
rob+0.093
 rides+0.091
ons+0.089
opl+0.084
 cand+0.080
Neg logit contributions
kin-0.081
 upon-0.071
isel-0.071
 moment-0.067
rated-0.067
Token nap
Token ID25422
Feature activation+6.34e-02

Pos logit contributions
rob+0.032
 rides+0.031
ons+0.029
opl+0.027
 cand+0.026
Neg logit contributions
kin-0.044
 upon-0.040
isel-0.039
 moment-0.038
rated-0.038
Tokenkin
Token ID5116
Feature activation-5.09e-01

Pos logit contributions
rob+0.205
 rides+0.205
ons+0.202
opl+0.192
 cand+0.190
Neg logit contributions
kin-0.018
isel-0.012
 upon-0.009
rated-0.005
 moment-0.003
Token.
Token ID13
Feature activation-2.15e-02

Pos logit contributions
kin+0.846
 upon+0.710
 moment+0.662
rated+0.621
isel+0.609
Neg logit contributions
rob-1.132
 rides-1.042
ons-1.006
opl-0.998
pill-0.935
Token The
Token ID383
Feature activation+4.84e-02

Pos logit contributions
kin+0.038
 upon+0.034
isel+0.034
 moment+0.032
rated+0.032
Neg logit contributions
rob-0.040
 rides-0.039
ons-0.038
opl-0.035
 cand-0.034
Token beautiful
Token ID4950
Feature activation+6.25e-02

Pos logit contributions
rob+0.085
 rides+0.085
ons+0.081
opl+0.076
 cand+0.074
Neg logit contributions
kin-0.090
isel-0.081
 upon-0.079
rated-0.077
 moment-0.075
Token bunny
Token ID44915
Feature activation+1.14e-02

Pos logit contributions
rob+0.094
 rides+0.094
ons+0.091
opl+0.082
 cand+0.079
Neg logit contributions
kin-0.132
isel-0.121
 upon-0.118
rated-0.114
 loser-0.112
Token agreed
Token ID4987
Feature activation+6.15e-02

Pos logit contributions
rob+0.025
 rides+0.023
opl+0.023
ons+0.023
grand+0.021
Neg logit contributions
kin-0.018
 upon-0.015
 moment-0.015
rated-0.014
isel-0.014
Token So
Token ID1406
Feature activation+1.64e-01

Pos logit contributions
kin+0.046
 upon+0.042
isel+0.041
 moment+0.040
rated+0.039
Neg logit contributions
rob-0.042
 rides-0.041
ons-0.040
opl-0.037
 cand-0.035
Token she
Token ID673
Feature activation+9.07e-02

Pos logit contributions
 rides+0.267
ons+0.259
rob+0.259
opl+0.229
 cand+0.229
Neg logit contributions
kin-0.326
isel-0.295
rated-0.283
 upon-0.281
 loser-0.271
Token took
Token ID1718
Feature activation+1.74e-02

Pos logit contributions
rob+0.167
 rides+0.161
ons+0.157
opl+0.152
 cand+0.140
Neg logit contributions
kin-0.167
 upon-0.146
isel-0.145
rated-0.138
 moment-0.137
Token the
Token ID262
Feature activation-3.28e-02

Pos logit contributions
 rides+0.033
ons+0.032
rob+0.032
 kisses+0.028
opl+0.028
Neg logit contributions
kin-0.032
 upon-0.028
rated-0.027
isel-0.027
 moment-0.026
Token nap
Token ID25422
Feature activation+6.21e-02

Pos logit contributions
kin+0.061
isel+0.055
 upon+0.054
rated+0.052
inn+0.051
Neg logit contributions
rob-0.057
 rides-0.057
ons-0.055
opl-0.050
 cand-0.049
Tokenkin
Token ID5116
Feature activation-5.09e-01

Pos logit contributions
rob+0.186
 rides+0.184
ons+0.181
opl+0.173
 cand+0.170
Neg logit contributions
kin-0.039
isel-0.027
 upon-0.026
rated-0.022
 moment-0.021
Token,
Token ID11
Feature activation-7.23e-03

Pos logit contributions
kin+0.830
 upon+0.733
 moment+0.664
inn+0.618
isel+0.614
Neg logit contributions
rob-1.143
 rides-1.055
opl-1.020
ons-1.011
pill-0.953
Token dipped
Token ID35300
Feature activation-1.06e-01

Pos logit contributions
kin+0.012
 upon+0.011
isel+0.010
 moment+0.010
rated+0.009
Neg logit contributions
rob-0.015
 rides-0.014
opl-0.014
ons-0.014
 cand-0.012
Token it
Token ID340
Feature activation-2.02e-01

Pos logit contributions
kin+0.210
rated+0.208
isel+0.204
 loser+0.200
OO+0.193
Neg logit contributions
ons-0.163
 rides-0.142
 kisses-0.141
 cand-0.139
 course-0.138
Token into
Token ID656
Feature activation-6.22e-02

Pos logit contributions
kin+0.300
 upon+0.254
isel+0.247
 moment+0.239
rated+0.236
Neg logit contributions
rob-0.445
 rides-0.433
ons-0.421
opl-0.404
 cand-0.382
Token her
Token ID607
Feature activation+3.38e-02

Pos logit contributions
kin+0.117
rated+0.108
isel+0.108
 upon+0.103
 loser+0.100
Neg logit contributions
 rides-0.106
ons-0.104
rob-0.103
 cand-0.095
 kisses-0.093
Token eyes
Token ID2951
Feature activation-9.00e-02

Pos logit contributions
rob+0.059
 rides+0.054
ons+0.053
opl+0.052
 cand+0.048
Neg logit contributions
kin-0.041
 upon-0.037
isel-0.035
 moment-0.034
 particular-0.032
Token,
Token ID11
Feature activation-5.27e-03

Pos logit contributions
kin+0.135
 upon+0.120
 moment+0.113
isel+0.111
rated+0.107
Neg logit contributions
rob-0.198
 rides-0.187
ons-0.183
opl-0.180
pill-0.166
Token took
Token ID1718
Feature activation+1.26e-02

Pos logit contributions
kin+0.009
 upon+0.008
isel+0.008
 moment+0.007
rated+0.007
Neg logit contributions
rob-0.011
 rides-0.010
ons-0.010
opl-0.010
 cand-0.009
Token the
Token ID262
Feature activation-2.59e-02

Pos logit contributions
rob+0.025
 rides+0.025
ons+0.024
opl+0.023
 cand+0.022
Neg logit contributions
kin-0.021
isel-0.018
 upon-0.018
 moment-0.017
rated-0.017
Token nap
Token ID25422
Feature activation+6.36e-02

Pos logit contributions
kin+0.047
isel+0.042
 upon+0.041
rated+0.040
 moment+0.039
Neg logit contributions
rob-0.046
 rides-0.046
ons-0.045
opl-0.041
 cand-0.040
Tokenkin
Token ID5116
Feature activation-5.08e-01

Pos logit contributions
rob+0.158
 rides+0.157
ons+0.154
opl+0.146
 cand+0.142
Neg logit contributions
kin-0.072
isel-0.059
 upon-0.058
rated-0.054
 moment-0.053
Token and
Token ID290
Feature activation-5.03e-03

Pos logit contributions
kin+0.807
 upon+0.713
 moment+0.633
ac+0.567
inn+0.566
Neg logit contributions
rob-1.193
 rides-1.090
opl-1.067
ons-1.027
pill-0.993
Token smiled
Token ID13541
Feature activation+2.43e-02

Pos logit contributions
kin+0.009
 upon+0.008
 moment+0.008
isel+0.008
rated+0.007
Neg logit contributions
rob-0.010
opl-0.009
 rides-0.009
ons-0.009
pill-0.008
Token.
Token ID13
Feature activation-1.90e-02

Pos logit contributions
 rides+0.043
rob+0.041
ons+0.040
 kisses+0.038
 cand+0.038
Neg logit contributions
kin-0.044
isel-0.041
rated-0.037
 loser-0.037
 upon-0.037
Token She
Token ID1375
Feature activation+1.13e-01

Pos logit contributions
kin+0.037
isel+0.032
 upon+0.032
rated+0.031
 moment+0.031
Neg logit contributions
rob-0.032
 rides-0.032
ons-0.031
opl-0.029
 cand-0.027
Token said
Token ID531
Feature activation+2.09e-01

Pos logit contributions
rob+0.216
 rides+0.203
opl+0.202
ons+0.199
 cand+0.178
Neg logit contributions
kin-0.203
 upon-0.178
 moment-0.164
isel-0.164
cca-0.159
Token it
Token ID340
Feature activation-1.95e-01

Pos logit contributions
kin+0.171
isel+0.137
 loser+0.136
rated+0.134
iding+0.130
Neg logit contributions
 rides-0.143
ons-0.132
 hugs-0.125
 kisses-0.123
 bars-0.121
Token up
Token ID510
Feature activation-5.69e-02

Pos logit contributions
kin+0.336
isel+0.293
 upon+0.287
rated+0.273
 moment+0.272
Neg logit contributions
 rides-0.371
rob-0.369
ons-0.359
opl-0.335
 cand-0.324
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
kin+0.110
isel+0.099
 loser+0.093
 upon+0.093
rated+0.092
Neg logit contributions
 rides-0.096
rob-0.092
ons-0.092
opl-0.082
 cand-0.082
Token The
Token ID383
Feature activation+5.74e-02

Pos logit contributions
kin+0.021
 upon+0.018
isel+0.018
 moment+0.017
rated+0.017
Neg logit contributions
rob-0.021
 rides-0.020
ons-0.020
opl-0.018
 cand-0.018
Token nap
Token ID25422
Feature activation+6.96e-02

Pos logit contributions
rob+0.091
 rides+0.090
ons+0.087
opl+0.080
 cand+0.077
Neg logit contributions
kin-0.118
isel-0.106
 upon-0.105
rated-0.101
 moment-0.100
Tokenkin
Token ID5116
Feature activation-5.08e-01

Pos logit contributions
ons+0.215
rob+0.207
 rides+0.202
 cand+0.197
 cookies+0.188
Neg logit contributions
isel-0.031
rated-0.022
 particular-0.016
 upon-0.016
 halfway-0.014
Token had
Token ID550
Feature activation-2.29e-03

Pos logit contributions
kin+0.846
 upon+0.709
 moment+0.662
rated+0.643
isel+0.638
Neg logit contributions
rob-1.107
 rides-1.037
opl-1.024
ons-0.989
 course-0.908
Token a
Token ID257
Feature activation-1.34e-02

Pos logit contributions
 upon+0.003
kin+0.003
 disaster+0.003
 moment+0.003
 time+0.002
Neg logit contributions
rob-0.005
opl-0.005
ons-0.005
grand-0.004
 rides-0.004
Token sandwich
Token ID20433
Feature activation+2.15e-01

Pos logit contributions
kin+0.023
 upon+0.020
isel+0.019
 moment+0.019
 loser+0.018
Neg logit contributions
rob-0.027
 rides-0.026
ons-0.026
opl-0.024
cream-0.023
Token inside
Token ID2641
Feature activation-9.32e-02

Pos logit contributions
rob+0.468
 rides+0.442
ons+0.425
opl+0.419
pill+0.397
Neg logit contributions
kin-0.366
 upon-0.291
 moment-0.265
inn-0.260
 loser-0.258
Token!
Token ID0
Feature activation+4.48e-02

Pos logit contributions
kin+0.161
isel+0.141
 upon+0.138
rated+0.133
 moment+0.132
Neg logit contributions
rob-0.178
 rides-0.177
ons-0.173
opl-0.161
 cand-0.154
Token it
Token ID340
Feature activation-1.98e-01

Pos logit contributions
 rides+0.100
ons+0.099
rob+0.098
 course+0.089
 cand+0.088
Neg logit contributions
kin-0.089
isel-0.082
rated-0.080
 upon-0.077
 loser-0.077
Token up
Token ID510
Feature activation-5.79e-02

Pos logit contributions
kin+0.346
isel+0.309
 upon+0.297
rated+0.286
 loser+0.284
Neg logit contributions
 rides-0.371
rob-0.362
ons-0.358
opl-0.326
 cand-0.321
Token in
Token ID287
Feature activation-1.00e-01

Pos logit contributions
kin+0.105
isel+0.100
rated+0.092
 upon+0.091
 loser+0.091
Neg logit contributions
 rides-0.102
ons-0.096
rob-0.096
 cand-0.087
 course-0.087
Token a
Token ID257
Feature activation-1.99e-02

Pos logit contributions
kin+0.184
isel+0.162
 upon+0.160
rated+0.156
 moment+0.151
Neg logit contributions
 rides-0.181
rob-0.181
ons-0.175
opl-0.163
 cand-0.158
Token nap
Token ID25422
Feature activation+6.73e-02

Pos logit contributions
kin+0.038
 upon+0.033
 moment+0.033
isel+0.030
 particular+0.030
Neg logit contributions
rob-0.039
 rides-0.036
ons-0.034
opl-0.033
cream-0.031
Tokenkin
Token ID5116
Feature activation-5.08e-01

Pos logit contributions
ons+0.203
rob+0.202
 rides+0.201
 cand+0.192
 course+0.189
Neg logit contributions
isel-0.028
 upon-0.020
rated-0.020
kin-0.014
 moment-0.011
Token.
Token ID13
Feature activation-2.06e-02

Pos logit contributions
kin+0.813
 upon+0.673
 moment+0.621
isel+0.612
inn+0.600
Neg logit contributions
rob-1.100
 rides-1.054
ons-1.033
opl-1.001
 kisses-0.933
Token This
Token ID770
Feature activation+1.61e-01

Pos logit contributions
kin+0.034
 upon+0.030
isel+0.030
 moment+0.028
rated+0.028
Neg logit contributions
rob-0.041
 rides-0.040
ons-0.039
opl-0.037
 cand-0.035
Token sandwich
Token ID20433
Feature activation+2.13e-01

Pos logit contributions
rob+0.446
 rides+0.439
ons+0.430
opl+0.414
 cand+0.399
Neg logit contributions
kin-0.149
 upon-0.109
isel-0.107
 moment-0.099
rated-0.096
Token was
Token ID373
Feature activation-4.91e-02

Pos logit contributions
rob+0.492
 rides+0.474
opl+0.457
ons+0.449
 kisses+0.412
Neg logit contributions
kin-0.327
 upon-0.249
 moment-0.245
rated-0.233
isel-0.231
Token so
Token ID523
Feature activation+1.88e-01

Pos logit contributions
kin+0.106
 upon+0.094
isel+0.093
 moment+0.090
rated+0.090
Neg logit contributions
rob-0.075
 rides-0.073
ons-0.070
opl-0.065
 cand-0.061
Token,
Token ID11
Feature activation-1.30e-02

Pos logit contributions
kin+0.232
 upon+0.201
 moment+0.191
isel+0.190
rated+0.181
Neg logit contributions
rob-0.300
 rides-0.285
ons-0.277
opl-0.268
pill-0.250
Token he
Token ID339
Feature activation+9.43e-02

Pos logit contributions
kin+0.024
isel+0.021
 upon+0.021
rated+0.020
 moment+0.020
Neg logit contributions
 rides-0.023
rob-0.023
ons-0.022
opl-0.020
 cand-0.020
Token saw
Token ID2497
Feature activation-7.66e-02

Pos logit contributions
rob+0.184
 rides+0.175
ons+0.171
opl+0.166
 cand+0.155
Neg logit contributions
kin-0.164
 upon-0.145
isel-0.141
 moment-0.136
rated-0.135
Token a
Token ID257
Feature activation-2.59e-02

Pos logit contributions
kin+0.140
 upon+0.123
isel+0.122
 moment+0.117
rated+0.115
Neg logit contributions
rob-0.140
 rides-0.136
ons-0.132
opl-0.125
 cand-0.118
Token nap
Token ID25422
Feature activation+6.65e-02

Pos logit contributions
kin+0.048
isel+0.043
 upon+0.042
rated+0.041
inn+0.039
Neg logit contributions
 rides-0.045
rob-0.045
ons-0.044
opl-0.040
 cand-0.039
Tokenkin
Token ID5116
Feature activation-5.07e-01

Pos logit contributions
ons+0.190
rob+0.189
 rides+0.188
 course+0.175
opl+0.173
Neg logit contributions
isel-0.040
rated-0.030
kin-0.028
 upon-0.027
 loser-0.023
Token on
Token ID319
Feature activation-2.21e-02

Pos logit contributions
kin+0.886
 upon+0.759
 moment+0.698
isel+0.677
rated+0.658
Neg logit contributions
rob-1.046
 rides-0.991
ons-0.951
opl-0.932
pill-0.870
Token the
Token ID262
Feature activation-2.64e-02

Pos logit contributions
kin+0.043
isel+0.040
rated+0.039
 upon+0.039
ac+0.037
Neg logit contributions
 rides-0.038
rob-0.036
ons-0.035
 course-0.032
opl-0.032
Token floor
Token ID4314
Feature activation+5.38e-02

Pos logit contributions
kin+0.045
 moment+0.038
 upon+0.035
 footing+0.035
 loser+0.034
Neg logit contributions
rob-0.054
ons-0.054
opl-0.048
 rides-0.048
pill-0.047
Token.
Token ID13
Feature activation-2.18e-02

Pos logit contributions
rob+0.109
 rides+0.106
ons+0.103
opl+0.097
 cand+0.093
Neg logit contributions
kin-0.089
 upon-0.077
isel-0.075
 moment-0.072
rated-0.071
Token The
Token ID383
Feature activation+5.09e-02

Pos logit contributions
kin+0.041
isel+0.036
 upon+0.036
rated+0.035
 moment+0.034
Neg logit contributions
 rides-0.038
rob-0.038
ons-0.036
opl-0.034
 cand-0.033
Token.
Token ID13
Feature activation-1.59e-02

Pos logit contributions
 rides+0.124
rob+0.116
ons+0.115
 kisses+0.109
 cand+0.109
Neg logit contributions
kin-0.135
isel-0.126
rated-0.118
 upon-0.117
 loser-0.115
Token
Token ID198
Feature activation+1.36e-02

Pos logit contributions
kin+0.031
isel+0.028
 upon+0.027
 moment+0.026
rated+0.026
Neg logit contributions
rob-0.027
 rides-0.026
ons-0.026
opl-0.024
 cand-0.023
Token
Token ID198
Feature activation+1.43e-02

Pos logit contributions
rob+0.023
 rides+0.023
ons+0.022
opl+0.021
 kisses+0.019
Neg logit contributions
kin-0.026
isel-0.023
 upon-0.023
rated-0.022
 moment-0.022
TokenThe
Token ID464
Feature activation+7.56e-02

Pos logit contributions
rob+0.026
 rides+0.025
ons+0.024
opl+0.023
 cand+0.022
Neg logit contributions
kin-0.027
isel-0.024
 upon-0.023
rated-0.022
 moment-0.022
Token nap
Token ID25422
Feature activation+6.75e-02

Pos logit contributions
 rides+0.135
rob+0.133
ons+0.129
opl+0.119
 cand+0.118
Neg logit contributions
kin-0.138
isel-0.126
 upon-0.121
rated-0.119
 moment-0.115
Tokenkin
Token ID5116
Feature activation-5.07e-01

Pos logit contributions
ons+0.207
rob+0.203
 rides+0.203
 cand+0.192
 kisses+0.188
Neg logit contributions
isel-0.026
rated-0.020
 upon-0.020
kin-0.020
inn-0.013
Token looked
Token ID3114
Feature activation+2.87e-02

Pos logit contributions
kin+0.843
 upon+0.669
 moment+0.640
isel+0.604
rated+0.603
Neg logit contributions
rob-1.150
opl-1.069
 rides-1.055
ons-1.007
pill-0.941
Token nice
Token ID3621
Feature activation+6.26e-02

Pos logit contributions
 rides+0.039
ons+0.035
rob+0.034
 cand+0.032
 kisses+0.032
Neg logit contributions
kin-0.066
isel-0.060
 loser-0.058
 moment-0.056
 upon-0.056
Token and
Token ID290
Feature activation+2.24e-04

Pos logit contributions
rob+0.131
 rides+0.125
ons+0.122
opl+0.119
grand+0.108
Neg logit contributions
kin-0.103
 upon-0.088
 moment-0.084
isel-0.083
rated-0.080
Token tidy
Token ID43044
Feature activation+7.53e-02

Pos logit contributions
rob+0.000
 rides+0.000
ons+0.000
opl+0.000
 cand+0.000
Neg logit contributions
kin-0.000
 upon-0.000
isel-0.000
 moment-0.000
rated-0.000
Token.
Token ID13
Feature activation-1.41e-02

Pos logit contributions
 rides+0.141
rob+0.140
ons+0.135
opl+0.125
 cand+0.123
Neg logit contributions
kin-0.131
isel-0.119
 upon-0.115
rated-0.109
 moment-0.108
Token.
Token ID13
Feature activation-2.66e-02

Pos logit contributions
kin+0.260
 upon+0.223
 moment+0.200
isel+0.195
rated+0.191
Neg logit contributions
rob-0.375
 rides-0.348
ons-0.335
opl-0.327
pill-0.305
Token They
Token ID1119
Feature activation+9.04e-03

Pos logit contributions
kin+0.051
isel+0.044
 upon+0.044
rated+0.043
 moment+0.042
Neg logit contributions
rob-0.046
 rides-0.046
ons-0.044
opl-0.041
 cand-0.039
Token use
Token ID779
Feature activation-1.07e-01

Pos logit contributions
rob+0.018
ons+0.017
 rides+0.016
opl+0.016
 cand+0.015
Neg logit contributions
kin-0.015
 upon-0.014
isel-0.013
rated-0.013
 moment-0.012
Token the
Token ID262
Feature activation-2.70e-02

Pos logit contributions
kin+0.181
isel+0.156
 upon+0.156
 moment+0.148
rated+0.148
Neg logit contributions
rob-0.208
 rides-0.205
ons-0.199
opl-0.187
 cand-0.179
Token nap
Token ID25422
Feature activation+6.35e-02

Pos logit contributions
kin+0.049
isel+0.045
rated+0.043
 upon+0.043
inn+0.042
Neg logit contributions
 rides-0.047
rob-0.046
ons-0.045
 cand-0.041
opl-0.041
Tokenkin
Token ID5116
Feature activation-5.07e-01

Pos logit contributions
rob+0.201
 rides+0.199
ons+0.198
opl+0.186
 cand+0.186
Neg logit contributions
kin-0.024
isel-0.017
 upon-0.014
rated-0.012
 moment-0.009
Token to
Token ID284
Feature activation+6.44e-02

Pos logit contributions
kin+0.870
 upon+0.738
 moment+0.672
ac+0.624
rated+0.624
Neg logit contributions
rob-1.106
 rides-1.015
opl-1.001
ons-0.965
pill-0.903
Token keep
Token ID1394
Feature activation-6.71e-02

Pos logit contributions
rob+0.114
 rides+0.110
ons+0.108
opl+0.101
pill+0.095
Neg logit contributions
kin-0.125
isel-0.107
 upon-0.106
 moment-0.103
rated-0.101
Token their
Token ID511
Feature activation-5.62e-02

Pos logit contributions
kin+0.115
 upon+0.097
isel+0.096
 moment+0.094
rated+0.091
Neg logit contributions
rob-0.133
 rides-0.129
ons-0.123
opl-0.120
pill-0.111
Token hands
Token ID2832
Feature activation-8.08e-02

Pos logit contributions
kin+0.106
 upon+0.093
isel+0.091
 moment+0.088
rated+0.087
Neg logit contributions
rob-0.102
 rides-0.098
ons-0.096
opl-0.090
 cand-0.083
Token clean
Token ID3424
Feature activation+8.70e-02

Pos logit contributions
kin+0.134
 upon+0.110
 moment+0.101
rated+0.095
ac+0.093
Neg logit contributions
rob-0.185
 rides-0.170
opl-0.164
ons-0.162
pill-0.159
Token You
Token ID921
Feature activation+2.16e-02

Pos logit contributions
kin+0.038
isel+0.033
 upon+0.033
rated+0.032
 moment+0.032
Neg logit contributions
rob-0.043
 rides-0.043
ons-0.042
opl-0.039
 cand-0.038
Token need
Token ID761
Feature activation-6.67e-02

Pos logit contributions
rob+0.051
 rides+0.047
opl+0.046
ons+0.046
 cand+0.042
Neg logit contributions
kin-0.031
 upon-0.026
isel-0.025
 don-0.023
 loser-0.023
Token a
Token ID257
Feature activation-1.53e-02

Pos logit contributions
kin+0.107
 upon+0.100
 moment+0.093
isel+0.092
 disaster+0.084
Neg logit contributions
rob-0.144
opl-0.130
 rides-0.126
ons-0.122
odic-0.113
Token clean
Token ID3424
Feature activation+8.99e-02

Pos logit contributions
kin+0.030
isel+0.027
 upon+0.027
rated+0.026
 moment+0.025
Neg logit contributions
 rides-0.025
rob-0.024
ons-0.023
opl-0.022
 cand-0.021
Token nap
Token ID25422
Feature activation+6.65e-02

Pos logit contributions
rob+0.144
 rides+0.144
ons+0.138
opl+0.126
 cand+0.125
Neg logit contributions
kin-0.178
isel-0.165
 upon-0.156
rated-0.155
inn-0.150
Tokenkin
Token ID5116
Feature activation-5.07e-01

Pos logit contributions
rob+0.152
 rides+0.151
ons+0.150
 cand+0.138
opl+0.138
Neg logit contributions
isel-0.077
kin-0.077
 upon-0.070
rated-0.067
 moment-0.064
Token.
Token ID13
Feature activation-2.39e-02

Pos logit contributions
kin+0.839
 upon+0.706
 moment+0.648
rated+0.625
ac+0.619
Neg logit contributions
rob-1.095
 rides-1.036
ons-1.001
opl-0.980
pill-0.924
Token And
Token ID843
Feature activation+1.22e-01

Pos logit contributions
kin+0.044
 upon+0.039
isel+0.039
rated+0.037
 moment+0.037
Neg logit contributions
rob-0.042
 rides-0.042
ons-0.041
opl-0.038
 cand-0.036
Token you
Token ID345
Feature activation+2.53e-01

Pos logit contributions
 rides+0.165
rob+0.161
ons+0.156
opl+0.139
 cand+0.137
Neg logit contributions
kin-0.276
isel-0.251
 upon-0.248
rated-0.243
 moment-0.239
Token need
Token ID761
Feature activation-6.40e-02

Pos logit contributions
rob+0.580
 rides+0.541
ons+0.534
opl+0.526
 cand+0.480
Neg logit contributions
kin-0.376
 upon-0.322
isel-0.309
 moment-0.294
rated-0.291
Token to
Token ID284
Feature activation+6.80e-02

Pos logit contributions
kin+0.103
 upon+0.096
 moment+0.089
isel+0.087
 disaster+0.082
Neg logit contributions
rob-0.138
opl-0.126
 rides-0.122
ons-0.118
pill-0.110
Token grateful
Token ID14066
Feature activation+1.64e-01

Pos logit contributions
rob+0.378
 rides+0.365
ons+0.354
opl+0.334
 cand+0.318
Neg logit contributions
kin-0.323
 upon-0.278
isel-0.275
 moment-0.260
rated-0.259
Token for
Token ID329
Feature activation-1.59e-02

Pos logit contributions
rob+0.311
 rides+0.295
ons+0.288
opl+0.276
 cand+0.256
Neg logit contributions
kin-0.294
 upon-0.268
 moment-0.252
isel-0.249
rated-0.239
Token the
Token ID262
Feature activation-2.21e-02

Pos logit contributions
kin+0.028
isel+0.024
 upon+0.024
 moment+0.023
rated+0.023
Neg logit contributions
rob-0.030
 rides-0.030
ons-0.029
opl-0.027
 cand-0.026
Token special
Token ID2041
Feature activation+9.56e-02

Pos logit contributions
kin+0.046
 upon+0.041
 moment+0.041
isel+0.039
 loser+0.038
Neg logit contributions
rob-0.037
 rides-0.034
ons-0.034
opl-0.032
cream-0.029
Token nap
Token ID25422
Feature activation+6.73e-02

Pos logit contributions
 rides+0.123
ons+0.117
rob+0.117
 cand+0.109
 kisses+0.102
Neg logit contributions
kin-0.216
isel-0.207
 upon-0.197
rated-0.197
inn-0.189
Tokenkin
Token ID5116
Feature activation-5.07e-01

Pos logit contributions
rob+0.197
 rides+0.196
ons+0.194
opl+0.184
 cand+0.181
Neg logit contributions
kin-0.043
isel-0.033
 upon-0.031
rated-0.027
 moment-0.025
Token.
Token ID13
Feature activation-2.47e-02

Pos logit contributions
kin+0.870
 upon+0.738
 moment+0.705
rated+0.609
 footing+0.596
Neg logit contributions
rob-1.110
 rides-1.002
opl-0.989
ons-0.961
pill-0.903
Token
Token ID220
Feature activation+9.50e-02

Pos logit contributions
kin+0.046
 upon+0.042
isel+0.041
 moment+0.040
inn+0.039
Neg logit contributions
rob-0.043
ons-0.041
 rides-0.041
opl-0.037
 cand-0.036
Token
Token ID198
Feature activation+7.24e-03

Pos logit contributions
 rides+0.157
rob+0.157
ons+0.154
opl+0.142
 kisses+0.132
Neg logit contributions
kin-0.187
isel-0.166
rated-0.161
 upon-0.160
 moment-0.158
Token
Token ID198
Feature activation+7.95e-03

Pos logit contributions
rob+0.013
 rides+0.013
ons+0.013
opl+0.012
 cand+0.011
Neg logit contributions
kin-0.013
 upon-0.012
isel-0.011
 moment-0.011
rated-0.011
TokenTom
Token ID13787
Feature activation-1.32e-02

Pos logit contributions
rob+0.015
 rides+0.015
ons+0.015
opl+0.014
 cand+0.013
Neg logit contributions
kin-0.014
 upon-0.012
isel-0.012
 moment-0.011
inn-0.011
Token The
Token ID383
Feature activation+5.60e-02

Pos logit contributions
kin+0.025
isel+0.022
 upon+0.022
rated+0.021
 moment+0.021
Neg logit contributions
rob-0.022
 rides-0.022
ons-0.021
opl-0.020
 cand-0.019
Token bear
Token ID6842
Feature activation+5.44e-02

Pos logit contributions
rob+0.094
 rides+0.092
ons+0.089
opl+0.083
 cand+0.078
Neg logit contributions
kin-0.112
 upon-0.100
isel-0.098
 moment-0.096
rated-0.094
Token saw
Token ID2497
Feature activation-6.58e-02

Pos logit contributions
rob+0.125
opl+0.120
 rides+0.114
ons+0.110
odic+0.103
Neg logit contributions
kin-0.081
 upon-0.075
 moment-0.068
rated-0.066
cca-0.063
Token a
Token ID257
Feature activation-1.45e-02

Pos logit contributions
 upon+0.074
kin+0.073
isel+0.061
 moment+0.060
 disaster+0.059
Neg logit contributions
rob-0.156
opl-0.151
 rides-0.150
ons-0.139
grand-0.139
Token nap
Token ID25422
Feature activation+6.91e-02

Pos logit contributions
kin+0.027
isel+0.024
 upon+0.023
rated+0.022
 moment+0.022
Neg logit contributions
rob-0.026
 rides-0.026
ons-0.025
opl-0.023
 cand-0.022
Tokenkin
Token ID5116
Feature activation-5.07e-01

Pos logit contributions
rob+0.214
ons+0.213
 rides+0.207
 course+0.196
 cand+0.195
Neg logit contributions
isel-0.029
rated-0.015
 upon-0.011
 moment-0.007
uzz-0.007
Token on
Token ID319
Feature activation-1.73e-02

Pos logit contributions
kin+0.824
 upon+0.685
 moment+0.627
isel+0.604
rated+0.592
Neg logit contributions
rob-1.103
 rides-1.067
ons-1.020
opl-1.003
pill-0.941
Token the
Token ID262
Feature activation-1.75e-02

Pos logit contributions
kin+0.029
 upon+0.025
isel+0.025
 moment+0.024
rated+0.024
Neg logit contributions
rob-0.034
 rides-0.034
ons-0.033
opl-0.031
 cand-0.030
Token ground
Token ID2323
Feature activation+8.77e-02

Pos logit contributions
kin+0.028
 foot+0.022
 moment+0.021
 footing+0.021
 upon+0.021
Neg logit contributions
rob-0.039
ons-0.038
pill-0.035
opl-0.035
 rides-0.035
Token and
Token ID290
Feature activation+1.01e-03

Pos logit contributions
rob+0.191
 rides+0.182
ons+0.177
opl+0.168
 cand+0.163
Neg logit contributions
kin-0.136
 upon-0.119
 moment-0.110
isel-0.109
rated-0.106
Token lifted
Token ID13663
Feature activation-8.08e-02

Pos logit contributions
rob+0.002
opl+0.002
 rides+0.002
ons+0.002
pill+0.002
Neg logit contributions
kin-0.002
 upon-0.002
isel-0.001
 moment-0.001
rated-0.001
Token wanted
Token ID2227
Feature activation-9.56e-02

Pos logit contributions
kin+0.251
 upon+0.221
isel+0.208
rated+0.206
 moment+0.204
Neg logit contributions
rob-0.322
 rides-0.308
ons-0.298
opl-0.291
 cand-0.276
Token to
Token ID284
Feature activation+5.65e-02

Pos logit contributions
kin+0.142
 upon+0.134
 moment+0.131
isel+0.123
 particular+0.119
Neg logit contributions
rob-0.208
opl-0.188
 rides-0.181
ons-0.179
pill-0.168
Token get
Token ID651
Feature activation-8.81e-02

Pos logit contributions
rob+0.116
ons+0.107
 rides+0.106
opl+0.101
 cand+0.097
Neg logit contributions
kin-0.094
isel-0.083
 upon-0.081
 moment-0.078
 particular-0.076
Token the
Token ID262
Feature activation-3.17e-02

Pos logit contributions
kin+0.138
 upon+0.121
isel+0.119
 moment+0.114
rated+0.111
Neg logit contributions
rob-0.184
 rides-0.178
ons-0.174
opl-0.167
 cand-0.158
Token nap
Token ID25422
Feature activation+6.59e-02

Pos logit contributions
kin+0.062
 upon+0.054
isel+0.054
 moment+0.052
rated+0.051
Neg logit contributions
rob-0.054
 rides-0.053
ons-0.052
opl-0.048
 cand-0.045
Tokenkin
Token ID5116
Feature activation-5.07e-01

Pos logit contributions
rob+0.171
 rides+0.171
ons+0.168
opl+0.157
 cand+0.156
Neg logit contributions
kin-0.061
isel-0.055
 upon-0.052
rated-0.047
 moment-0.045
Token so
Token ID523
Feature activation+1.87e-01

Pos logit contributions
kin+0.875
 upon+0.757
 moment+0.715
isel+0.695
rated+0.691
Neg logit contributions
rob-1.026
 rides-0.984
ons-0.955
opl-0.922
pill-0.853
Token she
Token ID673
Feature activation+9.16e-02

Pos logit contributions
 rides+0.287
ons+0.267
rob+0.259
 kisses+0.239
 cand+0.236
Neg logit contributions
kin-0.382
isel-0.351
 upon-0.337
rated-0.331
 moment-0.331
Token jumped
Token ID11687
Feature activation-2.67e-02

Pos logit contributions
rob+0.174
 rides+0.172
ons+0.167
opl+0.155
 cand+0.150
Neg logit contributions
kin-0.160
isel-0.139
 upon-0.139
 moment-0.132
rated-0.132
Token.
Token ID13
Feature activation-1.90e-02

Pos logit contributions
kin+0.052
isel+0.050
rated+0.046
 loser+0.044
 upon+0.044
Neg logit contributions
 rides-0.044
rob-0.040
ons-0.040
 cand-0.036
 kisses-0.036
Token She
Token ID1375
Feature activation+1.09e-01

Pos logit contributions
kin+0.041
isel+0.036
rated+0.035
 upon+0.035
 loser+0.034
Neg logit contributions
 rides-0.029
rob-0.028
ons-0.028
opl-0.025
 kisses-0.024
Tokenished
Token ID1348
Feature activation-5.04e-02

Pos logit contributions
kin+0.031
 moment+0.026
 upon+0.026
 particular+0.025
isel+0.025
Neg logit contributions
 rides-0.032
rob-0.031
ons-0.031
 kisses-0.028
 cand-0.028
Token it
Token ID340
Feature activation-1.94e-01

Pos logit contributions
kin+0.099
isel+0.088
rated+0.088
 loser+0.084
 particular+0.084
Neg logit contributions
ons-0.086
 rides-0.083
rob-0.077
 course-0.075
 cand-0.074
Token with
Token ID351
Feature activation+2.32e-02

Pos logit contributions
kin+0.324
isel+0.281
 upon+0.278
rated+0.264
 moment+0.263
Neg logit contributions
 rides-0.380
rob-0.380
ons-0.368
opl-0.344
 cand-0.332
Token a
Token ID257
Feature activation-1.64e-02

Pos logit contributions
 rides+0.037
ons+0.036
rob+0.035
 kisses+0.032
opl+0.032
Neg logit contributions
kin-0.048
rated-0.043
 upon-0.042
isel-0.041
 moment-0.040
Token nap
Token ID25422
Feature activation+6.75e-02

Pos logit contributions
kin+0.030
rated+0.027
isel+0.027
 upon+0.026
uzz+0.025
Neg logit contributions
ons-0.026
 rides-0.026
rob-0.025
 kisses-0.024
 cand-0.024
Tokenkin
Token ID5116
Feature activation-5.06e-01

Pos logit contributions
ons+0.206
rob+0.203
 rides+0.198
 cand+0.195
 course+0.188
Neg logit contributions
isel-0.026
 upon-0.019
rated-0.018
 particular-0.011
 moment-0.010
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
kin+0.814
 upon+0.681
isel+0.637
 moment+0.626
inn+0.617
Neg logit contributions
rob-1.096
 rides-1.044
ons-1.020
opl-0.988
pill-0.920
Token Tim
Token ID5045
Feature activation-1.35e-02

Pos logit contributions
kin+0.032
 upon+0.029
isel+0.028
 moment+0.027
rated+0.026
Neg logit contributions
rob-0.048
 rides-0.046
ons-0.046
opl-0.043
 cand-0.041
Tokenmy
Token ID1820
Feature activation+1.54e-01

Pos logit contributions
kin+0.031
 upon+0.029
isel+0.028
rated+0.027
 moment+0.027
Neg logit contributions
rob-0.018
 rides-0.018
ons-0.017
opl-0.016
 cand-0.015
Token felt
Token ID2936
Feature activation-5.08e-02

Pos logit contributions
rob+0.344
opl+0.321
 rides+0.319
ons+0.308
grand+0.280
Neg logit contributions
kin-0.234
 upon-0.200
isel-0.192
rated-0.186
 moment-0.186
Token bad
Token ID2089
Feature activation+2.37e-02

Pos logit contributions
kin+0.090
isel+0.079
 upon+0.079
 moment+0.075
rated+0.075
Neg logit contributions
rob-0.095
 rides-0.094
ons-0.091
opl-0.085
 cand-0.082
Token it
Token ID340
Feature activation-1.99e-01

Pos logit contributions
kin+0.061
isel+0.057
 upon+0.053
rated+0.053
 moment+0.051
Neg logit contributions
rob-0.073
ons-0.072
 rides-0.071
 cand-0.064
opl-0.064
Token off
Token ID572
Feature activation+2.68e-02

Pos logit contributions
kin+0.353
 upon+0.306
isel+0.300
 moment+0.292
rated+0.291
Neg logit contributions
rob-0.376
 rides-0.368
ons-0.357
opl-0.337
 cand-0.318
Token with
Token ID351
Feature activation+2.61e-02

Pos logit contributions
rob+0.047
 rides+0.046
ons+0.044
opl+0.042
 cand+0.039
Neg logit contributions
kin-0.051
 upon-0.045
isel-0.045
 moment-0.043
rated-0.043
Token a
Token ID257
Feature activation-2.03e-02

Pos logit contributions
rob+0.044
 rides+0.040
ons+0.037
opl+0.037
cream+0.034
Neg logit contributions
kin-0.054
 upon-0.047
isel-0.046
 moment-0.044
 loser-0.044
Token nap
Token ID25422
Feature activation+6.52e-02

Pos logit contributions
kin+0.040
isel+0.036
 upon+0.035
rated+0.034
inn+0.033
Neg logit contributions
 rides-0.033
rob-0.033
ons-0.032
opl-0.029
 cand-0.029
Tokenkin
Token ID5116
Feature activation-5.06e-01

Pos logit contributions
rob+0.162
ons+0.160
 rides+0.159
 cand+0.150
opl+0.146
Neg logit contributions
isel-0.064
 upon-0.056
kin-0.055
rated-0.051
inn-0.048
Token,"
Token ID553
Feature activation+5.98e-02

Pos logit contributions
kin+0.848
 upon+0.703
 moment+0.655
 loser+0.640
rated+0.629
Neg logit contributions
rob-1.069
 rides-1.028
ons-0.996
opl-0.964
pill-0.906
Token Mom
Token ID11254
Feature activation-1.95e-01

Pos logit contributions
rob+0.108
 rides+0.107
ons+0.104
opl+0.095
 cand+0.093
Neg logit contributions
kin-0.110
isel-0.097
 upon-0.096
rated-0.093
 moment-0.091
Token said
Token ID531
Feature activation+2.12e-01

Pos logit contributions
 upon+0.387
kin+0.367
 moment+0.349
rated+0.335
inn+0.333
Neg logit contributions
rob-0.314
 rides-0.296
opl-0.292
ons-0.256
 cand-0.252
Token.
Token ID13
Feature activation-1.99e-02

Pos logit contributions
 rides+0.368
ons+0.364
rob+0.360
 kisses+0.325
 cand+0.323
Neg logit contributions
kin-0.390
isel-0.349
 upon-0.342
rated-0.334
 moment-0.322
Token
Token ID198
Feature activation+1.48e-02

Pos logit contributions
kin+0.044
rated+0.040
isel+0.039
ac+0.036
 footing+0.036
Neg logit contributions
 rides-0.029
ons-0.028
rob-0.028
 kisses-0.026
opl-0.025
Token covers
Token ID8698
Feature activation+1.83e-01

Pos logit contributions
rob+0.047
ons+0.043
opl+0.043
 rides+0.040
handed+0.040
Neg logit contributions
kin-0.044
 upon-0.041
isel-0.038
 don-0.036
 moment-0.035
Token them
Token ID606
Feature activation-1.45e-01

Pos logit contributions
ons+0.267
 rides+0.253
 kisses+0.232
 hugs+0.228
rob+0.227
Neg logit contributions
kin-0.392
rated-0.376
isel-0.372
 loser-0.370
 runner-0.354
Token with
Token ID351
Feature activation+2.57e-02

Pos logit contributions
kin+0.231
 upon+0.199
 moment+0.188
rated+0.183
isel+0.181
Neg logit contributions
rob-0.323
ons-0.291
 rides-0.291
opl-0.284
pill-0.265
Token the
Token ID262
Feature activation-2.47e-02

Pos logit contributions
rob+0.045
 rides+0.045
ons+0.044
opl+0.040
 cand+0.039
Neg logit contributions
kin-0.048
isel-0.042
 upon-0.042
rated-0.041
 moment-0.040
Token nap
Token ID25422
Feature activation+6.77e-02

Pos logit contributions
kin+0.048
isel+0.044
 upon+0.043
rated+0.042
inn+0.042
Neg logit contributions
 rides-0.040
rob-0.039
ons-0.039
 cand-0.035
 kisses-0.035
Tokenkin
Token ID5116
Feature activation-5.06e-01

Pos logit contributions
ons+0.203
 rides+0.202
rob+0.201
 cand+0.190
opl+0.187
Neg logit contributions
isel-0.030
kin-0.028
 upon-0.026
rated-0.024
 moment-0.019
Token.
Token ID13
Feature activation-2.97e-02

Pos logit contributions
kin+0.756
 upon+0.583
 moment+0.534
isel+0.483
rated+0.478
Neg logit contributions
rob-1.243
 rides-1.117
opl-1.104
ons-1.089
pill-1.044
Token
Token ID198
Feature activation+1.81e-02

Pos logit contributions
kin+0.065
rated+0.059
isel+0.057
 upon+0.055
 moment+0.054
Neg logit contributions
 rides-0.045
rob-0.043
ons-0.041
 kisses-0.038
opl-0.038
Token
Token ID198
Feature activation+1.87e-02

Pos logit contributions
 rides+0.026
ons+0.025
rob+0.025
opl+0.022
 kisses+0.021
Neg logit contributions
kin-0.041
rated-0.037
isel-0.037
 loser-0.035
 footing-0.034
Token"
Token ID1
Feature activation-7.19e-02

Pos logit contributions
 rides+0.036
rob+0.036
ons+0.035
opl+0.032
 course+0.031
Neg logit contributions
kin-0.032
isel-0.028
rated-0.028
 upon-0.027
 moment-0.026
TokenHere
Token ID4342
Feature activation+2.28e-01

Pos logit contributions
kin+0.121
isel+0.117
 upon+0.113
rated+0.109
 footing+0.106
Neg logit contributions
rob-0.142
 rides-0.132
ons-0.125
 cand-0.120
 course-0.119
Token
Token ID198
Feature activation-3.41e-03

Pos logit contributions
kin+0.011
isel+0.010
rated+0.010
 upon+0.009
 loser+0.009
Neg logit contributions
 rides-0.009
rob-0.009
ons-0.009
opl-0.008
 course-0.007
TokenTom
Token ID13787
Feature activation-1.56e-02

Pos logit contributions
kin+0.006
isel+0.005
 upon+0.005
rated+0.005
 moment+0.005
Neg logit contributions
rob-0.006
 rides-0.006
ons-0.006
opl-0.006
 cand-0.005
Token used
Token ID973
Feature activation+2.73e-02

Pos logit contributions
kin+0.029
 upon+0.029
rated+0.027
 moment+0.026
isel+0.026
Neg logit contributions
rob-0.027
 rides-0.024
ons-0.024
opl-0.023
 cand-0.022
Token the
Token ID262
Feature activation-2.70e-02

Pos logit contributions
 rides+0.047
rob+0.047
ons+0.046
opl+0.042
 cand+0.041
Neg logit contributions
kin-0.052
isel-0.045
 upon-0.045
rated-0.045
 moment-0.043
Token nap
Token ID25422
Feature activation+6.44e-02

Pos logit contributions
kin+0.048
isel+0.042
 upon+0.042
rated+0.040
 moment+0.040
Neg logit contributions
rob-0.049
 rides-0.049
ons-0.047
opl-0.044
 cand-0.043
Tokenkin
Token ID5116
Feature activation-5.06e-01

Pos logit contributions
rob+0.169
 rides+0.169
ons+0.167
opl+0.156
 cand+0.154
Neg logit contributions
kin-0.058
isel-0.050
 upon-0.047
rated-0.045
 moment-0.042
Token to
Token ID284
Feature activation+5.76e-02

Pos logit contributions
kin+0.866
 upon+0.764
 moment+0.701
isel+0.669
rated+0.641
Neg logit contributions
rob-1.082
 rides-0.989
opl-0.958
ons-0.938
pill-0.871
Token clean
Token ID3424
Feature activation+8.60e-02

Pos logit contributions
rob+0.103
 rides+0.100
ons+0.098
opl+0.091
 cand+0.087
Neg logit contributions
kin-0.109
isel-0.094
 upon-0.094
 moment-0.091
rated-0.090
Token up
Token ID510
Feature activation-5.64e-02

Pos logit contributions
 rides+0.165
rob+0.165
ons+0.159
opl+0.148
 cand+0.144
Neg logit contributions
kin-0.149
isel-0.131
 upon-0.129
rated-0.124
 moment-0.122
Token the
Token ID262
Feature activation-2.43e-02

Pos logit contributions
kin+0.096
 upon+0.083
isel+0.083
 moment+0.079
rated+0.078
Neg logit contributions
rob-0.110
 rides-0.108
ons-0.105
opl-0.099
 cand-0.094
Token apple
Token ID17180
Feature activation+1.72e-01

Pos logit contributions
kin+0.047
 upon+0.041
isel+0.040
 moment+0.040
rated+0.038
Neg logit contributions
rob-0.043
 rides-0.041
ons-0.040
opl-0.038
cream-0.035
Token and
Token ID290
Feature activation+2.39e-03

Pos logit contributions
 rides+0.052
 kisses+0.048
 hugs+0.047
ons+0.045
rob+0.044
Neg logit contributions
kin-0.094
isel-0.087
 loser-0.083
rated-0.080
 footing-0.078
Token said
Token ID531
Feature activation+2.17e-01

Pos logit contributions
rob+0.003
 rides+0.003
ons+0.003
opl+0.003
 cand+0.002
Neg logit contributions
kin-0.006
 upon-0.005
isel-0.005
 moment-0.005
rated-0.005
Token:
Token ID25
Feature activation+1.34e-02

Pos logit contributions
ons+0.329
 rides+0.324
rob+0.306
 cand+0.293
 kisses+0.286
Neg logit contributions
kin-0.449
rated-0.413
isel-0.409
 loser-0.394
 upon-0.390
Token "
Token ID366
Feature activation-1.40e-01

Pos logit contributions
 rides+0.022
ons+0.022
rob+0.021
opl+0.019
 kisses+0.019
Neg logit contributions
kin-0.026
rated-0.024
isel-0.024
ac-0.022
 footing-0.022
TokenIt
Token ID1026
Feature activation-9.44e-02

Pos logit contributions
kin+0.222
 upon+0.194
isel+0.190
 moment+0.184
rated+0.180
Neg logit contributions
rob-0.288
 rides-0.286
ons-0.276
opl-0.263
 cand-0.253
Token's
Token ID338
Feature activation+3.39e-01

Pos logit contributions
kin+0.217
 upon+0.211
 moment+0.205
rated+0.204
isel+0.203
Neg logit contributions
rob-0.124
 rides-0.111
opl-0.105
ons-0.103
 cand-0.091
Token a
Token ID257
Feature activation-1.03e-02

Pos logit contributions
 rides+0.496
ons+0.462
rob+0.435
opl+0.434
 kisses+0.423
Neg logit contributions
kin-0.711
isel-0.664
 loser-0.621
rated-0.610
ges-0.599
Token net
Token ID2010
Feature activation-7.19e-03

Pos logit contributions
kin+0.020
isel+0.018
 upon+0.018
rated+0.018
inn+0.017
Neg logit contributions
 rides-0.017
rob-0.016
ons-0.016
opl-0.014
 cand-0.014
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
kin+0.011
 upon+0.009
 moment+0.009
 don+0.008
rated+0.008
Neg logit contributions
rob-0.017
 rides-0.015
ons-0.015
opl-0.014
cream-0.014
Token It
Token ID632
Feature activation-1.11e-01

Pos logit contributions
kin+0.025
 upon+0.021
isel+0.021
rated+0.021
 moment+0.020
Neg logit contributions
 rides-0.026
rob-0.026
ons-0.025
opl-0.024
 kisses-0.023
Token's
Token ID338
Feature activation+3.39e-01

Pos logit contributions
kin+0.231
 upon+0.217
isel+0.213
rated+0.209
 moment+0.208
Neg logit contributions
rob-0.173
 rides-0.158
ons-0.153
opl-0.152
 cand-0.135
Token their
Token ID511
Feature activation-4.86e-02

Pos logit contributions
rob+0.009
opl+0.008
ons+0.008
 rides+0.008
odic+0.007
Neg logit contributions
kin-0.005
 upon-0.004
isel-0.004
 moment-0.004
 halfway-0.004
Token ball
Token ID2613
Feature activation-3.77e-03

Pos logit contributions
kin+0.094
isel+0.084
 upon+0.083
rated+0.081
 moment+0.079
Neg logit contributions
 rides-0.083
rob-0.081
ons-0.079
opl-0.073
 cand-0.070
Token back
Token ID736
Feature activation+5.82e-02

Pos logit contributions
kin+0.005
 upon+0.004
 moment+0.004
 loser+0.004
inn+0.004
Neg logit contributions
rob-0.009
ons-0.008
 rides-0.008
opl-0.008
grand-0.008
Token.
Token ID13
Feature activation-1.58e-02

Pos logit contributions
rob+0.114
 rides+0.112
ons+0.109
opl+0.103
 cand+0.098
Neg logit contributions
kin-0.099
 upon-0.087
isel-0.085
 moment-0.082
rated-0.081
Token They
Token ID1119
Feature activation+1.31e-02

Pos logit contributions
kin+0.032
isel+0.028
rated+0.028
 upon+0.028
 moment+0.027
Neg logit contributions
 rides-0.026
rob-0.025
ons-0.023
opl-0.022
 kisses-0.022
Token thanked
Token ID26280
Feature activation+2.97e-01

Pos logit contributions
rob+0.025
opl+0.024
ons+0.023
 rides+0.022
pill+0.020
Neg logit contributions
kin-0.024
 upon-0.021
isel-0.020
 don-0.019
cca-0.019
Token Leo
Token ID19632
Feature activation-5.31e-02

Pos logit contributions
 rides+0.614
rob+0.601
ons+0.579
 kisses+0.546
 cand+0.545
Neg logit contributions
kin-0.472
isel-0.424
rated-0.418
 upon-0.405
 moment-0.376
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
kin+0.082
 upon+0.075
 moment+0.069
isel+0.065
rated+0.065
Neg logit contributions
rob-0.115
 rides-0.108
ons-0.108
opl-0.104
cream-0.095
Token They
Token ID1119
Feature activation+1.24e-02

Pos logit contributions
kin+0.029
 upon+0.025
isel+0.025
 moment+0.024
rated+0.024
Neg logit contributions
rob-0.031
 rides-0.030
ons-0.030
opl-0.028
 cand-0.026
Token said
Token ID531
Feature activation+2.19e-01

Pos logit contributions
rob+0.023
opl+0.022
ons+0.022
 rides+0.020
pill+0.019
Neg logit contributions
kin-0.024
 upon-0.020
isel-0.018
 don-0.018
cca-0.018
Token,
Token ID11
Feature activation+1.39e-03

Pos logit contributions
rob+0.420
 rides+0.412
ons+0.400
opl+0.377
 cand+0.357
Neg logit contributions
kin-0.387
 upon-0.335
isel-0.335
 moment-0.319
rated-0.315
Token?"
Token ID1701
Feature activation-3.76e-02

Pos logit contributions
rob+0.148
ons+0.130
pill+0.126
opl+0.124
 rides+0.123
Neg logit contributions
kin-0.112
 upon-0.102
 loser-0.098
isel-0.097
 moment-0.097
Token Sam
Token ID3409
Feature activation-9.69e-02

Pos logit contributions
kin+0.056
 upon+0.056
 moment+0.052
isel+0.050
 particular+0.050
Neg logit contributions
rob-0.076
ons-0.071
 rides-0.070
opl-0.069
 cand-0.064
Token nodded
Token ID14464
Feature activation-6.90e-02

Pos logit contributions
kin+0.144
 upon+0.127
 moment+0.122
rated+0.116
cca+0.114
Neg logit contributions
rob-0.210
 rides-0.202
ons-0.202
opl-0.200
grand-0.178
Token.
Token ID13
Feature activation-1.19e-02

Pos logit contributions
isel+0.173
kin+0.165
 footing+0.159
rated+0.159
 loser+0.155
Neg logit contributions
 hugs-0.069
 rides-0.069
 kisses-0.068
ons-0.062
 cand-0.060
Token He
Token ID679
Feature activation+3.31e-02

Pos logit contributions
kin+0.024
isel+0.021
 upon+0.021
rated+0.020
 moment+0.020
Neg logit contributions
rob-0.020
 rides-0.020
ons-0.019
opl-0.018
 cand-0.017
Token said
Token ID531
Feature activation+2.18e-01

Pos logit contributions
rob+0.051
 rides+0.049
ons+0.049
opl+0.048
 cand+0.041
Neg logit contributions
kin-0.070
 upon-0.063
isel-0.061
 moment-0.060
rated-0.059
Token,
Token ID11
Feature activation+5.99e-03

Pos logit contributions
 rides+0.373
ons+0.364
rob+0.362
 cand+0.330
 kisses+0.325
Neg logit contributions
kin-0.412
isel-0.368
rated-0.367
 upon-0.362
 moment-0.344
Token "
Token ID366
Feature activation-1.40e-01

Pos logit contributions
rob+0.014
 rides+0.014
ons+0.013
opl+0.013
 cand+0.012
Neg logit contributions
kin-0.008
isel-0.007
 upon-0.007
rated-0.006
 moment-0.006
TokenYes
Token ID5297
Feature activation-8.96e-03

Pos logit contributions
kin+0.177
 moment+0.156
 loser+0.144
 particular+0.140
 upon+0.140
Neg logit contributions
ons-0.329
 rides-0.326
rob-0.325
opl-0.318
yard-0.289
Token,
Token ID11
Feature activation+6.84e-03

Pos logit contributions
kin+0.019
isel+0.018
rated+0.018
cca+0.017
udge+0.017
Neg logit contributions
ons-0.012
 rides-0.012
 course-0.012
 hugs-0.011
 kisses-0.011
Token please
Token ID3387
Feature activation-1.63e-01

Pos logit contributions
 rides+0.013
rob+0.013
ons+0.013
opl+0.012
 cand+0.012
Neg logit contributions
kin-0.012
isel-0.010
 upon-0.010
rated-0.010
 moment-0.009
Token if
Token ID611
Feature activation-2.92e-01

Pos logit contributions
kin+0.274
 upon+0.232
isel+0.224
 moment+0.213
rated+0.209
Neg logit contributions
rob-0.517
 rides-0.506
ons-0.493
opl-0.473
 cand-0.453
Token he
Token ID339
Feature activation+1.05e-01

Pos logit contributions
kin+0.637
isel+0.573
 upon+0.567
rated+0.552
 moment+0.546
Neg logit contributions
rob-0.426
 rides-0.422
ons-0.406
opl-0.366
 cand-0.353
Token could
Token ID714
Feature activation-9.52e-02

Pos logit contributions
 rides+0.197
ons+0.191
rob+0.185
 cand+0.172
cream+0.171
Neg logit contributions
kin-0.187
isel-0.165
rated-0.158
 upon-0.157
 moment-0.155
Token have
Token ID423
Feature activation+2.44e-02

Pos logit contributions
kin+0.170
 upon+0.149
isel+0.145
 moment+0.140
 particular+0.137
Neg logit contributions
rob-0.189
 rides-0.174
ons-0.171
opl-0.162
 cand-0.152
Token some
Token ID617
Feature activation+8.02e-02

Pos logit contributions
rob+0.056
opl+0.054
 rides+0.052
ons+0.051
yard+0.049
Neg logit contributions
kin-0.030
 upon-0.026
 moment-0.026
isel-0.024
 particular-0.024
Token ice
Token ID4771
Feature activation+2.56e-01

Pos logit contributions
rob+0.130
 rides+0.118
ons+0.115
opl+0.114
odic+0.098
Neg logit contributions
kin-0.170
 upon-0.153
 moment-0.146
 particular-0.144
isel-0.144
Token cream
Token ID8566
Feature activation+2.46e-01

Pos logit contributions
rob+0.232
 rides+0.222
ons+0.210
 cand+0.176
opl+0.169
Neg logit contributions
kin-0.691
isel-0.656
 upon-0.640
rated-0.631
 moment-0.617
Token,
Token ID11
Feature activation-9.08e-04

Pos logit contributions
rob+0.495
 rides+0.488
ons+0.476
opl+0.451
 kisses+0.423
Neg logit contributions
kin-0.407
 upon-0.346
isel-0.337
 moment-0.328
rated-0.320
Token but
Token ID475
Feature activation-1.93e-01

Pos logit contributions
kin+0.001
 upon+0.001
isel+0.001
 moment+0.001
 particular+0.001
Neg logit contributions
rob-0.002
 rides-0.002
ons-0.002
opl-0.002
pill-0.002
Token she
Token ID673
Feature activation+1.01e-01

Pos logit contributions
kin+0.424
isel+0.411
rated+0.393
 loser+0.374
udge+0.370
Neg logit contributions
 rides-0.248
ons-0.239
rob-0.229
 cand-0.226
 course-0.210
Token said
Token ID531
Feature activation+2.14e-01

Pos logit contributions
rob+0.143
 rides+0.142
ons+0.137
opl+0.123
 cand+0.118
Neg logit contributions
kin-0.224
isel-0.203
 upon-0.201
rated-0.194
 moment-0.194
Token Jim
Token ID5395
Feature activation-1.05e-01

Pos logit contributions
 rides+0.359
ons+0.346
rob+0.315
 kisses+0.303
 course+0.301
Neg logit contributions
kin-0.414
rated-0.371
 upon-0.366
isel-0.356
 loser-0.347
Token,
Token ID11
Feature activation-1.85e-03

Pos logit contributions
kin+0.177
 upon+0.155
isel+0.148
 moment+0.147
rated+0.143
Neg logit contributions
rob-0.217
 rides-0.206
ons-0.199
opl-0.193
 course-0.178
Token "
Token ID366
Feature activation-1.43e-01

Pos logit contributions
kin+0.004
isel+0.003
 upon+0.003
rated+0.003
 moment+0.003
Neg logit contributions
 rides-0.003
rob-0.003
ons-0.003
opl-0.003
 cand-0.003
TokenNow
Token ID3844
Feature activation+1.35e-01

Pos logit contributions
kin+0.262
isel+0.243
 upon+0.229
rated+0.224
inn+0.212
Neg logit contributions
rob-0.252
 rides-0.247
ons-0.244
opl-0.224
cream-0.217
Token it
Token ID340
Feature activation-1.91e-01

Pos logit contributions
rob+0.243
 rides+0.235
ons+0.228
opl+0.215
 cand+0.203
Neg logit contributions
kin-0.251
 upon-0.221
isel-0.220
 moment-0.210
rated-0.210
Token's
Token ID338
Feature activation+3.34e-01

Pos logit contributions
kin+0.441
 upon+0.407
rated+0.398
 moment+0.392
isel+0.389
Neg logit contributions
rob-0.267
 rides-0.243
ons-0.224
opl-0.222
 cand-0.198
Token perfect
Token ID2818
Feature activation-1.57e-02

Pos logit contributions
 rides+0.584
ons+0.577
rob+0.555
opl+0.533
 cand+0.516
Neg logit contributions
kin-0.596
isel-0.538
 upon-0.514
 loser-0.510
 moment-0.499
Token!"
Token ID2474
Feature activation+5.87e-02

Pos logit contributions
kin+0.031
isel+0.028
 upon+0.027
rated+0.026
inn+0.025
Neg logit contributions
 rides-0.025
rob-0.025
ons-0.024
opl-0.022
 cand-0.022
Token
Token ID220
Feature activation+9.77e-02

Pos logit contributions
rob+0.117
 rides+0.111
ons+0.107
opl+0.104
 cand+0.100
Neg logit contributions
kin-0.100
 upon-0.089
isel-0.088
 moment-0.086
rated-0.081
Token
Token ID198
Feature activation+1.45e-02

Pos logit contributions
 rides+0.157
rob+0.153
ons+0.152
opl+0.140
 kisses+0.132
Neg logit contributions
kin-0.200
isel-0.174
rated-0.170
 upon-0.169
 moment-0.166
Token
Token ID198
Feature activation+1.46e-02

Pos logit contributions
rob+0.030
 rides+0.029
ons+0.027
 cand+0.026
opl+0.026
Neg logit contributions
kin-0.024
 upon-0.021
isel-0.020
 moment-0.020
inn-0.019
Token sweep
Token ID16085
Feature activation+2.01e-02

Pos logit contributions
rob+0.125
 rides+0.122
ons+0.119
opl+0.111
 cand+0.107
Neg logit contributions
kin-0.114
isel-0.099
 upon-0.098
 moment-0.094
rated-0.094
Token,
Token ID11
Feature activation-2.96e-03

Pos logit contributions
 rides+0.037
rob+0.037
ons+0.036
opl+0.033
 cand+0.032
Neg logit contributions
kin-0.036
isel-0.032
 upon-0.031
rated-0.030
 loser-0.030
Token a
Token ID257
Feature activation-1.56e-02

Pos logit contributions
kin+0.007
inn+0.006
isel+0.006
rated+0.006
 loser+0.006
Neg logit contributions
 rides-0.004
ons-0.004
rob-0.003
 course-0.003
 kisses-0.003
Token spider
Token ID19230
Feature activation-1.75e-01

Pos logit contributions
kin+0.028
isel+0.025
 upon+0.024
rated+0.024
inn+0.023
Neg logit contributions
 rides-0.028
rob-0.028
ons-0.027
opl-0.025
 cand-0.025
Token sc
Token ID629
Feature activation+3.16e-01

Pos logit contributions
kin+0.300
 upon+0.259
isel+0.252
 moment+0.247
rated+0.242
Neg logit contributions
rob-0.343
 rides-0.329
ons-0.317
opl-0.307
 cand-0.295
Tokenur
Token ID333
Feature activation+1.86e-02

Pos logit contributions
rob+0.605
 rides+0.562
ons+0.544
opl+0.507
 cand+0.506
Neg logit contributions
kin-0.569
isel-0.527
 upon-0.525
rated-0.474
inn-0.471
Tokenried
Token ID2228
Feature activation-3.24e-01

Pos logit contributions
rob+0.040
ons+0.039
 rides+0.039
 bars+0.036
 hugs+0.034
Neg logit contributions
kin-0.026
isel-0.023
 loser-0.022
 particular-0.021
inn-0.021
Token out
Token ID503
Feature activation-1.14e-01

Pos logit contributions
kin+0.611
isel+0.525
 upon+0.493
rated+0.491
 loser+0.487
Neg logit contributions
 rides-0.598
rob-0.571
ons-0.565
opl-0.517
 course-0.501
Token!
Token ID0
Feature activation+4.31e-02

Pos logit contributions
kin+0.229
isel+0.201
 upon+0.197
rated+0.193
 moment+0.190
Neg logit contributions
 rides-0.185
rob-0.183
ons-0.179
opl-0.164
 kisses-0.156
Token He
Token ID679
Feature activation+2.79e-02

Pos logit contributions
rob+0.082
 rides+0.081
ons+0.079
opl+0.074
 cand+0.071
Neg logit contributions
kin-0.075
isel-0.065
 upon-0.065
rated-0.062
 moment-0.062
Token jumped
Token ID11687
Feature activation-2.06e-02

Pos logit contributions
rob+0.053
 rides+0.053
ons+0.051
opl+0.047
 cand+0.046
Neg logit contributions
kin-0.049
isel-0.042
 upon-0.042
rated-0.040
 moment-0.040
Token,
Token ID11
Feature activation+1.25e-03

Pos logit contributions
rob+0.374
ons+0.346
 rides+0.344
opl+0.340
cream+0.328
Neg logit contributions
kin-0.280
 upon-0.212
 moment-0.195
 loser-0.187
 particular-0.183
Token a
Token ID257
Feature activation-9.02e-03

Pos logit contributions
rob+0.003
 rides+0.003
ons+0.003
opl+0.003
handed+0.002
Neg logit contributions
kin-0.002
 upon-0.002
 moment-0.001
isel-0.001
 loser-0.001
Token princess
Token ID21752
Feature activation-1.58e-02

Pos logit contributions
kin+0.018
 upon+0.015
isel+0.015
 moment+0.015
 loser+0.014
Neg logit contributions
rob-0.016
 rides-0.015
ons-0.015
opl-0.014
cream-0.013
Token costume
Token ID16569
Feature activation+1.70e-01

Pos logit contributions
kin+0.028
 upon+0.024
isel+0.024
 moment+0.023
rated+0.023
Neg logit contributions
rob-0.030
 rides-0.030
ons-0.029
opl-0.027
 cand-0.026
Token and
Token ID290
Feature activation-5.70e-03

Pos logit contributions
rob+0.380
ons+0.351
 rides+0.350
opl+0.346
cream+0.336
Neg logit contributions
kin-0.272
 upon-0.203
 moment-0.186
 loser-0.179
 particular-0.173
Token a
Token ID257
Feature activation-9.69e-03

Pos logit contributions
kin+0.008
 upon+0.007
isel+0.006
 moment+0.006
 loser+0.006
Neg logit contributions
rob-0.013
opl-0.012
ons-0.012
 rides-0.012
handed-0.011
Token doctor
Token ID6253
Feature activation+4.76e-02

Pos logit contributions
kin+0.018
 upon+0.016
isel+0.016
 moment+0.015
 loser+0.015
Neg logit contributions
rob-0.017
 rides-0.017
ons-0.017
opl-0.016
cream-0.014
Token costume
Token ID16569
Feature activation+1.70e-01

Pos logit contributions
rob+0.103
ons+0.099
 rides+0.098
opl+0.095
 course+0.088
Neg logit contributions
kin-0.072
 upon-0.059
 moment-0.057
 loser-0.054
ac-0.053
Token.
Token ID13
Feature activation-2.86e-02

Pos logit contributions
rob+0.371
ons+0.345
 rides+0.344
opl+0.338
pill+0.313
Neg logit contributions
kin-0.267
 upon-0.218
 moment-0.197
 loser-0.191
isel-0.187
Token She
Token ID1375
Feature activation+1.16e-01

Pos logit contributions
kin+0.048
isel+0.040
rated+0.039
 upon+0.038
 moment+0.037
Neg logit contributions
 rides-0.059
rob-0.057
ons-0.054
opl-0.053
 cand-0.052
Token likes
Token ID7832
Feature activation-3.93e-02

Pos logit contributions
rob+0.222
ons+0.212
 rides+0.206
opl+0.202
cream+0.192
Neg logit contributions
kin-0.200
 upon-0.179
isel-0.167
 moment-0.163
ac-0.158
Token little
Token ID1310
Feature activation-1.90e-01

Pos logit contributions
kin+0.067
isel+0.064
rated+0.061
ided+0.058
 upon+0.058
Neg logit contributions
 rides-0.076
rob-0.072
ons-0.068
 cand-0.066
 course-0.065
Token child
Token ID1200
Feature activation-1.26e-01

Pos logit contributions
kin+0.263
isel+0.227
 upon+0.217
rated+0.211
inn+0.198
Neg logit contributions
rob-0.423
 rides-0.421
ons-0.404
opl-0.381
 cand-0.380
Token.
Token ID13
Feature activation-2.40e-02

Pos logit contributions
kin+0.208
 upon+0.189
 moment+0.173
 particular+0.170
inn+0.166
Neg logit contributions
rob-0.252
 rides-0.233
opl-0.221
ons-0.215
 cand-0.212
Token She
Token ID1375
Feature activation+1.13e-01

Pos logit contributions
kin+0.045
 upon+0.040
isel+0.040
 moment+0.038
rated+0.037
Neg logit contributions
rob-0.043
 rides-0.042
ons-0.040
opl-0.037
 cand-0.036
Token was
Token ID373
Feature activation-5.81e-02

Pos logit contributions
rob+0.241
 rides+0.229
ons+0.227
opl+0.220
 cand+0.209
Neg logit contributions
kin-0.174
 upon-0.155
 moment-0.144
isel-0.143
rated-0.140
Token very
Token ID845
Feature activation+1.09e-01

Pos logit contributions
kin+0.099
 upon+0.091
isel+0.086
 moment+0.083
 particular+0.080
Neg logit contributions
rob-0.114
 rides-0.108
ons-0.107
opl-0.101
 cand-0.096
Token curious
Token ID11040
Feature activation-1.07e-01

Pos logit contributions
 rides+0.200
rob+0.199
ons+0.192
opl+0.180
 cand+0.173
Neg logit contributions
kin-0.194
isel-0.170
 upon-0.167
rated-0.162
 moment-0.161
Token and
Token ID290
Feature activation-2.62e-03

Pos logit contributions
kin+0.164
 upon+0.151
 moment+0.142
isel+0.140
rated+0.137
Neg logit contributions
rob-0.232
 rides-0.212
ons-0.210
opl-0.202
 cand-0.188
Token loved
Token ID6151
Feature activation+4.19e-02

Pos logit contributions
kin+0.004
 upon+0.004
isel+0.004
 moment+0.003
rated+0.003
Neg logit contributions
rob-0.006
 rides-0.005
ons-0.005
opl-0.005
 cand-0.005
Token to
Token ID284
Feature activation+5.72e-02

Pos logit contributions
rob+0.087
opl+0.076
ons+0.076
 rides+0.075
handed+0.071
Neg logit contributions
 upon-0.064
kin-0.060
 moment-0.059
isel-0.056
 particular-0.054
Token collect
Token ID2824
Feature activation-5.38e-02

Pos logit contributions
rob+0.123
ons+0.109
 rides+0.106
 cand+0.104
cream+0.102
Neg logit contributions
kin-0.087
isel-0.083
 particular-0.081
 upon-0.080
 moment-0.079
Token me
Token ID502
Feature activation+1.78e-01

Pos logit contributions
rob+0.098
 rides+0.090
ons+0.087
opl+0.084
 cand+0.080
Neg logit contributions
kin-0.091
 upon-0.083
isel-0.078
 moment-0.078
rated-0.078
Token happy
Token ID3772
Feature activation-1.65e-02

Pos logit contributions
rob+0.363
 rides+0.363
ons+0.352
opl+0.332
 cand+0.319
Neg logit contributions
kin-0.282
isel-0.243
 upon-0.238
rated-0.226
 moment-0.225
Token!"
Token ID2474
Feature activation+5.66e-02

Pos logit contributions
kin+0.029
 upon+0.026
isel+0.025
 moment+0.025
rated+0.025
Neg logit contributions
rob-0.031
 rides-0.030
ons-0.030
opl-0.028
 cand-0.026
Token
Token ID220
Feature activation+9.93e-02

Pos logit contributions
rob+0.124
opl+0.117
ons+0.113
 rides+0.113
odic+0.110
Neg logit contributions
 upon-0.069
 moment-0.069
kin-0.062
 don-0.057
 L-0.057
Token
Token ID198
Feature activation+1.47e-02

Pos logit contributions
 rides+0.162
rob+0.160
ons+0.156
opl+0.146
 kisses+0.134
Neg logit contributions
kin-0.202
isel-0.177
rated-0.172
 upon-0.171
 moment-0.169
Token
Token ID198
Feature activation+1.51e-02

Pos logit contributions
rob+0.030
 rides+0.029
ons+0.028
opl+0.028
 cand+0.027
Neg logit contributions
kin-0.023
 upon-0.021
 moment-0.020
isel-0.019
inn-0.019
TokenThe
Token ID464
Feature activation+7.68e-02

Pos logit contributions
rob+0.033
ons+0.031
 rides+0.031
opl+0.030
 kisses+0.029
Neg logit contributions
kin-0.022
 upon-0.019
 moment-0.018
cca-0.018
isel-0.018
Token little
Token ID1310
Feature activation-1.70e-01

Pos logit contributions
 rides+0.151
rob+0.140
ons+0.138
 cand+0.137
opl+0.128
Neg logit contributions
kin-0.127
isel-0.116
inn-0.109
rated-0.106
udge-0.106
Token boy
Token ID2933
Feature activation-1.83e-01

Pos logit contributions
kin+0.232
isel+0.192
 upon+0.181
rated+0.180
inn+0.175
Neg logit contributions
 rides-0.391
rob-0.385
ons-0.372
 cand-0.360
opl-0.345
Token smiled
Token ID13541
Feature activation+3.62e-02

Pos logit contributions
kin+0.307
 upon+0.276
 moment+0.259
isel+0.256
rated+0.249
Neg logit contributions
rob-0.372
opl-0.344
 rides-0.341
ons-0.340
pill-0.301
Token and
Token ID290
Feature activation-1.94e-03

Pos logit contributions
 rides+0.049
 kisses+0.043
rob+0.043
 hugs+0.042
ons+0.040
Neg logit contributions
kin-0.083
isel-0.076
rated-0.072
 loser-0.071
 footing-0.068
Token hug
Token ID16225
Feature activation+1.27e-01

Pos logit contributions
kin+0.022
 upon+0.020
 moment+0.019
isel+0.018
 particular+0.017
Neg logit contributions
rob-0.022
 rides-0.021
opl-0.021
ons-0.020
handed-0.018
Token and
Token ID290
Feature activation+2.40e-03

Pos logit contributions
rob+0.270
 rides+0.262
ons+0.255
opl+0.245
pill+0.229
Neg logit contributions
kin-0.202
 upon-0.170
 moment-0.163
isel-0.158
 loser-0.154
Token a
Token ID257
Feature activation-1.19e-02

Pos logit contributions
opl+0.006
rob+0.006
ons+0.005
handed+0.005
rell+0.005
Neg logit contributions
kin-0.003
 upon-0.002
 moment-0.002
isel-0.002
 disaster-0.002
Token kiss
Token ID9245
Feature activation+6.63e-02

Pos logit contributions
kin+0.022
 upon+0.020
 moment+0.020
isel+0.017
 particular+0.017
Neg logit contributions
rob-0.023
 rides-0.022
opl-0.021
ons-0.021
handed-0.019
Token,
Token ID11
Feature activation+3.46e-03

Pos logit contributions
rob+0.124
 rides+0.122
ons+0.119
opl+0.110
 cand+0.107
Neg logit contributions
kin-0.116
isel-0.105
 upon-0.102
rated-0.099
 moment-0.096
Token and
Token ID290
Feature activation+2.83e-03

Pos logit contributions
rob+0.008
 rides+0.007
ons+0.007
opl+0.007
 cand+0.007
Neg logit contributions
kin-0.005
 upon-0.004
isel-0.004
 moment-0.004
rated-0.004
Token a
Token ID257
Feature activation-1.20e-02

Pos logit contributions
opl+0.006
rob+0.005
ons+0.005
rell+0.005
 rides+0.005
Neg logit contributions
kin-0.005
 upon-0.004
 moment-0.004
isel-0.004
cca-0.004
Token cookie
Token ID19751
Feature activation+1.68e-01

Pos logit contributions
kin+0.023
 moment+0.020
 upon+0.020
 loser+0.018
isel+0.018
Neg logit contributions
rob-0.023
 rides-0.021
ons-0.021
opl-0.020
cream-0.019
Token each
Token ID1123
Feature activation+3.03e-03

Pos logit contributions
rob+0.382
 rides+0.365
ons+0.362
opl+0.356
pill+0.330
Neg logit contributions
kin-0.264
 moment-0.191
 upon-0.191
 loser-0.182
inn-0.173
Token.
Token ID13
Feature activation-1.14e-02

Pos logit contributions
rob+0.006
 rides+0.006
ons+0.006
opl+0.005
 cand+0.005
Neg logit contributions
kin-0.005
isel-0.005
 upon-0.005
rated-0.004
 moment-0.004
Token
Token ID198
Feature activation+1.97e-02

Pos logit contributions
kin+0.026
rated+0.024
isel+0.023
 upon+0.022
 moment+0.022
Neg logit contributions
 rides-0.016
rob-0.015
ons-0.015
opl-0.014
 kisses-0.013
Token,
Token ID11
Feature activation+1.12e-02

Pos logit contributions
kin+0.005
isel+0.005
rated+0.005
cca+0.005
 upon+0.005
Neg logit contributions
 rides-0.004
ons-0.004
rob-0.003
 course-0.003
 kisses-0.003
Token mom
Token ID1995
Feature activation-1.78e-01

Pos logit contributions
rob+0.027
 rides+0.026
ons+0.026
opl+0.024
 cand+0.024
Neg logit contributions
kin-0.014
isel-0.012
 upon-0.012
rated-0.011
 moment-0.011
Token.
Token ID13
Feature activation-2.30e-02

Pos logit contributions
kin+0.228
 upon+0.207
 moment+0.193
ac+0.174
 loser+0.174
Neg logit contributions
rob-0.420
 rides-0.402
ons-0.385
opl-0.378
pill-0.361
Token Let
Token ID3914
Feature activation-1.05e-01

Pos logit contributions
kin+0.047
isel+0.043
 upon+0.042
rated+0.041
 moment+0.040
Neg logit contributions
 rides-0.036
rob-0.036
ons-0.034
opl-0.031
 kisses-0.031
Token's
Token ID338
Feature activation+3.42e-01

Pos logit contributions
kin+0.258
 moment+0.245
 upon+0.244
rated+0.240
 disaster+0.230
Neg logit contributions
rob-0.120
opl-0.100
 rides-0.098
ons-0.098
cream-0.089
Token dance
Token ID9280
Feature activation-3.85e-02

Pos logit contributions
 rides+0.517
ons+0.455
 kisses+0.441
rob+0.434
 hugs+0.422
Neg logit contributions
kin-0.706
isel-0.663
rated-0.640
 upon-0.631
inn-0.627
Token together
Token ID1978
Feature activation+1.09e-01

Pos logit contributions
kin+0.075
isel+0.074
rated+0.068
 upon+0.066
inn+0.064
Neg logit contributions
 rides-0.064
rob-0.061
ons-0.058
 kisses-0.054
opl-0.052
Token.
Token ID13
Feature activation-2.29e-02

Pos logit contributions
 rides+0.189
rob+0.180
ons+0.178
opl+0.162
 kisses+0.160
Neg logit contributions
kin-0.206
isel-0.193
rated-0.178
 upon-0.177
inn-0.171
Token And
Token ID843
Feature activation+1.27e-01

Pos logit contributions
kin+0.045
isel+0.040
 upon+0.040
rated+0.039
inn+0.037
Neg logit contributions
 rides-0.038
rob-0.037
ons-0.034
 kisses-0.034
opl-0.033
Token then
Token ID788
Feature activation+8.93e-03

Pos logit contributions
 rides+0.207
rob+0.183
ons+0.179
 kisses+0.171
 cand+0.169
Neg logit contributions
kin-0.257
isel-0.241
rated-0.235
inn-0.228
 upon-0.227
Token we
Token ID356
Feature activation+7.25e-02

Pos logit contributions
 rides+0.013
ons+0.012
rob+0.012
 kisses+0.011
 hugs+0.011
Neg logit contributions
kin-0.020
isel-0.018
inn-0.018
 upon-0.017
rated-0.017
Token.
Token ID13
Feature activation-2.40e-02

Pos logit contributions
kin+0.032
isel+0.028
rated+0.027
 upon+0.027
 moment+0.026
Neg logit contributions
 rides-0.032
rob-0.031
ons-0.031
opl-0.028
 cand-0.028
Token
Token ID198
Feature activation+2.32e-02

Pos logit contributions
kin+0.058
rated+0.054
isel+0.053
 footing+0.051
 upon+0.049
Neg logit contributions
 rides-0.031
rob-0.028
ons-0.027
 kisses-0.026
opl-0.024
Token
Token ID198
Feature activation+2.37e-02

Pos logit contributions
rob+0.045
 rides+0.043
ons+0.042
opl+0.040
 cand+0.038
Neg logit contributions
kin-0.040
 upon-0.036
isel-0.035
 moment-0.034
rated-0.032
TokenAfter
Token ID3260
Feature activation-6.79e-02

Pos logit contributions
rob+0.047
 rides+0.047
ons+0.046
opl+0.043
 cand+0.041
Neg logit contributions
kin-0.039
isel-0.034
 upon-0.034
rated-0.032
 moment-0.032
Token a
Token ID257
Feature activation-5.37e-03

Pos logit contributions
kin+0.111
 upon+0.092
isel+0.090
 moment+0.089
 loser+0.084
Neg logit contributions
rob-0.142
 rides-0.135
opl-0.132
ons-0.130
pill-0.119
Token while
Token ID981
Feature activation-2.01e-01

Pos logit contributions
kin+0.008
isel+0.007
rated+0.006
 upon+0.006
ac+0.006
Neg logit contributions
 rides-0.011
rob-0.011
ons-0.011
 cand-0.011
 course-0.010
Token,
Token ID11
Feature activation+6.33e-03

Pos logit contributions
kin+0.417
rated+0.407
isel+0.388
 upon+0.376
cca+0.368
Neg logit contributions
 rides-0.301
ons-0.296
rob-0.277
 kisses-0.252
 course-0.251
Token they
Token ID484
Feature activation-3.93e-03

Pos logit contributions
 rides+0.008
 cookies+0.007
ons+0.006
 kisses+0.006
 bars+0.006
Neg logit contributions
rated-0.015
kin-0.015
isel-0.015
ac-0.015
inn-0.014
Token finish
Token ID5461
Feature activation+9.84e-02

Pos logit contributions
kin+0.007
isel+0.006
 upon+0.006
 moment+0.006
rated+0.006
Neg logit contributions
rob-0.007
 rides-0.007
ons-0.007
opl-0.007
 cand-0.006
Token the
Token ID262
Feature activation-1.64e-02

Pos logit contributions
 rides+0.147
ons+0.143
rob+0.121
 kisses+0.120
 cookies+0.118
Neg logit contributions
rated-0.209
kin-0.202
isel-0.200
 loser-0.188
cca-0.179
Token puzzle
Token ID15027
Feature activation+1.38e-01

Pos logit contributions
kin+0.036
 upon+0.032
 moment+0.032
isel+0.031
 loser+0.030
Neg logit contributions
rob-0.025
 rides-0.023
ons-0.022
opl-0.021
cream-0.020
Token
Token ID198
Feature activation+1.27e-02

Pos logit contributions
kin+0.039
isel+0.034
rated+0.033
 upon+0.032
 moment+0.032
Neg logit contributions
 rides-0.037
rob-0.036
ons-0.035
opl-0.033
 cand-0.032
Token
Token ID198
Feature activation+1.27e-02

Pos logit contributions
 rides+0.019
rob+0.019
ons+0.018
opl+0.016
 kisses+0.015
Neg logit contributions
kin-0.028
isel-0.025
rated-0.025
 loser-0.024
 upon-0.023
Token"
Token ID1
Feature activation-7.24e-02

Pos logit contributions
 rides+0.023
rob+0.023
ons+0.022
opl+0.020
 course+0.019
Neg logit contributions
kin-0.023
isel-0.021
 upon-0.020
rated-0.020
 moment-0.019
TokenLook
Token ID8567
Feature activation-6.52e-02

Pos logit contributions
kin+0.121
isel+0.112
 upon+0.105
rated+0.102
 footing+0.100
Neg logit contributions
rob-0.150
 rides-0.142
ons-0.133
 course-0.127
 cand-0.126
Token,
Token ID11
Feature activation-2.26e-03

Pos logit contributions
kin+0.133
rated+0.119
isel+0.119
 moment+0.115
 loser+0.113
Neg logit contributions
 rides-0.107
ons-0.106
rob-0.095
 cand-0.090
 kisses-0.089
Token Sam
Token ID3409
Feature activation-1.01e-01

Pos logit contributions
kin+0.004
isel+0.003
rated+0.003
 upon+0.003
 moment+0.003
Neg logit contributions
 rides-0.005
rob-0.004
ons-0.004
 cand-0.004
opl-0.004
Token,
Token ID11
Feature activation-7.75e-04

Pos logit contributions
kin+0.179
 upon+0.156
isel+0.155
 moment+0.148
rated+0.148
Neg logit contributions
rob-0.190
 rides-0.188
ons-0.182
opl-0.171
 cand-0.163
Token that
Token ID326
Feature activation+2.47e-01

Pos logit contributions
kin+0.001
isel+0.001
 upon+0.001
 moment+0.001
rated+0.001
Neg logit contributions
rob-0.001
 rides-0.001
ons-0.001
opl-0.001
 cand-0.001
Token star
Token ID3491
Feature activation-1.51e-01

Pos logit contributions
rob+0.474
 rides+0.454
ons+0.443
opl+0.424
 cand+0.402
Neg logit contributions
kin-0.428
 upon-0.382
 moment-0.371
isel-0.363
rated-0.349
Token is
Token ID318
Feature activation+4.60e-02

Pos logit contributions
kin+0.272
 upon+0.236
 moment+0.227
rated+0.216
isel+0.215
Neg logit contributions
rob-0.293
 rides-0.278
opl-0.257
ons-0.257
 cand-0.246
Token so
Token ID523
Feature activation+1.91e-01

Pos logit contributions
rob+0.077
 rides+0.073
ons+0.071
opl+0.065
 cand+0.062
Neg logit contributions
kin-0.093
 upon-0.084
isel-0.081
 moment-0.080
rated-0.078
Token clock
Token ID8801
Feature activation+1.12e-02

Pos logit contributions
kin+0.076
isel+0.067
 upon+0.067
rated+0.064
 moment+0.064
Neg logit contributions
rob-0.071
 rides-0.071
ons-0.068
opl-0.064
 cand-0.061
Token to
Token ID284
Feature activation+4.96e-02

Pos logit contributions
rob+0.023
 rides+0.021
ons+0.020
opl+0.020
 cand+0.019
Neg logit contributions
kin-0.019
 upon-0.017
 moment-0.016
isel-0.016
rated-0.015
Token Sus
Token ID8932
Feature activation-1.79e-01

Pos logit contributions
 rides+0.094
rob+0.093
ons+0.091
opl+0.084
 cand+0.081
Neg logit contributions
kin-0.086
isel-0.075
 upon-0.074
rated-0.072
 moment-0.070
Tokenie
Token ID494
Feature activation-6.53e-02

Pos logit contributions
kin+0.319
isel+0.279
 upon+0.268
 moment+0.259
 loser+0.259
Neg logit contributions
rob-0.335
 rides-0.331
ons-0.328
opl-0.300
 cand-0.288
Token's
Token ID338
Feature activation+3.17e-01

Pos logit contributions
kin+0.119
 upon+0.108
 moment+0.102
isel+0.101
rated+0.097
Neg logit contributions
rob-0.125
 rides-0.113
ons-0.110
opl-0.107
 cand-0.100
Token bedroom
Token ID14043
Feature activation-7.62e-02

Pos logit contributions
rob+0.630
 rides+0.595
ons+0.587
opl+0.550
 cand+0.519
Neg logit contributions
kin-0.547
 upon-0.480
isel-0.469
 moment-0.455
rated-0.438
Token wall
Token ID3355
Feature activation-2.26e-02

Pos logit contributions
kin+0.131
 upon+0.114
isel+0.110
 moment+0.107
rated+0.105
Neg logit contributions
rob-0.150
 rides-0.144
ons-0.141
opl-0.134
 cand-0.126
Token.
Token ID13
Feature activation-3.18e-02

Pos logit contributions
kin+0.038
 upon+0.033
 moment+0.031
isel+0.031
rated+0.030
Neg logit contributions
rob-0.046
 rides-0.043
ons-0.042
opl-0.041
 cand-0.039
Token
Token ID198
Feature activation+3.80e-03

Pos logit contributions
kin+0.064
isel+0.054
rated+0.053
 loser+0.052
 upon+0.051
Neg logit contributions
 rides-0.053
rob-0.052
ons-0.051
opl-0.048
 kisses-0.046
Token
Token ID198
Feature activation+4.01e-03

Pos logit contributions
 rides+0.006
rob+0.006
ons+0.006
opl+0.005
 kisses+0.005
Neg logit contributions
kin-0.008
isel-0.007
rated-0.007
 loser-0.007
 footing-0.007
TokenSus
Token ID30746
Feature activation-7.45e-02

Pos logit contributions
 rides+0.007
rob+0.007
ons+0.007
opl+0.006
 cand+0.006
Neg logit contributions
kin-0.007
isel-0.007
rated-0.006
 upon-0.006
 moment-0.006
Token cr
Token ID1067
Feature activation+6.66e-02

Pos logit contributions
kin+0.043
isel+0.039
rated+0.038
 upon+0.038
inn+0.036
Neg logit contributions
 rides-0.039
rob-0.039
ons-0.038
 cand-0.035
opl-0.034
Tokenay
Token ID323
Feature activation-1.08e-02

Pos logit contributions
rob+0.137
 rides+0.134
ons+0.122
 cand+0.118
opl+0.115
Neg logit contributions
kin-0.112
isel-0.097
 upon-0.094
inn-0.091
rated-0.087
Tokenon
Token ID261
Feature activation+2.29e-01

Pos logit contributions
kin+0.029
 upon+0.026
isel+0.026
 moment+0.025
rated+0.025
Neg logit contributions
rob-0.011
 rides-0.011
ons-0.009
opl-0.009
 cand-0.008
Token!
Token ID0
Feature activation+3.64e-02

Pos logit contributions
rob+0.436
 rides+0.418
ons+0.398
opl+0.380
 cand+0.363
Neg logit contributions
kin-0.419
 upon-0.362
isel-0.350
 moment-0.340
rated-0.334
Token He
Token ID679
Feature activation+1.84e-02

Pos logit contributions
rob+0.065
 rides+0.065
ons+0.063
opl+0.059
 cand+0.056
Neg logit contributions
kin-0.067
isel-0.058
 upon-0.058
rated-0.056
 moment-0.056
Token felt
Token ID2936
Feature activation-5.70e-02

Pos logit contributions
 rides+0.032
ons+0.032
rob+0.031
 cand+0.028
 kisses+0.028
Neg logit contributions
kin-0.034
isel-0.030
 upon-0.029
 loser-0.029
rated-0.029
Token excited
Token ID6568
Feature activation-8.72e-02

Pos logit contributions
kin+0.109
isel+0.095
 upon+0.095
rated+0.095
 moment+0.092
Neg logit contributions
 rides-0.098
ons-0.094
rob-0.093
opl-0.086
 cand-0.084
Token and
Token ID290
Feature activation-9.04e-03

Pos logit contributions
kin+0.135
 upon+0.125
 moment+0.118
isel+0.116
rated+0.114
Neg logit contributions
rob-0.184
 rides-0.172
ons-0.170
opl-0.164
 cand-0.152
Token grabbed
Token ID13176
Feature activation-4.50e-02

Pos logit contributions
kin+0.015
 upon+0.013
isel+0.013
 moment+0.012
rated+0.012
Neg logit contributions
rob-0.019
 rides-0.018
ons-0.017
opl-0.017
 cand-0.016
Token it
Token ID340
Feature activation-1.99e-01

Pos logit contributions
kin+0.096
rated+0.092
 loser+0.085
 upon+0.081
OO+0.080
Neg logit contributions
ons-0.075
 rides-0.072
 hugs-0.063
 course-0.062
rob-0.062
Token.
Token ID13
Feature activation-2.54e-02

Pos logit contributions
kin+0.319
 upon+0.281
isel+0.267
 moment+0.263
rated+0.254
Neg logit contributions
rob-0.424
 rides-0.400
ons-0.392
opl-0.375
 cand-0.354
Token in
Token ID287
Feature activation-9.64e-02

Pos logit contributions
kin+0.057
 upon+0.049
isel+0.044
 moment+0.044
inn+0.040
Neg logit contributions
rob-0.114
opl-0.107
ons-0.104
 rides-0.103
pill-0.100
Token it
Token ID340
Feature activation-1.93e-01

Pos logit contributions
kin+0.182
isel+0.170
rated+0.169
inn+0.158
 upon+0.156
Neg logit contributions
 rides-0.169
ons-0.160
rob-0.151
 course-0.144
opl-0.144
Token.
Token ID13
Feature activation-1.80e-02

Pos logit contributions
kin+0.284
 upon+0.244
 moment+0.226
rated+0.211
isel+0.210
Neg logit contributions
rob-0.446
 rides-0.409
ons-0.406
opl-0.397
pill-0.373
Token But
Token ID887
Feature activation-1.62e-01

Pos logit contributions
kin+0.035
isel+0.030
 upon+0.030
rated+0.029
 moment+0.028
Neg logit contributions
 rides-0.032
rob-0.031
ons-0.030
opl-0.028
 cand-0.026
Token over
Token ID625
Feature activation-5.39e-02

Pos logit contributions
kin+0.292
isel+0.276
rated+0.264
udge+0.256
inn+0.249
Neg logit contributions
 rides-0.286
ons-0.265
rob-0.261
 course-0.257
 cand-0.250
Token time
Token ID640
Feature activation-2.94e-01

Pos logit contributions
kin+0.113
isel+0.101
rated+0.100
inn+0.096
 upon+0.093
Neg logit contributions
 rides-0.090
ons-0.084
 course-0.080
rob-0.080
 cand-0.075
Token,
Token ID11
Feature activation-8.01e-04

Pos logit contributions
kin+0.626
isel+0.592
rated+0.569
inn+0.543
udge+0.541
Neg logit contributions
 rides-0.474
ons-0.445
rob-0.414
 cand-0.378
 kisses-0.362
Token the
Token ID262
Feature activation-1.98e-02

Pos logit contributions
kin+0.002
isel+0.001
rated+0.001
inn+0.001
 upon+0.001
Neg logit contributions
 rides-0.001
ons-0.001
rob-0.001
 cand-0.001
 course-0.001
Token bin
Token ID9874
Feature activation+1.01e-01

Pos logit contributions
kin+0.044
isel+0.040
 upon+0.039
rated+0.038
inn+0.037
Neg logit contributions
 rides-0.028
rob-0.027
ons-0.026
 cand-0.024
opl-0.024
Token began
Token ID2540
Feature activation+8.29e-03

Pos logit contributions
rob+0.202
 rides+0.198
ons+0.192
opl+0.182
 cand+0.174
Neg logit contributions
kin-0.166
 upon-0.143
isel-0.142
 moment-0.135
rated-0.135
Token to
Token ID284
Feature activation+6.55e-02

Pos logit contributions
 rides+0.013
rob+0.012
ons+0.012
opl+0.011
 cand+0.011
Neg logit contributions
kin-0.018
isel-0.016
 upon-0.015
rated-0.015
 moment-0.015
Token said
Token ID531
Feature activation+2.11e-01

Pos logit contributions
kin+0.005
 upon+0.005
isel+0.005
 moment+0.005
rated+0.005
Neg logit contributions
rob-0.005
 rides-0.005
ons-0.005
opl-0.005
 cand-0.004
Token,
Token ID11
Feature activation-2.45e-03

Pos logit contributions
 rides+0.326
ons+0.320
rob+0.298
 cand+0.286
 kisses+0.282
Neg logit contributions
kin-0.435
isel-0.397
rated-0.395
 upon-0.372
 loser-0.370
Token "
Token ID366
Feature activation-1.45e-01

Pos logit contributions
kin+0.004
isel+0.003
rated+0.003
 loser+0.003
ac+0.003
Neg logit contributions
 rides-0.005
ons-0.005
rob-0.005
 kisses-0.004
opl-0.004
TokenIt
Token ID1026
Feature activation-9.97e-02

Pos logit contributions
kin+0.237
isel+0.202
 upon+0.195
rated+0.187
 loser+0.180
Neg logit contributions
rob-0.300
 rides-0.294
ons-0.285
opl-0.267
 course-0.259
Token's
Token ID338
Feature activation+3.34e-01

Pos logit contributions
kin+0.247
 upon+0.238
 moment+0.232
rated+0.231
isel+0.228
Neg logit contributions
rob-0.119
 rides-0.104
ons-0.096
opl-0.095
 cand-0.084
Token time
Token ID640
Feature activation-2.93e-01

Pos logit contributions
 rides+0.594
ons+0.572
opl+0.556
 kisses+0.545
rob+0.545
Neg logit contributions
kin-0.572
isel-0.543
 loser-0.493
ges-0.474
udge-0.464
Token for
Token ID329
Feature activation-1.11e-02

Pos logit contributions
kin+0.607
isel+0.540
rated+0.508
 upon+0.504
 loser+0.504
Neg logit contributions
 rides-0.461
ons-0.444
rob-0.440
opl-0.396
 kisses-0.394
Token bed
Token ID3996
Feature activation+1.39e-01

Pos logit contributions
kin+0.022
 upon+0.020
 moment+0.019
isel+0.019
 disaster+0.019
Neg logit contributions
rob-0.020
 rides-0.017
opl-0.017
ons-0.017
pill-0.016
Token now
Token ID783
Feature activation+5.74e-03

Pos logit contributions
rob+0.277
 rides+0.268
ons+0.264
opl+0.250
 cand+0.236
Neg logit contributions
kin-0.236
 upon-0.202
isel-0.192
 moment-0.191
rated-0.191
Token."
Token ID526
Feature activation+2.12e-02

Pos logit contributions
rob+0.011
 rides+0.010
ons+0.010
opl+0.009
 cand+0.009
Neg logit contributions
kin-0.010
isel-0.009
 upon-0.009
rated-0.009
 moment-0.009
Token As
Token ID1081
Feature activation-9.24e-02

Pos logit contributions
rob+0.037
 rides+0.037
ons+0.035
opl+0.033
 cand+0.032
Neg logit contributions
kin-0.040
isel-0.036
 upon-0.035
rated-0.034
 moment-0.034
Token to
Token ID284
Feature activation+6.44e-02

Pos logit contributions
rob+0.042
opl+0.037
 rides+0.036
ons+0.036
odic+0.034
Neg logit contributions
kin-0.030
 upon-0.029
isel-0.028
 moment-0.027
 loser-0.026
Token keep
Token ID1394
Feature activation-6.11e-02

Pos logit contributions
rob+0.145
ons+0.129
 rides+0.126
pill+0.125
opl+0.123
Neg logit contributions
kin-0.100
isel-0.087
 upon-0.086
 moment-0.085
 don-0.084
Token the
Token ID262
Feature activation-1.91e-02

Pos logit contributions
kin+0.090
 upon+0.082
 moment+0.077
 halfway+0.077
isel+0.076
Neg logit contributions
rob-0.128
opl-0.112
 rides-0.110
pill-0.108
grand-0.107
Token tw
Token ID665
Feature activation-8.02e-03

Pos logit contributions
kin+0.038
 upon+0.033
 moment+0.033
isel+0.033
rated+0.032
Neg logit contributions
rob-0.032
 rides-0.031
ons-0.030
opl-0.029
cream-0.026
Tokenig
Token ID328
Feature activation-1.54e-01

Pos logit contributions
kin+0.012
isel+0.010
 upon+0.010
rated+0.010
 loser+0.010
Neg logit contributions
rob-0.017
 rides-0.017
ons-0.017
opl-0.016
 cand-0.015
Token if
Token ID611
Feature activation-2.99e-01

Pos logit contributions
kin+0.266
 upon+0.225
 moment+0.218
rated+0.210
isel+0.206
Neg logit contributions
rob-0.321
 rides-0.305
ons-0.287
opl-0.280
pill-0.268
Token you
Token ID345
Feature activation+2.53e-01

Pos logit contributions
kin+0.765
isel+0.704
 upon+0.694
rated+0.680
 moment+0.672
Neg logit contributions
 rides-0.321
rob-0.315
ons-0.303
opl-0.257
 cand-0.244
Token don
Token ID836
Feature activation-3.59e-01

Pos logit contributions
rob+0.569
 rides+0.560
ons+0.547
opl+0.519
 cand+0.500
Neg logit contributions
kin-0.353
 upon-0.296
isel-0.295
rated-0.276
 moment-0.276
Token't
Token ID470
Feature activation+4.31e-02

Pos logit contributions
kin+0.566
 upon+0.474
inn+0.472
isel+0.471
 loser+0.462
Neg logit contributions
rob-0.716
 rides-0.686
 cand-0.645
ons-0.640
 kisses-0.626
Token like
Token ID588
Feature activation-1.62e-01

Pos logit contributions
rob+0.097
 rides+0.093
ons+0.092
opl+0.087
 cand+0.083
Neg logit contributions
kin-0.062
 upon-0.053
isel-0.053
rated-0.050
 moment-0.050
Token it
Token ID340
Feature activation-1.92e-01

Pos logit contributions
kin+0.220
isel+0.184
 upon+0.179
rated+0.175
 moment+0.167
Neg logit contributions
 rides-0.380
rob-0.369
ons-0.368
opl-0.345
 cand-0.337
Token were
Token ID547
Feature activation+3.62e-02

Pos logit contributions
kin+0.007
 upon+0.006
isel+0.006
 moment+0.006
rated+0.006
Neg logit contributions
rob-0.009
 rides-0.009
ons-0.008
opl-0.008
pill-0.008
Token happy
Token ID3772
Feature activation-1.76e-02

Pos logit contributions
rob+0.074
 rides+0.069
ons+0.068
opl+0.067
pill+0.063
Neg logit contributions
kin-0.064
 upon-0.052
isel-0.051
 loser-0.049
cca-0.049
Token.
Token ID13
Feature activation-8.53e-03

Pos logit contributions
kin+0.030
 upon+0.026
isel+0.025
 moment+0.024
rated+0.024
Neg logit contributions
rob-0.035
 rides-0.034
ons-0.033
opl-0.031
 cand-0.030
Token<|endoftext|>
Token ID50256
Feature activation-6.21e-03

Pos logit contributions
kin+0.019
isel+0.018
rated+0.017
 upon+0.016
 footing+0.016
Neg logit contributions
 rides-0.012
rob-0.012
 kisses-0.011
ons-0.010
opl-0.010
TokenL
Token ID43
Feature activation-1.01e-01

Pos logit contributions
kin+0.011
isel+0.010
rated+0.010
 upon+0.010
 moment+0.009
Neg logit contributions
rob-0.011
 rides-0.011
ons-0.011
opl-0.010
 cand-0.009
Tokenila
Token ID10102
Feature activation-3.11e-01

Pos logit contributions
kin+0.128
isel+0.110
rated+0.106
 upon+0.101
 moment+0.100
Neg logit contributions
 rides-0.239
rob-0.239
ons-0.238
opl-0.216
 cand-0.215
Token and
Token ID290
Feature activation+2.46e-03

Pos logit contributions
kin+0.479
 upon+0.410
 moment+0.385
isel+0.383
rated+0.367
Neg logit contributions
rob-0.652
 rides-0.617
ons-0.611
opl-0.603
 cand-0.563
Token Ben
Token ID3932
Feature activation-1.62e-01

Pos logit contributions
rob+0.005
 rides+0.005
ons+0.005
opl+0.005
 cand+0.005
Neg logit contributions
kin-0.004
 upon-0.003
isel-0.003
 moment-0.003
rated-0.003
Token were
Token ID547
Feature activation+3.71e-02

Pos logit contributions
kin+0.288
 upon+0.252
isel+0.250
 moment+0.239
rated+0.238
Neg logit contributions
rob-0.302
 rides-0.295
ons-0.288
opl-0.271
 cand-0.257
Token playing
Token ID2712
Feature activation+1.84e-01

Pos logit contributions
rob+0.073
 rides+0.065
ons+0.064
opl+0.063
cream+0.063
Neg logit contributions
kin-0.066
 upon-0.065
ac-0.055
inn-0.054
isel-0.053
Token in
Token ID287
Feature activation-8.48e-02

Pos logit contributions
 rides+0.346
rob+0.339
ons+0.332
 course+0.302
 cand+0.289
Neg logit contributions
kin-0.319
isel-0.297
rated-0.297
 upon-0.278
 moment-0.270
Token loyal
Token ID9112
Feature activation+7.96e-02

Pos logit contributions
kin+0.023
 upon+0.020
isel+0.020
 moment+0.019
rated+0.019
Neg logit contributions
rob-0.021
 rides-0.021
ons-0.020
opl-0.019
 cand-0.018
Token dog
Token ID3290
Feature activation+2.65e-02

Pos logit contributions
 rides+0.144
rob+0.133
ons+0.129
 cand+0.129
opl+0.121
Neg logit contributions
kin-0.144
isel-0.131
rated-0.128
 upon-0.125
inn-0.121
Token."
Token ID526
Feature activation+1.89e-02

Pos logit contributions
rob+0.055
ons+0.052
 rides+0.052
opl+0.050
 cand+0.047
Neg logit contributions
kin-0.042
 upon-0.038
 moment-0.034
 loser-0.034
rated-0.033
Token Jack
Token ID3619
Feature activation-2.95e-02

Pos logit contributions
rob+0.046
 rides+0.043
opl+0.042
ons+0.042
 cand+0.039
Neg logit contributions
kin-0.023
 upon-0.022
 moment-0.020
isel-0.020
inn-0.018
Token cheer
Token ID14042
Feature activation+4.83e-02

Pos logit contributions
kin+0.048
 upon+0.042
isel+0.040
 moment+0.040
rated+0.039
Neg logit contributions
rob-0.061
 rides-0.058
ons-0.058
opl-0.056
 cand-0.051
Tokenfully
Token ID2759
Feature activation-3.04e-01

Pos logit contributions
ons+0.096
 rides+0.095
rob+0.090
 hugs+0.090
 kisses+0.090
Neg logit contributions
isel-0.068
kin-0.066
 loser-0.060
 particular-0.055
 bet-0.055
Token said
Token ID531
Feature activation+2.17e-01

Pos logit contributions
kin+0.415
 moment+0.375
 upon+0.372
ided+0.364
inn+0.358
Neg logit contributions
rob-0.725
ons-0.660
opl-0.660
 rides-0.608
pill-0.584
Token,
Token ID11
Feature activation+2.67e-03

Pos logit contributions
 rides+0.350
ons+0.341
rob+0.322
 cand+0.308
 kisses+0.306
Neg logit contributions
kin-0.409
isel-0.380
 upon-0.371
rated-0.370
inn-0.353
Token "
Token ID366
Feature activation-1.40e-01

Pos logit contributions
 rides+0.006
rob+0.006
ons+0.006
opl+0.005
 cand+0.005
Neg logit contributions
kin-0.004
isel-0.003
 upon-0.003
rated-0.003
 loser-0.003
TokenYes
Token ID5297
Feature activation-8.74e-03

Pos logit contributions
kin+0.278
isel+0.246
 upon+0.241
rated+0.231
 moment+0.227
Neg logit contributions
rob-0.238
 rides-0.235
ons-0.224
opl-0.209
 cand-0.197
Token!"
Token ID2474
Feature activation+6.04e-02

Pos logit contributions
kin+0.018
isel+0.016
 upon+0.016
rated+0.016
 moment+0.015
Neg logit contributions
 rides-0.013
ons-0.013
rob-0.012
 course-0.012
 cand-0.011