TOP ACTIVATIONS
MAX = 10.493

grandma 's house for safe keeping . When
it to me for safe keeping . He told me to
! That 's how all masks should be organized ."
on her favorite p aj amas and sn ugg led up
to the direction of the leash . Little
see that his favorite red sweater had a big hole in
proceeded to guess what the shield was for . Was it
and R uf us ' itch was gone !
, she figured out which mattress to pick . It was
on a leash . The leash was a long , red
him . Suddenly , the leash came off the collar and
dry and cozy p aj amas and sn ugg led in
. He put up some bases and got some balls .
wearing his favourite py j amas , feeling so proud of
eat the y ummy ins ides . From that day on
What is the r iddle ? â
to see what all the fuss was about . " What
put on his p aj amas and went to bed .
to measure how big the maze was so she knew exactly
I folded up those paper towels for our nap kins ?

MIN ACTIVATIONS
MIN = -17.445

helped the old lady fix the fence .
why he had fixed her the screen . "
you . I will fix the pengu in . Then you
him if he would share the pie with her .
neighbor to help them repair the tractor .
little boy to put away the hose and come inside .
should be able to fix the dress ."
showed him how to fix the branch . From that day
" Maybe we can share the ball with him . Maybe
Look . I have fixed the important roof . Let 's
going to help us fix the screen ." The
let me help you carry the ac orn home ? I
did not want to share the seal . He
! You need to share the ball ." Buddy and Wh
learned to be careful of the crabs . <|endoftext|> Ben and
she would try to fix the train . She said they
They discuss how to share the sausage . They
I should not have taken the boot . That was rude
Can you help me split the fruit ?" The cow tried
and helped her dad fix the fence . She had fun

INTERVAL 3.508 - 10.493
CONTAINS 13.941%

s a surprise . I â ll
to the park that day . They cried and cried until
mom . She told her mom all about her adventure with
the tree again . His dad warned him against it ,
wanted a watch . The watch was very attractive and she

INTERVAL -3.476 - 3.508
CONTAINS 71.677%

in the frame . <|endoftext|> Once upon a time , in
not yours !" Ben yelled . The man tried
. She was very troubled . She did not know what
that if he was ever feeling miserable again , he could
my . " Let me try ," said Billy . Billy

INTERVAL -10.461 - -3.476
CONTAINS 10.298%

Amy then wanted to be even more helpful . She grabbed
new . Suddenly there was an emergency . The family started
day he wanted to show his Mom how brave he was
, going high up in the air with every jump .
reminded him that quiet was an important part of being at

INTERVAL -17.445 - -10.461
CONTAINS 4.084%

, " I met a new friend named Max . He
soup . He looked at the apple piece . He took
listen . When the naughty band finished their work
poured down outside . When the cup cakes were done ,
side , they said to the small boy , " Stay
Token grandma
Token ID49890
Feature activation+2.12e+00

Pos logit contributions
 ey+0.152
 pastor+0.149
reating+0.148
Ta+0.145
 priest+0.145
Neg logit contributions
es-0.137
 could-0.130
 with-0.124
 on-0.122
 in-0.122
Token's
Token ID338
Feature activation-1.03e+01

Pos logit contributions
icked+0.031
es+0.029
ed+0.021
ched+0.021
 could+0.020
Neg logit contributions
 opera-0.048
 hotel-0.047
 city-0.047
 talent-0.047
 airport-0.046
Token house
Token ID2156
Feature activation+5.59e+00

Pos logit contributions
reating+0.140
Ta+0.138
 orchestra+0.138
 priest+0.136
 pastor+0.136
Neg logit contributions
es-0.192
 could-0.177
 in-0.177
 with-0.176
 on-0.174
Token for
Token ID329
Feature activation-5.03e-01

Pos logit contributions
es+0.070
icked+0.064
 could+0.045
owed+0.044
iled+0.042
Neg logit contributions
 hotel-0.138
 talent-0.137
 city-0.137
 opera-0.136
 airport-0.132
Token safe
Token ID3338
Feature activation+8.69e-01

Pos logit contributions
 hotel+0.011
 city+0.011
 talent+0.011
 opera+0.011
 orchestra+0.011
Neg logit contributions
es-0.008
icked-0.007
 could-0.006
owed-0.005
iled-0.005
Tokenkeeping
Token ID19934
Feature activation+1.05e+01

Pos logit contributions
es+0.014
icked+0.013
 could+0.010
owed+0.010
iled+0.009
Neg logit contributions
 hotel-0.019
 talent-0.019
 city-0.019
 opera-0.018
 airport-0.018
Token.
Token ID13
Feature activation+4.39e+00

Pos logit contributions
es+0.140
icked+0.134
 could+0.096
iled+0.092
owed+0.091
Neg logit contributions
 hotel-0.240
 talent-0.239
 city-0.238
 opera-0.236
 airport-0.230
Token
Token ID220
Feature activation+2.29e-01

Pos logit contributions
es+0.067
icked+0.061
owed+0.045
 could+0.042
iled+0.042
Neg logit contributions
 city-0.099
 hotel-0.098
 talent-0.097
 former-0.095
 opera-0.094
Token
Token ID198
Feature activation+4.48e-01

Pos logit contributions
es+0.004
icked+0.003
owed+0.003
 could+0.003
iled+0.003
Neg logit contributions
 city-0.004
 talent-0.004
 former-0.004
 hotel-0.004
 classroom-0.004
Token
Token ID198
Feature activation+9.05e-01

Pos logit contributions
es+0.007
icked+0.007
owed+0.005
ed+0.005
 could+0.005
Neg logit contributions
 city-0.009
 talent-0.009
 hotel-0.009
 playground-0.009
 museum-0.009
TokenWhen
Token ID2215
Feature activation+1.94e+00

Pos logit contributions
es+0.015
icked+0.014
 could+0.011
owed+0.011
ed+0.011
Neg logit contributions
 talent-0.018
 hotel-0.018
 city-0.018
 opera-0.018
 orchestra-0.018
Token it
Token ID340
Feature activation+5.87e-01

Pos logit contributions
es+0.006
icked+0.005
 could+0.004
ed+0.003
owed+0.003
Neg logit contributions
 hotel-0.014
 talent-0.014
 city-0.014
 former-0.014
 orchestra-0.014
Token to
Token ID284
Feature activation+2.01e-01

Pos logit contributions
es+0.006
icked+0.006
 could+0.004
ed+0.004
owed+0.003
Neg logit contributions
 hotel-0.016
 city-0.016
 orchestra-0.016
 former-0.015
 airport-0.015
Token me
Token ID502
Feature activation+1.59e+00

Pos logit contributions
es+0.003
icked+0.003
 could+0.002
 they+0.002
 on+0.002
Neg logit contributions
 talent-0.004
 hotel-0.004
 city-0.004
 former-0.004
 orchestra-0.004
Token for
Token ID329
Feature activation-9.88e-01

Pos logit contributions
es+0.020
icked+0.019
 could+0.014
owed+0.013
iled+0.013
Neg logit contributions
 talent-0.038
 hotel-0.038
 opera-0.038
 city-0.037
 orchestra-0.036
Token safe
Token ID3338
Feature activation-4.89e-01

Pos logit contributions
 hotel+0.021
 city+0.021
 orchestra+0.020
 airport+0.020
 opera+0.020
Neg logit contributions
es-0.016
icked-0.014
 could-0.012
 they-0.011
 on-0.011
Tokenkeeping
Token ID19934
Feature activation+9.82e+00

Pos logit contributions
 talent+0.010
 hotel+0.010
 city+0.010
 opera+0.010
 orchestra+0.010
Neg logit contributions
es-0.008
icked-0.008
 could-0.006
owed-0.006
ed-0.006
Token.
Token ID13
Feature activation+3.21e+00

Pos logit contributions
es+0.129
icked+0.122
 could+0.090
owed+0.085
iled+0.083
Neg logit contributions
 talent-0.228
 hotel-0.228
 opera-0.226
 city-0.225
 orchestra-0.218
Token He
Token ID679
Feature activation+2.02e+00

Pos logit contributions
es+0.046
icked+0.042
owed+0.034
bed+0.030
ed+0.030
Neg logit contributions
 city-0.072
 talent-0.071
 hotel-0.071
 opera-0.070
 museum-0.070
Token told
Token ID1297
Feature activation+1.67e+00

Pos logit contributions
es+0.029
icked+0.026
 could+0.021
owed+0.019
iled+0.018
Neg logit contributions
 hotel-0.046
 talent-0.046
 city-0.046
 opera-0.046
 orchestra-0.045
Token me
Token ID502
Feature activation+2.23e+00

Pos logit contributions
es+0.024
icked+0.021
 could+0.017
 they+0.016
owed+0.015
Neg logit contributions
 talent-0.038
 city-0.038
 former-0.038
 hotel-0.037
 orchestra-0.037
Token to
Token ID284
Feature activation-6.39e-01

Pos logit contributions
es+0.029
icked+0.027
 could+0.019
owed+0.019
iled+0.019
Neg logit contributions
 talent-0.053
 hotel-0.053
 opera-0.052
 city-0.052
 airport-0.051
Token!
Token ID0
Feature activation+2.18e+00

Pos logit contributions
icked+0.048
es+0.047
owed+0.034
 could+0.032
bed+0.032
Neg logit contributions
 talent-0.077
 opera-0.077
 hotel-0.077
 city-0.077
 zoo-0.074
Token That
Token ID1320
Feature activation-3.15e+00

Pos logit contributions
es+0.035
icked+0.032
owed+0.026
led+0.025
bed+0.024
Neg logit contributions
 talent-0.044
 city-0.044
 opera-0.043
 hotel-0.043
 orchestra-0.043
Token's
Token ID338
Feature activation-3.06e+00

Pos logit contributions
 hotel+0.071
 talent+0.071
 city+0.070
 opera+0.070
 former+0.070
Neg logit contributions
es-0.046
icked-0.039
 could-0.034
ed-0.029
owed-0.029
Token how
Token ID703
Feature activation-1.03e-01

Pos logit contributions
 hotel+0.064
 talent+0.064
 city+0.063
 opera+0.062
 orchestra+0.061
Neg logit contributions
es-0.050
icked-0.046
 could-0.038
owed-0.036
iled-0.035
Token all
Token ID477
Feature activation-1.73e+00

Pos logit contributions
 talent+0.002
 hotel+0.002
 city+0.002
 opera+0.002
 orchestra+0.002
Neg logit contributions
es-0.002
icked-0.001
owed-0.001
 could-0.001
iled-0.001
Token masks
Token ID20680
Feature activation+9.72e+00

Pos logit contributions
 hotel+0.038
 talent+0.038
 city+0.038
 opera+0.037
 former+0.037
Neg logit contributions
es-0.026
icked-0.023
 could-0.019
owed-0.018
iled-0.017
Token should
Token ID815
Feature activation-7.89e-01

Pos logit contributions
es+0.174
icked+0.167
owed+0.133
iled+0.131
bed+0.128
Neg logit contributions
 talent-0.185
 city-0.183
 hotel-0.182
 opera-0.182
 airport-0.174
Token be
Token ID307
Feature activation-2.01e+00

Pos logit contributions
 hotel+0.015
 city+0.015
 opera+0.015
 orchestra+0.015
 talent+0.015
Neg logit contributions
es-0.013
icked-0.012
 could-0.011
 they-0.010
owed-0.010
Token organized
Token ID8389
Feature activation+3.56e+00

Pos logit contributions
 talent+0.033
 hotel+0.033
 city+0.032
 opera+0.032
 orchestra+0.031
Neg logit contributions
es-0.042
icked-0.040
 could-0.034
owed-0.033
iled-0.032
Token."
Token ID526
Feature activation+3.42e+00

Pos logit contributions
es+0.047
icked+0.046
owed+0.033
 could+0.032
iled+0.031
Neg logit contributions
 talent-0.084
 hotel-0.083
 opera-0.083
 city-0.083
 former-0.080
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
es+0.049
icked+0.048
owed+0.036
 could+0.033
iled+0.033
Neg logit contributions
 city-0.077
 talent-0.077
 hotel-0.075
 opera-0.074
 museum-0.073
Token on
Token ID319
Feature activation+6.03e-01

Pos logit contributions
es+0.004
icked+0.004
owed+0.003
 could+0.003
iled+0.003
Neg logit contributions
 talent-0.008
 hotel-0.008
 opera-0.008
 city-0.008
 mirror-0.008
Token her
Token ID607
Feature activation-7.16e+00

Pos logit contributions
es+0.007
icked+0.006
 on+0.005
 could+0.005
bed+0.005
Neg logit contributions
 hotel-0.015
 city-0.015
 orchestra-0.015
 talent-0.015
 former-0.015
Token favorite
Token ID4004
Feature activation-6.52e+00

Pos logit contributions
 city+0.091
 hotel+0.089
 opera+0.087
 talent+0.086
 orchestra+0.086
Neg logit contributions
es-0.172
icked-0.161
 could-0.149
 on-0.139
owed-0.139
Token p
Token ID279
Feature activation-3.50e+00

Pos logit contributions
 former+0.080
 city+0.080
 hotel+0.077
 talent+0.075
 orchestra+0.074
Neg logit contributions
es-0.160
icked-0.147
 could-0.136
 on-0.130
bed-0.129
Tokenaj
Token ID1228
Feature activation+7.19e-01

Pos logit contributions
 opera+0.059
 city+0.059
 hotel+0.058
 talent+0.058
 orchestra+0.058
Neg logit contributions
es-0.072
icked-0.068
owed-0.058
 could-0.057
iled-0.056
Tokenamas
Token ID17485
Feature activation+9.45e+00

Pos logit contributions
es+0.013
icked+0.013
 could+0.010
owed+0.010
ched+0.010
Neg logit contributions
 talent-0.013
 hotel-0.013
 city-0.013
 opera-0.013
 former-0.013
Token and
Token ID290
Feature activation+1.36e+00

Pos logit contributions
es+0.134
icked+0.125
 could+0.088
owed+0.087
iled+0.087
Neg logit contributions
 hotel-0.213
 opera-0.212
 city-0.211
 talent-0.210
 airport-0.208
Token sn
Token ID3013
Feature activation+7.30e-02

Pos logit contributions
es+0.022
icked+0.020
iled+0.016
owed+0.016
 could+0.015
Neg logit contributions
 hotel-0.029
 talent-0.028
 opera-0.028
 city-0.028
 airport-0.027
Tokenugg
Token ID6837
Feature activation+9.61e-01

Pos logit contributions
es+0.002
icked+0.001
 could+0.001
owed+0.001
iled+0.001
Neg logit contributions
 talent-0.001
 hotel-0.001
 opera-0.001
 city-0.001
 former-0.001
Tokenled
Token ID992
Feature activation+2.65e+00

Pos logit contributions
es+0.010
icked+0.009
iled+0.006
 could+0.006
owed+0.005
Neg logit contributions
 hotel-0.025
 talent-0.025
 opera-0.025
 mirror-0.024
 airport-0.024
Token up
Token ID510
Feature activation+1.29e+00

Pos logit contributions
es+0.039
icked+0.036
 could+0.027
iled+0.026
owed+0.026
Neg logit contributions
 talent-0.060
 opera-0.060
 hotel-0.060
 city-0.058
 former-0.057
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
es+0.052
icked+0.051
iled+0.039
owed+0.038
hot+0.038
Neg logit contributions
 talent-0.075
 hotel-0.074
 opera-0.073
 city-0.072
 memory-0.070
Token the
Token ID262
Feature activation-8.74e+00

Pos logit contributions
 hotel+0.029
 talent+0.029
 city+0.028
 opera+0.028
 orchestra+0.028
Neg logit contributions
es-0.027
icked-0.025
 could-0.021
owed-0.020
 they-0.019
Token direction
Token ID4571
Feature activation+4.84e+00

Pos logit contributions
 orchestra+0.096
 talent+0.093
 tant+0.092
 former+0.089
 hotel+0.084
Neg logit contributions
es-0.188
 on-0.179
 could-0.174
 in-0.174
 there-0.169
Token of
Token ID286
Feature activation-2.92e+00

Pos logit contributions
es+0.064
icked+0.061
owed+0.042
 could+0.040
iled+0.040
Neg logit contributions
 hotel-0.115
 talent-0.115
 city-0.115
 opera-0.114
 orchestra-0.111
Token the
Token ID262
Feature activation-1.10e+01

Pos logit contributions
 hotel+0.064
 talent+0.063
 former+0.062
 city+0.062
 orchestra+0.061
Neg logit contributions
es-0.042
icked-0.036
 could-0.031
 on-0.030
 there-0.030
Token leash
Token ID40529
Feature activation+9.38e+00

Pos logit contributions
 former+0.125
 talent+0.123
 orchestra+0.119
 hotel+0.116
 opera+0.113
Neg logit contributions
es-0.236
 on-0.222
 could-0.216
 in-0.211
 there-0.206
Token.
Token ID13
Feature activation+4.16e+00

Pos logit contributions
es+0.126
icked+0.122
iled+0.086
owed+0.085
ched+0.077
Neg logit contributions
 city-0.214
 hotel-0.213
 opera-0.211
 airport-0.210
 talent-0.208
Token
Token ID220
Feature activation+2.60e-01

Pos logit contributions
es+0.063
icked+0.059
owed+0.046
ched+0.042
ed+0.041
Neg logit contributions
 city-0.093
 hotel-0.090
 talent-0.089
 zoo-0.088
 opera-0.088
Token
Token ID198
Feature activation+7.00e-01

Pos logit contributions
es+0.004
icked+0.004
owed+0.003
bed+0.003
iled+0.003
Neg logit contributions
 city-0.005
 hotel-0.005
 talent-0.005
 classroom-0.005
 opera-0.005
Token
Token ID198
Feature activation+9.57e-01

Pos logit contributions
es+0.009
icked+0.008
 could+0.006
owed+0.006
ed+0.006
Neg logit contributions
 talent-0.017
 hotel-0.017
 city-0.017
 opera-0.017
 orchestra-0.016
TokenLittle
Token ID22253
Feature activation-1.59e+00

Pos logit contributions
es+0.016
icked+0.015
 could+0.012
owed+0.011
iled+0.011
Neg logit contributions
 hotel-0.020
 talent-0.020
 city-0.019
 opera-0.019
 orchestra-0.019
Token see
Token ID766
Feature activation+2.34e+00

Pos logit contributions
es+0.001
icked+0.001
 could+0.001
 they+0.001
 on+0.001
Neg logit contributions
 hotel-0.004
 talent-0.003
 airport-0.003
 former-0.003
 opera-0.003
Token that
Token ID326
Feature activation-6.60e-01

Pos logit contributions
es+0.031
icked+0.027
 could+0.021
owed+0.019
iled+0.018
Neg logit contributions
 talent-0.057
 hotel-0.057
 city-0.056
 opera-0.056
 orchestra-0.055
Token his
Token ID465
Feature activation-7.53e+00

Pos logit contributions
 talent+0.017
 hotel+0.016
 city+0.016
 opera+0.016
 former+0.016
Neg logit contributions
es-0.008
icked-0.006
 could-0.006
 on-0.005
 they-0.005
Token favorite
Token ID4004
Feature activation-5.02e+00

Pos logit contributions
 orchestra+0.118
 talent+0.114
 opera+0.114
 hotel+0.112
 city+0.112
Neg logit contributions
es-0.144
icked-0.131
 could-0.126
 on-0.122
 in-0.121
Token red
Token ID2266
Feature activation-5.67e+00

Pos logit contributions
 former+0.068
 talent+0.065
 airport+0.065
 orchestra+0.064
 hotel+0.063
Neg logit contributions
es-0.115
icked-0.099
 could-0.098
 on-0.094
 in-0.090
Token sweater
Token ID35685
Feature activation+9.35e+00

Pos logit contributions
 talent+0.082
 hotel+0.081
 opera+0.079
 orchestra+0.079
 city+0.078
Neg logit contributions
es-0.128
icked-0.118
 could-0.107
bed-0.103
owed-0.102
Token had
Token ID550
Feature activation+1.58e+00

Pos logit contributions
icked+0.140
es+0.136
iled+0.112
 Remy+0.109
owed+0.101
Neg logit contributions
 hotel-0.180
 city-0.177
 playground-0.176
 bus-0.175
 opera-0.174
Token a
Token ID257
Feature activation-6.07e+00

Pos logit contributions
es+0.027
icked+0.025
 could+0.021
ed+0.019
owed+0.019
Neg logit contributions
 talent-0.033
 hotel-0.033
 city-0.032
 opera-0.032
 orchestra-0.032
Token big
Token ID1263
Feature activation-7.06e+00

Pos logit contributions
 opera+0.085
 hotel+0.084
 city+0.082
 talent+0.081
 airport+0.079
Neg logit contributions
es-0.131
 could-0.120
icked-0.119
 on-0.114
 there-0.106
Token hole
Token ID7604
Feature activation+6.92e+00

Pos logit contributions
 talent+0.112
 hotel+0.111
 opera+0.110
 city+0.108
 former+0.106
Neg logit contributions
es-0.144
icked-0.133
 could-0.121
 on-0.114
bed-0.113
Token in
Token ID287
Feature activation-1.05e+00

Pos logit contributions
es+0.087
icked+0.077
 Remy+0.056
owed+0.055
 could+0.053
Neg logit contributions
 hotel-0.160
 opera-0.158
 city-0.157
 talent-0.156
 airport-0.155
Token proceeded
Token ID18814
Feature activation+4.54e+00

Pos logit contributions
es+0.029
icked+0.028
owed+0.021
iled+0.020
 could+0.020
Neg logit contributions
 hotel-0.048
 talent-0.048
 opera-0.048
 city-0.048
 airport-0.047
Token to
Token ID284
Feature activation-7.20e-01

Pos logit contributions
es+0.061
icked+0.055
 could+0.041
owed+0.040
iled+0.039
Neg logit contributions
 talent-0.108
 hotel-0.106
 opera-0.106
 city-0.106
 airport-0.104
Token guess
Token ID4724
Feature activation+2.86e+00

Pos logit contributions
 hotel+0.013
 talent+0.013
 city+0.013
 orchestra+0.013
 tant+0.012
Neg logit contributions
es-0.013
icked-0.011
 could-0.010
 on-0.010
owed-0.009
Token what
Token ID644
Feature activation-1.33e-01

Pos logit contributions
es+0.040
icked+0.037
 could+0.028
owed+0.027
iled+0.027
Neg logit contributions
 talent-0.065
 opera-0.065
 hotel-0.065
 city-0.065
 orchestra-0.063
Token the
Token ID262
Feature activation-1.09e+01

Pos logit contributions
 talent+0.003
 city+0.003
 opera+0.003
 hotel+0.003
 airport+0.003
Neg logit contributions
es-0.002
icked-0.002
owed-0.001
iled-0.001
 could-0.001
Token shield
Token ID7614
Feature activation+9.34e+00

Pos logit contributions
 hotel+0.140
 apartment+0.139
 former+0.132
 tant+0.130
 orchestra+0.128
Neg logit contributions
es-0.237
 could-0.220
 on-0.212
 there-0.201
icked-0.200
Token was
Token ID373
Feature activation-9.08e-01

Pos logit contributions
es+0.133
icked+0.127
iled+0.094
owed+0.092
bed+0.086
Neg logit contributions
 hotel-0.206
 talent-0.206
 city-0.205
 opera-0.204
 airport-0.199
Token for
Token ID329
Feature activation+1.63e+00

Pos logit contributions
 talent+0.021
 opera+0.021
 hotel+0.021
 city+0.021
 airport+0.020
Neg logit contributions
es-0.013
icked-0.012
owed-0.008
 could-0.008
iled-0.008
Token.
Token ID13
Feature activation+3.45e+00

Pos logit contributions
icked+0.023
es+0.022
ched+0.017
 could+0.016
owed+0.016
Neg logit contributions
 talent-0.037
 opera-0.036
 city-0.035
 hotel-0.034
 museum-0.034
Token Was
Token ID8920
Feature activation-3.34e-01

Pos logit contributions
es+0.051
icked+0.046
owed+0.037
led+0.035
iled+0.035
Neg logit contributions
 city-0.077
 zoo-0.075
 hotel-0.074
 talent-0.074
 playground-0.073
Token it
Token ID340
Feature activation-1.07e+00

Pos logit contributions
 talent+0.008
 hotel+0.008
 opera+0.008
 city+0.008
 airport+0.008
Neg logit contributions
es-0.004
icked-0.004
owed-0.003
iled-0.003
 could-0.003
Token and
Token ID290
Feature activation+6.77e-01

Pos logit contributions
icked+0.046
es+0.046
owed+0.034
 could+0.032
iled+0.032
Neg logit contributions
 talent-0.065
 hotel-0.063
 city-0.063
 opera-0.062
 mistake-0.062
Token R
Token ID371
Feature activation-5.85e+00

Pos logit contributions
es+0.010
icked+0.009
owed+0.007
iled+0.007
 could+0.007
Neg logit contributions
 hotel-0.015
 city-0.015
 talent-0.015
 opera-0.015
 airport-0.014
Tokenuf
Token ID3046
Feature activation-6.59e-01

Pos logit contributions
 hotel+0.084
 talent+0.083
 city+0.082
 opera+0.080
 former+0.078
Neg logit contributions
es-0.132
icked-0.126
 could-0.110
owed-0.105
iled-0.102
Tokenus
Token ID385
Feature activation+2.82e+00

Pos logit contributions
 hotel+0.012
 city+0.011
 museum+0.011
 airport+0.011
 zoo+0.011
Neg logit contributions
icked-0.012
es-0.011
bed-0.009
owed-0.009
 could-0.009
Token'
Token ID6
Feature activation-3.84e+00

Pos logit contributions
es+0.034
icked+0.033
owed+0.023
hot+0.023
 could+0.023
Neg logit contributions
 talent-0.064
 hotel-0.063
 city-0.062
 former-0.062
 opera-0.061
Token itch
Token ID49700
Feature activation+9.23e+00

Pos logit contributions
 hotel+0.060
 city+0.059
 talent+0.059
 opera+0.058
 orchestra+0.058
Neg logit contributions
es-0.085
icked-0.079
 could-0.069
owed-0.065
iled-0.065
Token was
Token ID373
Feature activation-1.34e+00

Pos logit contributions
es+0.131
icked+0.127
owed+0.097
iled+0.096
 Remy+0.091
Neg logit contributions
 hotel-0.188
 opera-0.185
 city-0.184
 talent-0.183
 airport-0.181
Token gone
Token ID3750
Feature activation+1.89e+00

Pos logit contributions
 talent+0.024
 hotel+0.023
 opera+0.023
 city+0.023
 former+0.023
Neg logit contributions
es-0.026
icked-0.023
owed-0.019
 could-0.019
iled-0.019
Token!
Token ID0
Feature activation+2.74e+00

Pos logit contributions
es+0.027
icked+0.027
owed+0.019
 could+0.018
iled+0.018
Neg logit contributions
 hotel-0.042
 city-0.042
 talent-0.041
 former-0.041
 opera-0.041
Token
Token ID198
Feature activation-7.39e-01

Pos logit contributions
es+0.043
icked+0.040
owed+0.035
led+0.032
bed+0.031
Neg logit contributions
 hotel-0.056
 city-0.056
 zoo-0.055
 talent-0.053
 museum-0.053
Token
Token ID198
Feature activation-3.17e-01

Pos logit contributions
 hotel+0.015
 talent+0.015
 city+0.015
 zoo+0.015
 opera+0.015
Neg logit contributions
es-0.011
icked-0.011
owed-0.009
ed-0.008
iled-0.008
Token,
Token ID11
Feature activation+2.84e+00

Pos logit contributions
icked+0.043
es+0.042
owed+0.033
iled+0.032
ched+0.031
Neg logit contributions
 opera-0.066
 city-0.065
 hotel-0.065
 mirror-0.065
 talent-0.064
Token she
Token ID673
Feature activation+2.36e+00

Pos logit contributions
es+0.034
icked+0.032
owed+0.022
iled+0.021
 could+0.021
Neg logit contributions
 opera-0.070
 talent-0.070
 hotel-0.070
 city-0.070
 airport-0.068
Token figured
Token ID11638
Feature activation+2.71e+00

Pos logit contributions
es+0.039
icked+0.036
owed+0.028
iled+0.027
hot+0.026
Neg logit contributions
 talent-0.047
 hotel-0.047
 city-0.047
 airport-0.046
 opera-0.046
Token out
Token ID503
Feature activation+2.17e+00

Pos logit contributions
es+0.038
icked+0.033
iled+0.026
owed+0.026
 could+0.026
Neg logit contributions
 talent-0.061
 opera-0.060
 hotel-0.060
 city-0.059
 airport-0.058
Token which
Token ID543
Feature activation-1.71e+00

Pos logit contributions
es+0.031
icked+0.028
 could+0.021
owed+0.020
iled+0.019
Neg logit contributions
 talent-0.050
 hotel-0.050
 city-0.050
 opera-0.050
 orchestra-0.048
Token mattress
Token ID33388
Feature activation+9.20e+00

Pos logit contributions
 talent+0.032
 hotel+0.032
 city+0.032
 opera+0.032
 orchestra+0.031
Neg logit contributions
es-0.032
icked-0.029
 could-0.024
owed-0.024
iled-0.023
Token to
Token ID284
Feature activation-1.65e+00

Pos logit contributions
icked+0.127
es+0.126
iled+0.099
 Remy+0.090
owed+0.088
Neg logit contributions
 hotel-0.194
 opera-0.191
 city-0.189
 airport-0.188
 talent-0.187
Token pick
Token ID2298
Feature activation+3.70e+00

Pos logit contributions
 talent+0.032
 hotel+0.032
 city+0.032
 opera+0.031
 orchestra+0.031
Neg logit contributions
es-0.029
icked-0.027
 could-0.023
owed-0.022
bed-0.020
Token.
Token ID13
Feature activation+4.40e+00

Pos logit contributions
es+0.054
icked+0.051
 could+0.038
owed+0.038
iled+0.037
Neg logit contributions
 hotel-0.083
 talent-0.082
 opera-0.082
 city-0.082
 airport-0.079
Token It
Token ID632
Feature activation+1.98e+00

Pos logit contributions
es+0.067
icked+0.063
owed+0.049
led+0.047
iled+0.045
Neg logit contributions
 city-0.096
 talent-0.093
 hotel-0.092
 classroom-0.092
 former-0.092
Token was
Token ID373
Feature activation-1.69e+00

Pos logit contributions
es+0.030
icked+0.028
iled+0.021
owed+0.021
hot+0.020
Neg logit contributions
 hotel-0.043
 talent-0.041
 city-0.041
 opera-0.041
 former-0.040
Token on
Token ID319
Feature activation-3.69e-01

Pos logit contributions
es+0.060
icked+0.058
owed+0.040
 could+0.040
iled+0.037
Neg logit contributions
 hotel-0.108
 city-0.107
 talent-0.107
 opera-0.106
 airport-0.104
Token a
Token ID257
Feature activation-7.26e+00

Pos logit contributions
 talent+0.009
 hotel+0.009
 opera+0.009
 city+0.009
 orchestra+0.009
Neg logit contributions
es-0.005
icked-0.004
 could-0.003
owed-0.003
iled-0.003
Token leash
Token ID40529
Feature activation+7.40e+00

Pos logit contributions
 former+0.109
 ey+0.106
 talent+0.102
 humor+0.101
 pride+0.100
Neg logit contributions
es-0.125
 could-0.120
 they-0.117
 on-0.117
,-0.115
Token.
Token ID13
Feature activation+3.98e+00

Pos logit contributions
es+0.102
icked+0.096
iled+0.068
owed+0.067
 could+0.065
Neg logit contributions
 hotel-0.169
 city-0.169
 opera-0.168
 talent-0.167
 airport-0.166
Token The
Token ID383
Feature activation-1.05e+01

Pos logit contributions
es+0.061
icked+0.057
owed+0.046
led+0.042
ched+0.041
Neg logit contributions
 city-0.087
 hotel-0.085
 zoo-0.084
 classroom-0.083
 museum-0.083
Token leash
Token ID40529
Feature activation+9.11e+00

Pos logit contributions
 talent+0.155
 former+0.154
 hotel+0.150
 orchestra+0.147
 opera+0.145
Neg logit contributions
es-0.199
 could-0.185
 on-0.182
icked-0.173
 there-0.170
Token was
Token ID373
Feature activation-1.64e+00

Pos logit contributions
es+0.130
icked+0.122
owed+0.090
iled+0.089
 could+0.080
Neg logit contributions
 hotel-0.203
 city-0.200
 opera-0.198
 talent-0.197
 airport-0.196
Token a
Token ID257
Feature activation-5.53e+00

Pos logit contributions
 talent+0.028
 hotel+0.027
 opera+0.027
 city+0.027
 orchestra+0.026
Neg logit contributions
es-0.034
icked-0.031
owed-0.026
 could-0.026
iled-0.025
Token long
Token ID890
Feature activation-4.48e+00

Pos logit contributions
 former+0.091
 opera+0.091
 ey+0.089
 orchestra+0.089
 city+0.087
Neg logit contributions
 could-0.092
 on-0.088
 they-0.084
es-0.083
 there-0.082
Token,
Token ID11
Feature activation-6.62e-02

Pos logit contributions
 talent+0.090
 hotel+0.090
 city+0.089
 opera+0.089
 orchestra+0.087
Neg logit contributions
es-0.076
icked-0.070
 could-0.057
owed-0.055
iled-0.054
Token red
Token ID2266
Feature activation-4.40e+00

Pos logit contributions
 hotel+0.001
 talent+0.001
 city+0.001
 opera+0.001
 orchestra+0.001
Neg logit contributions
es-0.001
icked-0.001
 could-0.001
owed-0.001
iled-0.001
Token him
Token ID683
Feature activation+2.40e+00

Pos logit contributions
 former+0.006
 hotel+0.006
 talent+0.006
 city+0.006
 orchestra+0.006
Neg logit contributions
es-0.003
icked-0.003
 could-0.002
 they-0.002
 there-0.002
Token.
Token ID13
Feature activation+3.06e+00

Pos logit contributions
es+0.034
icked+0.034
iled+0.024
owed+0.024
ched+0.023
Neg logit contributions
 talent-0.048
 opera-0.048
 city-0.047
 hotel-0.047
 mistake-0.047
Token Suddenly
Token ID24975
Feature activation+1.81e+00

Pos logit contributions
es+0.049
icked+0.045
owed+0.037
led+0.035
ched+0.034
Neg logit contributions
 city-0.065
 zoo-0.063
 classroom-0.063
 museum-0.063
 hotel-0.062
Token,
Token ID11
Feature activation+1.45e+00

Pos logit contributions
es+0.021
icked+0.021
owed+0.016
iled+0.014
 could+0.014
Neg logit contributions
 hotel-0.045
 city-0.044
 opera-0.043
 talent-0.043
 airport-0.043
Token the
Token ID262
Feature activation-1.07e+01

Pos logit contributions
es+0.015
icked+0.014
 could+0.009
owed+0.009
iled+0.008
Neg logit contributions
 hotel-0.039
 talent-0.039
 city-0.038
 opera-0.038
 orchestra-0.037
Token leash
Token ID40529
Feature activation+9.10e+00

Pos logit contributions
 former+0.149
 talent+0.146
 orchestra+0.142
 opera+0.136
 hotel+0.136
Neg logit contributions
es-0.210
 could-0.194
 on-0.193
icked-0.192
 in-0.185
Token came
Token ID1625
Feature activation+1.76e+00

Pos logit contributions
es+0.135
icked+0.126
owed+0.100
iled+0.094
 Remy+0.089
Neg logit contributions
 hotel-0.189
 city-0.188
 airport-0.185
 bus-0.184
 playground-0.183
Token off
Token ID572
Feature activation+2.59e+00

Pos logit contributions
es+0.029
icked+0.026
owed+0.021
 could+0.021
iled+0.019
Neg logit contributions
 city-0.034
 opera-0.033
 hotel-0.033
 mistake-0.032
 playground-0.032
Token the
Token ID262
Feature activation-1.02e+01

Pos logit contributions
es+0.036
icked+0.035
owed+0.026
 could+0.025
iled+0.023
Neg logit contributions
 hotel-0.060
 city-0.060
 opera-0.059
 talent-0.058
 airport-0.057
Token collar
Token ID19908
Feature activation+7.88e+00

Pos logit contributions
 talent+0.123
 tant+0.115
 former+0.114
 opera+0.109
 orchestra+0.109
Neg logit contributions
es-0.216
 on-0.206
 in-0.201
 could-0.200
 there-0.189
Token and
Token ID290
Feature activation+1.15e+00

Pos logit contributions
es+0.112
icked+0.108
owed+0.076
 could+0.075
iled+0.075
Neg logit contributions
 city-0.170
 hotel-0.169
 opera-0.169
 airport-0.167
 talent-0.166
Token dry
Token ID5894
Feature activation-1.64e+00

Pos logit contributions
es+0.016
icked+0.013
 could+0.011
 on+0.010
 they+0.010
Neg logit contributions
 talent-0.023
 hotel-0.023
 orchestra-0.023
 opera-0.022
 city-0.022
Token and
Token ID290
Feature activation-9.66e-01

Pos logit contributions
 talent+0.021
 hotel+0.021
 city+0.021
 opera+0.020
 orchestra+0.020
Neg logit contributions
es-0.040
icked-0.038
 could-0.033
owed-0.032
ed-0.032
Token cozy
Token ID37438
Feature activation-2.12e+00

Pos logit contributions
 talent+0.015
 hotel+0.015
 city+0.015
 opera+0.015
 orchestra+0.014
Neg logit contributions
es-0.021
icked-0.020
 could-0.017
owed-0.016
iled-0.016
Token p
Token ID279
Feature activation-1.32e+00

Pos logit contributions
 hotel+0.035
 talent+0.035
 city+0.034
 opera+0.034
 orchestra+0.033
Neg logit contributions
es-0.045
icked-0.042
 could-0.035
owed-0.035
iled-0.034
Tokenaj
Token ID1228
Feature activation+3.10e+00

Pos logit contributions
 talent+0.019
 city+0.019
 hotel+0.019
 opera+0.019
 orchestra+0.018
Neg logit contributions
es-0.030
icked-0.028
owed-0.024
 could-0.024
iled-0.023
Tokenamas
Token ID17485
Feature activation+9.06e+00

Pos logit contributions
icked+0.057
es+0.056
 could+0.046
iled+0.045
owed+0.043
Neg logit contributions
 hotel-0.053
 talent-0.053
 city-0.052
 former-0.052
 opera-0.052
Token and
Token ID290
Feature activation+2.97e-01

Pos logit contributions
es+0.125
icked+0.121
iled+0.084
 Remy+0.083
owed+0.082
Neg logit contributions
 hotel-0.205
 opera-0.202
 city-0.200
 airport-0.199
 talent-0.198
Token sn
Token ID3013
Feature activation+6.65e-01

Pos logit contributions
es+0.006
icked+0.005
 could+0.004
owed+0.004
iled+0.004
Neg logit contributions
 hotel-0.005
 talent-0.005
 city-0.005
 opera-0.005
 orchestra-0.005
Tokenugg
Token ID6837
Feature activation+1.03e+00

Pos logit contributions
es+0.014
icked+0.013
 could+0.011
owed+0.011
iled+0.010
Neg logit contributions
 hotel-0.011
 talent-0.010
 former-0.010
 opera-0.010
 city-0.010
Tokenled
Token ID992
Feature activation+3.00e+00

Pos logit contributions
es+0.010
icked+0.009
 could+0.006
iled+0.006
owed+0.005
Neg logit contributions
 hotel-0.028
 opera-0.028
 talent-0.028
 city-0.027
 airport-0.027
Token in
Token ID287
Feature activation-2.28e-01

Pos logit contributions
es+0.038
icked+0.034
 could+0.025
owed+0.024
iled+0.022
Neg logit contributions
 hotel-0.074
 talent-0.074
 opera-0.073
 city-0.073
 orchestra-0.071
Token.
Token ID13
Feature activation+4.33e+00

Pos logit contributions
es+0.077
icked+0.071
 could+0.052
owed+0.051
iled+0.049
Neg logit contributions
 hotel-0.133
 talent-0.133
 city-0.132
 opera-0.131
 airport-0.128
Token He
Token ID679
Feature activation+2.09e+00

Pos logit contributions
es+0.065
icked+0.061
owed+0.046
ed+0.042
 could+0.042
Neg logit contributions
 city-0.098
 hotel-0.096
 talent-0.094
 zoo-0.093
 former-0.093
Token put
Token ID1234
Feature activation+1.11e+00

Pos logit contributions
es+0.030
icked+0.027
 could+0.020
owed+0.020
iled+0.019
Neg logit contributions
 hotel-0.048
 talent-0.048
 city-0.047
 opera-0.047
 orchestra-0.046
Token up
Token ID510
Feature activation+1.81e+00

Pos logit contributions
es+0.014
icked+0.013
owed+0.010
 could+0.010
iled+0.009
Neg logit contributions
 hotel-0.027
 talent-0.026
 city-0.026
 opera-0.026
 airport-0.026
Token some
Token ID617
Feature activation-4.64e+00

Pos logit contributions
es+0.028
icked+0.025
 could+0.021
ed+0.019
owed+0.019
Neg logit contributions
 talent-0.039
 hotel-0.039
 orchestra-0.039
 city-0.039
 opera-0.039
Token bases
Token ID12536
Feature activation+9.02e+00

Pos logit contributions
 hotel+0.071
 city+0.071
 former+0.070
 talent+0.070
 opera+0.070
Neg logit contributions
es-0.101
icked-0.094
 could-0.084
 on-0.079
ed-0.079
Token and
Token ID290
Feature activation+8.60e-01

Pos logit contributions
es+0.116
icked+0.112
owed+0.082
 could+0.080
iled+0.076
Neg logit contributions
 talent-0.208
 hotel-0.207
 opera-0.206
 city-0.206
 airport-0.201
Token got
Token ID1392
Feature activation+1.25e-01

Pos logit contributions
es+0.014
icked+0.013
owed+0.010
 could+0.010
iled+0.010
Neg logit contributions
 hotel-0.018
 talent-0.018
 city-0.018
 opera-0.018
 airport-0.017
Token some
Token ID617
Feature activation-4.18e+00

Pos logit contributions
es+0.002
icked+0.002
 could+0.001
owed+0.001
iled+0.001
Neg logit contributions
 talent-0.003
 hotel-0.003
 city-0.003
 opera-0.003
 orchestra-0.003
Token balls
Token ID11333
Feature activation+6.91e+00

Pos logit contributions
 hotel+0.062
 city+0.061
 opera+0.061
 talent+0.061
 orchestra+0.059
Neg logit contributions
es-0.093
icked-0.087
 could-0.077
owed-0.073
ed-0.072
Token.
Token ID13
Feature activation+4.19e+00

Pos logit contributions
es+0.092
icked+0.085
owed+0.064
 could+0.061
iled+0.057
Neg logit contributions
 hotel-0.158
 talent-0.158
 opera-0.156
 city-0.156
 airport-0.153
Token wearing
Token ID5762
Feature activation+1.44e+00

Pos logit contributions
es+0.058
icked+0.057
 could+0.040
iled+0.038
owed+0.038
Neg logit contributions
 hotel-0.108
 talent-0.106
 opera-0.106
 city-0.105
 airport-0.104
Token his
Token ID465
Feature activation-9.17e+00

Pos logit contributions
es+0.023
icked+0.021
 could+0.017
owed+0.016
ed+0.016
Neg logit contributions
 hotel-0.030
 city-0.030
 talent-0.030
 opera-0.030
 orchestra-0.029
Token favourite
Token ID12507
Feature activation-6.84e+00

Pos logit contributions
 city+0.117
 hotel+0.115
 former+0.113
 opera+0.113
 orchestra+0.110
Neg logit contributions
es-0.210
icked-0.193
 could-0.189
 on-0.178
 there-0.169
Token py
Token ID12972
Feature activation+8.35e-01

Pos logit contributions
 former+0.085
 city+0.085
 hotel+0.082
 airport+0.079
 opera+0.078
Neg logit contributions
es-0.164
icked-0.147
 could-0.141
 on-0.137
owed-0.132
Tokenj
Token ID73
Feature activation-1.15e+00

Pos logit contributions
es+0.018
icked+0.017
 could+0.015
owed+0.014
iled+0.014
Neg logit contributions
 talent-0.013
 hotel-0.013
 city-0.013
 opera-0.013
 orchestra-0.012
Tokenamas
Token ID17485
Feature activation+9.01e+00

Pos logit contributions
 hotel+0.022
 talent+0.022
 city+0.022
 opera+0.022
 airport+0.021
Neg logit contributions
es-0.020
icked-0.019
 could-0.016
owed-0.015
iled-0.014
Token,
Token ID11
Feature activation+1.83e+00

Pos logit contributions
es+0.131
icked+0.127
owed+0.089
 Remy+0.088
iled+0.085
Neg logit contributions
 hotel-0.199
 city-0.195
 airport-0.194
 opera-0.194
 talent-0.191
Token feeling
Token ID4203
Feature activation-7.93e-01

Pos logit contributions
es+0.027
icked+0.024
 could+0.018
owed+0.018
iled+0.017
Neg logit contributions
 hotel-0.042
 talent-0.042
 city-0.041
 opera-0.041
 orchestra-0.040
Token so
Token ID523
Feature activation-2.26e+00

Pos logit contributions
 talent+0.015
 hotel+0.015
 city+0.014
 opera+0.014
 orchestra+0.014
Neg logit contributions
es-0.015
icked-0.014
 could-0.012
owed-0.011
iled-0.011
Token proud
Token ID6613
Feature activation+2.55e-01

Pos logit contributions
 hotel+0.033
 talent+0.033
 city+0.033
 opera+0.032
 orchestra+0.031
Neg logit contributions
es-0.051
icked-0.048
 could-0.041
owed-0.040
iled-0.039
Token of
Token ID286
Feature activation-1.33e-01

Pos logit contributions
es+0.004
icked+0.004
owed+0.003
 could+0.003
iled+0.003
Neg logit contributions
 talent-0.006
 hotel-0.006
 opera-0.006
 city-0.006
 orchestra-0.005
Token eat
Token ID4483
Feature activation+3.25e+00

Pos logit contributions
 hotel+0.038
 talent+0.037
 city+0.037
 opera+0.037
 orchestra+0.036
Neg logit contributions
es-0.041
icked-0.037
 could-0.032
owed-0.031
iled-0.030
Token the
Token ID262
Feature activation-1.06e+01

Pos logit contributions
es+0.050
icked+0.048
owed+0.037
 could+0.036
iled+0.035
Neg logit contributions
 hotel-0.070
 talent-0.070
 city-0.069
 opera-0.069
 former-0.066
Token y
Token ID331
Feature activation-5.53e+00

Pos logit contributions
 orchestra+0.161
 talent+0.156
 opera+0.152
 hotel+0.151
 city+0.150
Neg logit contributions
es-0.201
 on-0.181
 could-0.177
icked-0.175
 in-0.172
Tokenummy
Token ID13513
Feature activation-6.65e+00

Pos logit contributions
 hotel+0.092
 city+0.090
 talent+0.090
 opera+0.087
 former+0.085
Neg logit contributions
es-0.118
icked-0.110
 could-0.095
owed-0.091
ched-0.087
Token ins
Token ID1035
Feature activation-2.52e+00

Pos logit contributions
 talent+0.095
 hotel+0.094
 city+0.093
 opera+0.092
 orchestra+0.090
Neg logit contributions
es-0.152
icked-0.141
 could-0.124
owed-0.120
ed-0.118
Tokenides
Token ID1460
Feature activation+9.00e+00

Pos logit contributions
 talent+0.054
 hotel+0.054
 city+0.053
 opera+0.053
 orchestra+0.052
Neg logit contributions
es-0.040
icked-0.037
 could-0.030
owed-0.028
iled-0.027
Token.
Token ID13
Feature activation+3.86e+00

Pos logit contributions
icked+0.120
es+0.119
owed+0.083
iled+0.082
 could+0.078
Neg logit contributions
 hotel-0.201
 city-0.199
 talent-0.198
 opera-0.196
 airport-0.192
Token From
Token ID3574
Feature activation-2.03e-01

Pos logit contributions
es+0.060
icked+0.056
owed+0.043
ed+0.040
 could+0.040
Neg logit contributions
 city-0.085
 hotel-0.083
 former-0.082
 talent-0.082
 zoo-0.081
Token that
Token ID326
Feature activation-1.48e+00

Pos logit contributions
 talent+0.005
 opera+0.005
 city+0.005
 hotel+0.005
 airport+0.005
Neg logit contributions
es-0.003
icked-0.003
owed-0.002
 could-0.002
iled-0.002
Token day
Token ID1110
Feature activation+2.01e+00

Pos logit contributions
 talent+0.015
 hotel+0.015
 city+0.015
 opera+0.014
 airport+0.013
Neg logit contributions
es-0.041
icked-0.040
owed-0.034
 could-0.034
ed-0.033
Token on
Token ID319
Feature activation+6.89e-01

Pos logit contributions
owed+0.025
es+0.024
icked+0.024
uts+0.021
ppers+0.020
Neg logit contributions
 opera-0.040
 audience-0.040
 city-0.039
 mirror-0.038
 airport-0.038
Token
Token ID241
Feature activation+1.30e+00

Pos logit contributions
 hotel+0.088
 talent+0.087
 city+0.086
 opera+0.086
 orchestra+0.083
Neg logit contributions
es-0.085
icked-0.079
 could-0.066
owed-0.064
iled-0.063
TokenWhat
Token ID2061
Feature activation+1.44e+00

Pos logit contributions
es+0.019
icked+0.017
owed+0.013
 could+0.012
iled+0.012
Neg logit contributions
 talent-0.030
 city-0.030
 hotel-0.030
 opera-0.029
 orchestra-0.029
Token is
Token ID318
Feature activation-2.02e+00

Pos logit contributions
es+0.026
icked+0.025
bed+0.020
owed+0.020
iled+0.020
Neg logit contributions
 talent-0.027
 hotel-0.027
 opera-0.027
 city-0.027
 museum-0.026
Token the
Token ID262
Feature activation-9.98e+00

Pos logit contributions
 talent+0.044
 hotel+0.043
 opera+0.043
 city+0.043
 orchestra+0.042
Neg logit contributions
es-0.032
icked-0.030
 could-0.024
owed-0.023
iled-0.022
Token r
Token ID374
Feature activation-3.69e+00

Pos logit contributions
 former+0.111
 tant+0.110
 apartment+0.108
 hotel+0.105
 orchestra+0.103
Neg logit contributions
 on-0.208
es-0.202
 could-0.198
 there-0.194
 in-0.191
Tokeniddle
Token ID2509
Feature activation+8.97e+00

Pos logit contributions
 hotel+0.062
 talent+0.062
 city+0.061
 opera+0.060
 orchestra+0.059
Neg logit contributions
es-0.076
icked-0.071
 could-0.060
owed-0.059
iled-0.057
Token?
Token ID30
Feature activation+5.05e+00

Pos logit contributions
es+0.146
icked+0.143
bed+0.105
iled+0.104
owed+0.102
Neg logit contributions
 opera-0.188
 hotel-0.184
 city-0.184
 talent-0.183
 airport-0.180
Tokenâ
Token ID22940
Feature activation-2.47e+00

Pos logit contributions
es+0.075
icked+0.071
owed+0.054
led+0.051
bed+0.049
Neg logit contributions
 city-0.112
 hotel-0.109
 talent-0.108
 museum-0.107
 opera-0.107
Token
Token ID26391
Feature activation-2.87e-01

Pos logit contributions
 talent+0.040
 city+0.039
 opera+0.039
 hotel+0.039
 orchestra+0.038
Neg logit contributions
es-0.053
icked-0.050
 could-0.042
owed-0.040
ed-0.039
Token
Token ID198
Feature activation+1.83e-01

Pos logit contributions
 city+0.006
 classroom+0.006
 playground+0.006
 hotel+0.006
 airport+0.006
Neg logit contributions
icked-0.005
es-0.004
led-0.004
owed-0.004
ched-0.003
Token
Token ID198
Feature activation+7.90e-01

Pos logit contributions
es+0.003
icked+0.002
 could+0.002
owed+0.002
ed+0.002
Neg logit contributions
 talent-0.004
 hotel-0.004
 city-0.004
 opera-0.004
 orchestra-0.004
Token to
Token ID284
Feature activation-2.96e-01

Pos logit contributions
es+0.006
icked+0.005
 could+0.004
owed+0.004
iled+0.004
Neg logit contributions
 talent-0.013
 hotel-0.013
 city-0.012
 opera-0.012
 orchestra-0.012
Token see
Token ID766
Feature activation+2.13e+00

Pos logit contributions
 talent+0.006
 hotel+0.006
 city+0.006
 former+0.006
 opera+0.006
Neg logit contributions
es-0.005
icked-0.005
 could-0.004
owed-0.004
 they-0.004
Token what
Token ID644
Feature activation+1.34e-01

Pos logit contributions
es+0.030
icked+0.027
 could+0.021
owed+0.020
iled+0.019
Neg logit contributions
 talent-0.049
 hotel-0.049
 city-0.049
 opera-0.049
 orchestra-0.048
Token all
Token ID477
Feature activation-3.55e-01

Pos logit contributions
es+0.002
icked+0.002
owed+0.001
bed+0.001
iled+0.001
Neg logit contributions
 talent-0.003
 city-0.003
 hotel-0.003
 opera-0.003
 museum-0.003
Token the
Token ID262
Feature activation-7.31e+00

Pos logit contributions
 hotel+0.007
 talent+0.007
 city+0.007
 opera+0.007
 orchestra+0.007
Neg logit contributions
es-0.006
icked-0.005
 could-0.004
owed-0.004
iled-0.004
Token fuss
Token ID34297
Feature activation+8.89e+00

Pos logit contributions
 hotel+0.101
 orchestra+0.099
 former+0.095
 talent+0.095
 airport+0.095
Neg logit contributions
es-0.155
 could-0.137
 on-0.133
 there-0.130
 in-0.130
Token was
Token ID373
Feature activation-1.15e+00

Pos logit contributions
es+0.124
icked+0.118
iled+0.089
 Remy+0.088
owed+0.084
Neg logit contributions
 hotel-0.190
 talent-0.190
 opera-0.190
 city-0.189
 orchestra-0.183
Token about
Token ID546
Feature activation+1.13e+00

Pos logit contributions
 talent+0.028
 hotel+0.028
 city+0.028
 opera+0.028
 orchestra+0.027
Neg logit contributions
es-0.015
icked-0.014
 could-0.010
owed-0.010
iled-0.009
Token.
Token ID13
Feature activation+4.26e+00

Pos logit contributions
es+0.014
icked+0.013
 could+0.009
owed+0.009
iled+0.008
Neg logit contributions
 talent-0.028
 hotel-0.028
 city-0.028
 opera-0.028
 orchestra-0.027
Token "
Token ID366
Feature activation-1.83e-01

Pos logit contributions
es+0.064
icked+0.059
owed+0.045
ched+0.042
iled+0.041
Neg logit contributions
 city-0.095
 hotel-0.093
 talent-0.093
 opera-0.091
 museum-0.091
TokenWhat
Token ID2061
Feature activation+9.66e-01

Pos logit contributions
 hotel+0.004
 talent+0.004
 city+0.004
 opera+0.004
 airport+0.004
Neg logit contributions
es-0.003
icked-0.002
 could-0.002
iled-0.002
ched-0.002
Token put
Token ID1234
Feature activation+6.14e-01

Pos logit contributions
es+0.026
icked+0.023
 could+0.020
owed+0.017
ed+0.016
Neg logit contributions
 talent-0.044
 hotel-0.044
 city-0.044
 opera-0.044
 orchestra-0.043
Token on
Token ID319
Feature activation+5.75e-01

Pos logit contributions
es+0.006
icked+0.005
 could+0.004
owed+0.003
iled+0.003
Neg logit contributions
 hotel-0.017
 talent-0.017
 city-0.017
 opera-0.017
 orchestra-0.016
Token his
Token ID465
Feature activation-8.02e+00

Pos logit contributions
es+0.008
icked+0.006
 could+0.005
 on+0.005
ed+0.005
Neg logit contributions
 orchestra-0.014
 talent-0.014
 city-0.014
 former-0.013
 opera-0.013
Token p
Token ID279
Feature activation-4.51e+00

Pos logit contributions
 city+0.107
 orchestra+0.105
 former+0.104
 opera+0.104
 hotel+0.103
Neg logit contributions
es-0.175
icked-0.165
 could-0.158
 on-0.152
 in-0.145
Tokenaj
Token ID1228
Feature activation+2.82e-01

Pos logit contributions
 opera+0.089
 orchestra+0.086
 city+0.086
 hotel+0.085
 talent+0.085
Neg logit contributions
es-0.079
icked-0.074
owed-0.066
 could-0.060
ed-0.059
Tokenamas
Token ID17485
Feature activation+8.88e+00

Pos logit contributions
es+0.005
icked+0.005
 could+0.004
owed+0.004
iled+0.003
Neg logit contributions
 talent-0.006
 hotel-0.006
 city-0.005
 opera-0.005
 orchestra-0.005
Token and
Token ID290
Feature activation+1.30e+00

Pos logit contributions
es+0.122
icked+0.116
 could+0.083
owed+0.083
iled+0.079
Neg logit contributions
 hotel-0.203
 city-0.201
 talent-0.200
 opera-0.200
 airport-0.197
Token went
Token ID1816
Feature activation+1.94e+00

Pos logit contributions
es+0.020
icked+0.019
owed+0.014
 could+0.014
iled+0.014
Neg logit contributions
 hotel-0.028
 talent-0.028
 city-0.028
 opera-0.028
 airport-0.027
Token to
Token ID284
Feature activation-1.80e-01

Pos logit contributions
es+0.026
icked+0.023
 could+0.017
owed+0.016
ed+0.016
Neg logit contributions
 talent-0.046
 city-0.046
 hotel-0.046
 opera-0.046
 orchestra-0.045
Token bed
Token ID3996
Feature activation+3.99e+00

Pos logit contributions
 talent+0.003
 city+0.003
 tant+0.002
 hotel+0.002
 former+0.002
Neg logit contributions
es-0.004
icked-0.004
 could-0.003
 on-0.003
 they-0.003
Token.
Token ID13
Feature activation+4.02e+00

Pos logit contributions
es+0.052
icked+0.049
 could+0.036
owed+0.034
iled+0.033
Neg logit contributions
 hotel-0.097
 talent-0.096
 opera-0.095
 city-0.094
 airport-0.093
Token to
Token ID284
Feature activation-1.87e+00

Pos logit contributions
es+0.023
icked+0.021
 could+0.016
owed+0.016
iled+0.015
Neg logit contributions
 hotel-0.035
 city-0.035
 talent-0.035
 opera-0.035
 airport-0.034
Token measure
Token ID3953
Feature activation+3.01e+00

Pos logit contributions
 talent+0.036
 opera+0.035
 hotel+0.035
 orchestra+0.034
 former+0.034
Neg logit contributions
es-0.031
icked-0.027
 could-0.027
owed-0.023
 on-0.023
Token how
Token ID703
Feature activation-2.03e+00

Pos logit contributions
es+0.051
icked+0.047
 could+0.038
owed+0.037
iled+0.036
Neg logit contributions
 talent-0.061
 hotel-0.061
 city-0.061
 opera-0.060
 orchestra-0.059
Token big
Token ID1263
Feature activation+2.96e-01

Pos logit contributions
 hotel+0.033
 talent+0.033
 opera+0.032
 city+0.032
 orchestra+0.032
Neg logit contributions
es-0.042
icked-0.040
 could-0.035
owed-0.033
ed-0.032
Token the
Token ID262
Feature activation-1.26e+01

Pos logit contributions
icked+0.005
es+0.005
owed+0.004
iled+0.004
ched+0.004
Neg logit contributions
 city-0.006
 opera-0.006
 hotel-0.006
 airport-0.006
 talent-0.006
Token maze
Token ID31237
Feature activation+8.88e+00

Pos logit contributions
 talent+0.158
 priest+0.156
 hotel+0.156
 opera+0.155
 former+0.153
Neg logit contributions
es-0.299
 could-0.271
icked-0.266
 on-0.247
 there-0.242
Token was
Token ID373
Feature activation-9.76e-02

Pos logit contributions
icked+0.129
es+0.127
iled+0.099
 Remy+0.091
owed+0.090
Neg logit contributions
 city-0.195
 opera-0.192
 hotel-0.192
 airport-0.188
 talent-0.185
Token so
Token ID523
Feature activation-2.84e+00

Pos logit contributions
 talent+0.002
 city+0.002
 opera+0.002
 hotel+0.002
 museum+0.002
Neg logit contributions
es-0.001
icked-0.001
owed-0.001
iled-0.001
bed-0.001
Token she
Token ID673
Feature activation+1.30e+00

Pos logit contributions
 talent+0.036
 hotel+0.036
 city+0.035
 opera+0.035
 orchestra+0.033
Neg logit contributions
es-0.071
icked-0.067
 could-0.059
owed-0.057
iled-0.056
Token knew
Token ID2993
Feature activation+2.30e+00

Pos logit contributions
es+0.015
icked+0.013
owed+0.010
iled+0.010
hot+0.009
Neg logit contributions
 talent-0.031
 hotel-0.031
 opera-0.030
 city-0.030
 airport-0.030
Token exactly
Token ID3446
Feature activation-1.12e+00

Pos logit contributions
es+0.030
icked+0.028
iled+0.022
owed+0.021
ched+0.020
Neg logit contributions
 opera-0.054
 talent-0.054
 hotel-0.053
 city-0.053
 airport-0.052
Token I
Token ID314
Feature activation+1.21e+00

Pos logit contributions
es+0.019
icked+0.018
 could+0.014
owed+0.014
iled+0.013
Neg logit contributions
 talent-0.022
 hotel-0.022
 city-0.021
 opera-0.021
 orchestra-0.021
Token folded
Token ID24650
Feature activation+1.65e+00

Pos logit contributions
es+0.022
icked+0.020
owed+0.016
iled+0.016
 could+0.016
Neg logit contributions
 talent-0.023
 hotel-0.023
 opera-0.022
 city-0.022
 former-0.022
Token up
Token ID510
Feature activation+1.37e+00

Pos logit contributions
es+0.023
icked+0.021
 could+0.016
owed+0.015
iled+0.015
Neg logit contributions
 hotel-0.038
 talent-0.038
 city-0.038
 opera-0.038
 orchestra-0.037
Token those
Token ID883
Feature activation-5.06e+00

Pos logit contributions
es+0.020
icked+0.017
 could+0.014
owed+0.013
ed+0.012
Neg logit contributions
 hotel-0.031
 talent-0.031
 city-0.031
 opera-0.030
 orchestra-0.030
Token paper
Token ID3348
Feature activation+3.36e+00

Pos logit contributions
 hotel+0.079
 talent+0.079
 city+0.078
 former+0.077
 orchestra+0.076
Neg logit contributions
es-0.109
icked-0.097
 could-0.089
 on-0.083
owed-0.082
Token towels
Token ID38494
Feature activation+8.86e+00

Pos logit contributions
es+0.045
icked+0.042
 could+0.031
owed+0.030
iled+0.029
Neg logit contributions
 talent-0.079
 hotel-0.079
 city-0.078
 opera-0.078
 airport-0.076
Token for
Token ID329
Feature activation-2.76e-01

Pos logit contributions
es+0.126
icked+0.120
owed+0.087
iled+0.085
 Remy+0.080
Neg logit contributions
 hotel-0.199
 talent-0.196
 city-0.195
 opera-0.195
 airport-0.192
Token our
Token ID674
Feature activation-9.74e+00

Pos logit contributions
 hotel+0.006
 city+0.006
 talent+0.006
 opera+0.006
 orchestra+0.006
Neg logit contributions
es-0.004
icked-0.004
 could-0.003
owed-0.003
iled-0.003
Token nap
Token ID25422
Feature activation+2.25e+00

Pos logit contributions
 orchestra+0.116
 hotel+0.114
 city+0.113
 opera+0.113
 talent+0.111
Neg logit contributions
es-0.219
icked-0.198
 could-0.195
 on-0.182
 in-0.180
Tokenkins
Token ID5331
Feature activation+6.34e+00

Pos logit contributions
es+0.035
icked+0.034
owed+0.026
 could+0.026
iled+0.025
Neg logit contributions
 hotel-0.048
 talent-0.048
 city-0.047
 opera-0.046
 former-0.045
Token?
Token ID30
Feature activation+4.99e+00

Pos logit contributions
es+0.095
icked+0.093
owed+0.069
iled+0.066
bed+0.064
Neg logit contributions
 talent-0.140
 hotel-0.137
 city-0.134
 opera-0.133
 airport-0.131
Token helped
Token ID4193
Feature activation+2.36e+00

Pos logit contributions
es+0.020
icked+0.018
owed+0.014
uts+0.014
iled+0.014
Neg logit contributions
 talent-0.022
 city-0.022
 hotel-0.021
 airport-0.021
 opera-0.021
Token the
Token ID262
Feature activation-1.30e+01

Pos logit contributions
icked+0.045
es+0.045
 could+0.036
owed+0.035
iled+0.035
Neg logit contributions
 opera-0.040
 hotel-0.040
 city-0.039
 church-0.039
 talent-0.039
Token old
Token ID1468
Feature activation-9.60e+00

Pos logit contributions
 talent+0.159
 orchestra+0.151
 former+0.150
 hotel+0.143
 opera+0.139
Neg logit contributions
es-0.309
icked-0.291
 could-0.273
 they-0.266
 there-0.263
Token lady
Token ID10846
Feature activation+2.30e+00

Pos logit contributions
 talent+0.094
 former+0.090
 hotel+0.089
 opera+0.085
 orchestra+0.085
Neg logit contributions
es-0.264
icked-0.245
 could-0.222
owed-0.220
ed-0.215
Token fix
Token ID4259
Feature activation-4.24e-01

Pos logit contributions
es+0.043
icked+0.042
 could+0.032
iled+0.031
ed+0.031
Neg logit contributions
 city-0.040
 talent-0.040
 hotel-0.040
 opera-0.039
 former-0.038
Token the
Token ID262
Feature activation-1.74e+01

Pos logit contributions
 hotel+0.009
 talent+0.009
 city+0.009
 opera+0.009
 airport+0.009
Neg logit contributions
es-0.007
icked-0.006
 could-0.005
owed-0.005
iled-0.004
Token fence
Token ID13990
Feature activation+4.20e+00

Pos logit contributions
 talent+0.237
 orchestra+0.235
 opera+0.220
 actor+0.219
 priest+0.215
Neg logit contributions
es-0.391
icked-0.362
 could-0.342
 there-0.329
 on-0.328
Token.
Token ID13
Feature activation+2.90e+00

Pos logit contributions
es+0.061
icked+0.061
owed+0.042
iled+0.041
ched+0.040
Neg logit contributions
 city-0.092
 hotel-0.091
 opera-0.088
 playground-0.088
 airport-0.088
Token
Token ID220
Feature activation+1.28e-01

Pos logit contributions
es+0.051
icked+0.046
ppers+0.041
owed+0.039
iled+0.039
Neg logit contributions
 city-0.054
 zoo-0.052
 hotel-0.052
 talent-0.050
 playground-0.050
Token
Token ID198
Feature activation-3.59e-01

Pos logit contributions
es+0.002
icked+0.002
led+0.002
iled+0.002
 could+0.002
Neg logit contributions
 city-0.002
 talent-0.002
 park-0.002
 zoo-0.002
 playground-0.002
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
 city+0.007
 talent+0.007
 hotel+0.007
 zoo+0.007
 playground+0.006
Neg logit contributions
es-0.006
icked-0.006
owed-0.005
iled-0.005
ed-0.005
Token why
Token ID1521
Feature activation-2.96e-01

Pos logit contributions
es+0.051
icked+0.050
owed+0.035
ched+0.034
iled+0.034
Neg logit contributions
 hotel-0.093
 talent-0.092
 opera-0.092
 city-0.091
 museum-0.089
Token he
Token ID339
Feature activation+2.03e+00

Pos logit contributions
 hotel+0.008
 city+0.008
 talent+0.008
 opera+0.008
 airport+0.007
Neg logit contributions
es-0.003
icked-0.003
owed-0.002
iled-0.002
ed-0.002
Token had
Token ID550
Feature activation-6.84e-01

Pos logit contributions
es+0.032
icked+0.030
bed+0.021
ed+0.021
iled+0.021
Neg logit contributions
 talent-0.042
 city-0.042
 hotel-0.042
 opera-0.041
 airport-0.040
Token fixed
Token ID5969
Feature activation-8.48e-02

Pos logit contributions
 hotel+0.016
 city+0.016
 orchestra+0.015
 former+0.015
 opera+0.015
Neg logit contributions
es-0.009
icked-0.009
 could-0.008
 on-0.006
 there-0.006
Token her
Token ID607
Feature activation-1.10e+01

Pos logit contributions
 hotel+0.002
 talent+0.002
 city+0.002
 opera+0.002
 former+0.002
Neg logit contributions
es-0.001
icked-0.001
 could-0.001
owed-0.001
iled-0.001
Token the
Token ID262
Feature activation-1.69e+01

Pos logit contributions
 former+0.131
 city+0.125
 hotel+0.123
 talent+0.122
 opera+0.122
Neg logit contributions
es-0.273
icked-0.243
 could-0.228
 on-0.219
owed-0.215
Token screen
Token ID3159
Feature activation+4.51e+00

Pos logit contributions
 former+0.277
 priest+0.229
 salon+0.224
 majesty+0.214
 tant+0.209
Neg logit contributions
es-0.327
 on-0.325
 could-0.300
 in-0.299
 with-0.288
Token.
Token ID13
Feature activation+3.23e+00

Pos logit contributions
es+0.062
icked+0.059
iled+0.041
 could+0.040
owed+0.040
Neg logit contributions
 hotel-0.105
 talent-0.105
 city-0.105
 opera-0.104
 airport-0.102
Token
Token ID198
Feature activation-1.44e-01

Pos logit contributions
es+0.054
icked+0.049
 could+0.039
owed+0.038
iled+0.037
Neg logit contributions
 talent-0.068
 hotel-0.067
 city-0.067
 opera-0.066
 orchestra-0.064
Token
Token ID198
Feature activation+2.42e-01

Pos logit contributions
 hotel+0.004
 talent+0.004
 city+0.004
 opera+0.004
 orchestra+0.004
Neg logit contributions
es-0.002
icked-0.002
 could-0.001
owed-0.001
iled-0.001
Token"
Token ID1
Feature activation-2.89e-01

Pos logit contributions
es+0.004
icked+0.004
 could+0.003
owed+0.003
iled+0.003
Neg logit contributions
 hotel-0.005
 city-0.005
 talent-0.005
 opera-0.005
 orchestra-0.005
Token you
Token ID345
Feature activation+6.41e-01

Pos logit contributions
es+0.018
icked+0.017
 could+0.013
owed+0.013
iled+0.012
Neg logit contributions
 talent-0.029
 hotel-0.029
 city-0.029
 opera-0.029
 orchestra-0.028
Token.
Token ID13
Feature activation+2.48e+00

Pos logit contributions
icked+0.010
es+0.010
owed+0.008
ched+0.008
ed+0.007
Neg logit contributions
 opera-0.013
 talent-0.013
 mistake-0.013
 hotel-0.013
 city-0.013
Token I
Token ID314
Feature activation+1.61e+00

Pos logit contributions
es+0.041
icked+0.037
owed+0.030
 could+0.028
ched+0.027
Neg logit contributions
 talent-0.053
 opera-0.051
 city-0.051
 hotel-0.050
 museum-0.050
Token will
Token ID481
Feature activation+4.28e-01

Pos logit contributions
es+0.033
icked+0.030
 could+0.028
iled+0.025
owed+0.025
Neg logit contributions
 hotel-0.028
 city-0.028
 airport-0.027
 opera-0.027
 orchestra-0.027
Token fix
Token ID4259
Feature activation+1.34e+00

Pos logit contributions
es+0.007
icked+0.006
 could+0.006
bed+0.005
owed+0.005
Neg logit contributions
 hotel-0.009
 city-0.009
 opera-0.008
 airport-0.008
 orchestra-0.008
Token the
Token ID262
Feature activation-1.69e+01

Pos logit contributions
es+0.021
icked+0.018
 could+0.014
 on+0.013
 they+0.013
Neg logit contributions
 hotel-0.030
 talent-0.030
 city-0.030
 former-0.029
 orchestra-0.029
Token pengu
Token ID38373
Feature activation-4.55e+00

Pos logit contributions
 former+0.256
 orchestra+0.248
 talent+0.244
igsaw+0.235
 classrooms+0.231
Neg logit contributions
es-0.313
 on-0.289
 with-0.279
 in-0.274
 could-0.259
Tokenin
Token ID259
Feature activation-6.38e-01

Pos logit contributions
 talent+0.090
 city+0.090
 hotel+0.090
 former+0.088
 opera+0.088
Neg logit contributions
es-0.082
icked-0.073
 could-0.060
owed-0.059
iled-0.057
Token.
Token ID13
Feature activation+2.55e+00

Pos logit contributions
 hotel+0.016
 talent+0.016
 city+0.016
 opera+0.016
 zoo+0.015
Neg logit contributions
es-0.008
icked-0.007
 could-0.005
owed-0.005
iled-0.005
Token Then
Token ID3244
Feature activation+2.65e+00

Pos logit contributions
es+0.039
icked+0.034
owed+0.028
 could+0.026
iled+0.025
Neg logit contributions
 talent-0.057
 city-0.056
 opera-0.056
 hotel-0.055
 former-0.055
Token you
Token ID345
Feature activation+1.25e+00

Pos logit contributions
es+0.050
icked+0.047
iled+0.039
owed+0.038
ched+0.038
Neg logit contributions
 talent-0.050
 opera-0.048
 memory-0.048
 hotel-0.047
 mirror-0.047
Token him
Token ID683
Feature activation+1.52e+00

Pos logit contributions
es+0.045
icked+0.041
 could+0.030
owed+0.028
iled+0.027
Neg logit contributions
 talent-0.090
 hotel-0.090
 opera-0.089
 city-0.089
 orchestra-0.087
Token if
Token ID611
Feature activation+2.61e+00

Pos logit contributions
es+0.021
icked+0.020
iled+0.015
owed+0.015
ched+0.015
Neg logit contributions
 opera-0.034
 talent-0.034
 hotel-0.034
 city-0.033
 museum-0.033
Token he
Token ID339
Feature activation+2.25e+00

Pos logit contributions
es+0.029
icked+0.027
owed+0.020
iled+0.019
ched+0.017
Neg logit contributions
 talent-0.068
 hotel-0.068
 opera-0.068
 city-0.067
 airport-0.066
Token would
Token ID561
Feature activation+1.12e+00

Pos logit contributions
es+0.025
icked+0.022
bed+0.016
iled+0.015
owed+0.015
Neg logit contributions
 talent-0.053
 hotel-0.053
 city-0.053
 museum-0.052
 mistake-0.052
Token share
Token ID2648
Feature activation+2.37e+00

Pos logit contributions
es+0.021
icked+0.020
 could+0.016
owed+0.016
iled+0.015
Neg logit contributions
 talent-0.021
 hotel-0.021
 city-0.021
 opera-0.021
 orchestra-0.020
Token the
Token ID262
Feature activation-1.67e+01

Pos logit contributions
es+0.036
icked+0.032
 could+0.026
owed+0.024
iled+0.024
Neg logit contributions
 hotel-0.053
 talent-0.053
 city-0.052
 opera-0.052
 orchestra-0.051
Token pie
Token ID2508
Feature activation+1.59e+00

Pos logit contributions
 orchestra+0.294
 opera+0.268
 former+0.268
 hotel+0.267
 talent+0.260
Neg logit contributions
es-0.304
icked-0.290
 there-0.276
 could-0.271
 on-0.265
Token with
Token ID351
Feature activation+6.86e-01

Pos logit contributions
icked+0.022
es+0.021
 could+0.015
owed+0.015
ched+0.015
Neg logit contributions
 talent-0.036
 hotel-0.036
 city-0.036
 opera-0.035
 mistake-0.035
Token her
Token ID607
Feature activation-5.49e+00

Pos logit contributions
es+0.008
icked+0.007
 could+0.005
owed+0.004
ed+0.004
Neg logit contributions
 hotel-0.018
 talent-0.018
 city-0.018
 opera-0.017
 orchestra-0.017
Token.
Token ID13
Feature activation+2.17e+00

Pos logit contributions
 talent+0.137
 hotel+0.137
 city+0.136
 opera+0.135
 orchestra+0.132
Neg logit contributions
es-0.068
icked-0.061
 could-0.045
owed-0.043
iled-0.040
Token
Token ID198
Feature activation+5.44e-01

Pos logit contributions
es+0.031
icked+0.029
owed+0.023
iled+0.021
ed+0.021
Neg logit contributions
 talent-0.050
 city-0.049
 opera-0.048
 hotel-0.048
 classroom-0.048
Token neighbor
Token ID4780
Feature activation+2.44e+00

Pos logit contributions
 orchestra+0.141
 ey+0.139
 tant+0.138
 mirror+0.128
 doorway+0.128
Neg logit contributions
es-0.151
icked-0.136
 could-0.134
 on-0.126
 they-0.124
Token to
Token ID284
Feature activation-7.78e-01

Pos logit contributions
es+0.032
icked+0.030
 could+0.022
owed+0.021
iled+0.021
Neg logit contributions
 hotel-0.058
 talent-0.058
 opera-0.057
 city-0.057
 airport-0.055
Token help
Token ID1037
Feature activation+2.28e+00

Pos logit contributions
 hotel+0.014
 city+0.013
 talent+0.013
 orchestra+0.013
 opera+0.013
Neg logit contributions
es-0.015
icked-0.014
 could-0.012
owed-0.011
iled-0.011
Token them
Token ID606
Feature activation+1.19e-01

Pos logit contributions
es+0.043
icked+0.043
owed+0.033
 could+0.033
ed+0.033
Neg logit contributions
 opera-0.042
 talent-0.041
 city-0.041
 hotel-0.041
 airport-0.039
Token repair
Token ID9185
Feature activation+2.05e+00

Pos logit contributions
es+0.002
icked+0.002
ed+0.001
owed+0.001
 could+0.001
Neg logit contributions
 talent-0.002
 city-0.002
 opera-0.002
 hotel-0.002
 former-0.002
Token the
Token ID262
Feature activation-1.66e+01

Pos logit contributions
es+0.032
icked+0.030
 could+0.023
owed+0.023
iled+0.022
Neg logit contributions
 hotel-0.044
 talent-0.044
 city-0.044
 opera-0.044
 orchestra-0.043
Token tractor
Token ID38278
Feature activation+4.47e+00

Pos logit contributions
 talent+0.253
 orchestra+0.250
 hotel+0.245
 former+0.241
 opera+0.241
Neg logit contributions
es-0.334
icked-0.307
 could-0.291
 on-0.278
iled-0.269
Token.
Token ID13
Feature activation+3.91e+00

Pos logit contributions
es+0.065
icked+0.064
owed+0.046
iled+0.045
ed+0.044
Neg logit contributions
 city-0.099
 hotel-0.097
 talent-0.096
 opera-0.095
 airport-0.095
Token
Token ID220
Feature activation+3.67e-02

Pos logit contributions
es+0.054
icked+0.049
owed+0.036
 could+0.036
ched+0.034
Neg logit contributions
 city-0.093
 hotel-0.092
 talent-0.091
 opera-0.090
 airport-0.088
Token
Token ID198
Feature activation+1.82e-01

Pos logit contributions
es+0.001
icked+0.001
led+0.000
owed+0.000
iled+0.000
Neg logit contributions
 city-0.001
 hotel-0.001
 museum-0.001
 zoo-0.001
 talent-0.001
Token
Token ID198
Feature activation+5.32e-01

Pos logit contributions
es+0.003
icked+0.003
owed+0.002
 could+0.002
ed+0.002
Neg logit contributions
 city-0.004
 talent-0.004
 hotel-0.004
 museum-0.004
 zoo-0.004
Token little
Token ID1310
Feature activation-6.94e+00

Pos logit contributions
 former+0.214
reating+0.200
opl+0.194
 tant+0.182
 talent+0.180
Neg logit contributions
es-0.232
 could-0.228
 there-0.227
 in-0.214
 they-0.206
Token boy
Token ID2933
Feature activation+2.33e+00

Pos logit contributions
 talent+0.090
 former+0.089
 orchestra+0.084
 opera+0.083
 hotel+0.083
Neg logit contributions
es-0.165
icked-0.152
 could-0.145
ed-0.138
 there-0.137
Token to
Token ID284
Feature activation-8.87e-01

Pos logit contributions
es+0.032
icked+0.031
 could+0.023
bed+0.022
iled+0.022
Neg logit contributions
 hotel-0.052
 opera-0.052
 talent-0.051
 city-0.051
 museum-0.050
Token put
Token ID1234
Feature activation-3.27e-01

Pos logit contributions
 hotel+0.017
 city+0.017
 talent+0.017
 orchestra+0.016
 former+0.016
Neg logit contributions
es-0.016
icked-0.015
 could-0.013
owed-0.012
 they-0.011
Token away
Token ID1497
Feature activation+1.62e+00

Pos logit contributions
 talent+0.007
 hotel+0.007
 opera+0.007
 city+0.007
 orchestra+0.007
Neg logit contributions
es-0.005
icked-0.004
 could-0.004
owed-0.004
iled-0.003
Token the
Token ID262
Feature activation-1.66e+01

Pos logit contributions
es+0.027
icked+0.024
 could+0.020
owed+0.019
iled+0.018
Neg logit contributions
 talent-0.034
 hotel-0.034
 city-0.034
 opera-0.034
 orchestra-0.033
Token hose
Token ID31489
Feature activation+4.62e+00

Pos logit contributions
 former+0.270
 hotel+0.258
 talent+0.258
 orchestra+0.251
 city+0.245
Neg logit contributions
es-0.325
icked-0.305
 could-0.286
 on-0.286
 there-0.286
Token and
Token ID290
Feature activation+5.80e-01

Pos logit contributions
es+0.065
icked+0.061
 could+0.043
owed+0.043
iled+0.041
Neg logit contributions
 hotel-0.106
 city-0.105
 talent-0.104
 opera-0.104
 airport-0.102
Token come
Token ID1282
Feature activation+1.25e+00

Pos logit contributions
es+0.009
icked+0.009
 could+0.007
owed+0.007
iled+0.006
Neg logit contributions
 hotel-0.012
 talent-0.012
 opera-0.012
 city-0.012
 orchestra-0.012
Token inside
Token ID2641
Feature activation+3.97e+00

Pos logit contributions
es+0.025
icked+0.024
 could+0.019
owed+0.019
ched+0.019
Neg logit contributions
 hotel-0.020
 city-0.020
 opera-0.020
 talent-0.019
 playground-0.019
Token.
Token ID13
Feature activation+3.89e+00

Pos logit contributions
es+0.054
icked+0.050
owed+0.036
 could+0.036
iled+0.034
Neg logit contributions
 hotel-0.095
 talent-0.095
 city-0.094
 opera-0.093
 orchestra-0.090
Token should
Token ID815
Feature activation+5.45e-01

Pos logit contributions
es+0.018
icked+0.016
 could+0.013
owed+0.013
iled+0.012
Neg logit contributions
 talent-0.023
 hotel-0.023
 city-0.022
 opera-0.022
 orchestra-0.022
Token be
Token ID307
Feature activation-3.19e+00

Pos logit contributions
es+0.010
icked+0.009
 could+0.008
owed+0.007
iled+0.007
Neg logit contributions
 hotel-0.010
 talent-0.010
 city-0.010
 opera-0.010
 orchestra-0.010
Token able
Token ID1498
Feature activation-1.64e-01

Pos logit contributions
 talent+0.052
 opera+0.051
 hotel+0.050
 city+0.050
 orchestra+0.048
Neg logit contributions
es-0.068
icked-0.064
 could-0.054
owed-0.054
iled-0.052
Token to
Token ID284
Feature activation-3.73e+00

Pos logit contributions
 talent+0.004
 opera+0.004
 hotel+0.004
 city+0.004
 memory+0.003
Neg logit contributions
es-0.003
icked-0.002
owed-0.002
 could-0.002
iled-0.002
Token fix
Token ID4259
Feature activation+1.08e+00

Pos logit contributions
 hotel+0.069
 talent+0.068
 city+0.067
 opera+0.066
 orchestra+0.065
Neg logit contributions
es-0.068
icked-0.061
 could-0.056
 on-0.051
ched-0.051
Token the
Token ID262
Feature activation-1.65e+01

Pos logit contributions
es+0.017
icked+0.015
 could+0.012
owed+0.011
iled+0.011
Neg logit contributions
 hotel-0.024
 talent-0.024
 city-0.023
 opera-0.023
 orchestra-0.023
Token dress
Token ID6576
Feature activation+3.60e+00

Pos logit contributions
 priest+0.244
 pastor+0.233
 tant+0.231
 city+0.230
 actor+0.229
Neg logit contributions
es-0.321
 on-0.300
 could-0.289
 there-0.287
icked-0.276
Token."
Token ID526
Feature activation+4.00e+00

Pos logit contributions
es+0.047
icked+0.046
iled+0.033
 could+0.033
owed+0.031
Neg logit contributions
 hotel-0.084
 opera-0.084
 city-0.083
 talent-0.083
 airport-0.081
Token
Token ID220
Feature activation+1.14e-01

Pos logit contributions
es+0.063
icked+0.060
owed+0.049
iled+0.046
ched+0.043
Neg logit contributions
 talent-0.081
 former-0.078
 mirror-0.077
 city-0.077
 classroom-0.076
Token
Token ID198
Feature activation+3.74e-01

Pos logit contributions
es+0.002
icked+0.002
owed+0.001
iled+0.001
led+0.001
Neg logit contributions
 former-0.002
 talent-0.002
 mistake-0.002
 classroom-0.002
 city-0.002
Token
Token ID198
Feature activation+4.18e-01

Pos logit contributions
es+0.005
icked+0.005
owed+0.004
 could+0.004
iled+0.004
Neg logit contributions
 talent-0.008
 city-0.008
 opera-0.008
 former-0.008
 hotel-0.008
Token showed
Token ID3751
Feature activation+1.83e+00

Pos logit contributions
es+0.066
icked+0.061
iled+0.047
hot+0.045
 could+0.044
Neg logit contributions
 talent-0.096
 opera-0.095
 hotel-0.095
 city-0.093
 former-0.092
Token him
Token ID683
Feature activation+5.36e-01

Pos logit contributions
es+0.023
icked+0.021
owed+0.015
 could+0.015
iled+0.014
Neg logit contributions
 talent-0.045
 hotel-0.044
 opera-0.044
 city-0.044
 orchestra-0.042
Token how
Token ID703
Feature activation-1.32e+00

Pos logit contributions
es+0.008
icked+0.007
 could+0.006
iled+0.006
owed+0.006
Neg logit contributions
 talent-0.012
 hotel-0.012
 opera-0.011
 city-0.011
 mistake-0.011
Token to
Token ID284
Feature activation-2.31e+00

Pos logit contributions
 talent+0.029
 hotel+0.027
 city+0.027
 opera+0.027
 memory+0.026
Neg logit contributions
es-0.021
icked-0.019
owed-0.015
bed-0.013
iled-0.013
Token fix
Token ID4259
Feature activation+4.66e-01

Pos logit contributions
 hotel+0.042
 city+0.041
 talent+0.041
 opera+0.040
 orchestra+0.040
Neg logit contributions
es-0.044
icked-0.041
 could-0.037
owed-0.035
bed-0.034
Token the
Token ID262
Feature activation-1.65e+01

Pos logit contributions
es+0.007
icked+0.006
 could+0.005
owed+0.005
iled+0.005
Neg logit contributions
 hotel-0.010
 talent-0.010
 city-0.010
 opera-0.010
 orchestra-0.010
Token branch
Token ID8478
Feature activation+2.33e+00

Pos logit contributions
 talent+0.266
 hotel+0.262
 orchestra+0.261
 opera+0.259
 city+0.257
Neg logit contributions
es-0.348
icked-0.323
 could-0.286
owed-0.266
 on-0.266
Token.
Token ID13
Feature activation+3.32e+00

Pos logit contributions
icked+0.034
es+0.034
iled+0.024
owed+0.024
ed+0.023
Neg logit contributions
 city-0.049
 hotel-0.048
 opera-0.048
 mistake-0.048
 talent-0.047
Token From
Token ID3574
Feature activation-7.51e-01

Pos logit contributions
es+0.060
icked+0.052
owed+0.050
mar+0.045
ppers+0.044
Neg logit contributions
 former-0.062
 talent-0.060
 new-0.056
 museum-0.055
 city-0.055
Token that
Token ID326
Feature activation-2.97e+00

Pos logit contributions
 talent+0.018
 opera+0.018
 city+0.017
 hotel+0.017
 airport+0.017
Neg logit contributions
es-0.011
icked-0.010
owed-0.007
 could-0.007
iled-0.007
Token day
Token ID1110
Feature activation+3.30e-01

Pos logit contributions
 talent+0.031
 city+0.030
 hotel+0.030
 opera+0.029
 zoo+0.027
Neg logit contributions
es-0.082
icked-0.079
owed-0.069
 could-0.067
ed-0.066
Token "
Token ID366
Feature activation+3.17e-01

Pos logit contributions
es+0.053
icked+0.052
owed+0.047
led+0.044
ched+0.042
Neg logit contributions
 opera-0.049
 zoo-0.048
 mirror-0.047
 bus-0.047
 city-0.046
TokenMaybe
Token ID13300
Feature activation+1.20e+00

Pos logit contributions
es+0.006
icked+0.006
owed+0.005
 could+0.005
iled+0.004
Neg logit contributions
 talent-0.006
 city-0.006
 opera-0.006
 hotel-0.006
 airport-0.005
Token we
Token ID356
Feature activation+1.12e+00

Pos logit contributions
es+0.018
icked+0.018
owed+0.014
ched+0.013
iled+0.013
Neg logit contributions
 opera-0.027
 city-0.027
 talent-0.026
 hotel-0.026
 museum-0.026
Token can
Token ID460
Feature activation-1.78e-01

Pos logit contributions
es+0.019
icked+0.018
owed+0.015
iled+0.014
ed+0.014
Neg logit contributions
 talent-0.022
 city-0.022
 hotel-0.022
 opera-0.022
 airport-0.021
Token share
Token ID2648
Feature activation+2.14e+00

Pos logit contributions
 talent+0.003
 city+0.003
 hotel+0.003
 opera+0.003
 orchestra+0.003
Neg logit contributions
es-0.004
icked-0.004
owed-0.003
 could-0.003
ed-0.003
Token the
Token ID262
Feature activation-1.65e+01

Pos logit contributions
es+0.033
icked+0.029
 could+0.023
owed+0.022
iled+0.021
Neg logit contributions
 hotel-0.048
 talent-0.047
 city-0.047
 opera-0.046
 orchestra-0.046
Token ball
Token ID2613
Feature activation+2.92e+00

Pos logit contributions
 priest+0.311
 hotel+0.310
 former+0.309
 orchestra+0.304
 opera+0.304
Neg logit contributions
es-0.277
icked-0.249
 could-0.242
 there-0.238
 on-0.238
Token with
Token ID351
Feature activation+3.14e-01

Pos logit contributions
es+0.037
icked+0.036
owed+0.026
 could+0.026
ched+0.023
Neg logit contributions
 talent-0.069
 opera-0.069
 hotel-0.069
 city-0.069
 zoo-0.066
Token him
Token ID683
Feature activation+1.92e+00

Pos logit contributions
es+0.005
icked+0.004
 could+0.004
owed+0.003
iled+0.003
Neg logit contributions
 hotel-0.007
 talent-0.007
 city-0.007
 opera-0.007
 orchestra-0.007
Token.
Token ID13
Feature activation+2.83e+00

Pos logit contributions
icked+0.028
es+0.027
owed+0.021
ched+0.020
iled+0.020
Neg logit contributions
 opera-0.040
 city-0.040
 hotel-0.040
 talent-0.039
 zoo-0.038
Token Maybe
Token ID6674
Feature activation+1.21e+00

Pos logit contributions
es+0.043
icked+0.039
owed+0.032
led+0.030
ed+0.029
Neg logit contributions
 city-0.061
 opera-0.060
 talent-0.060
 hotel-0.060
 museum-0.060
TokenLook
Token ID8567
Feature activation+5.66e-01

Pos logit contributions
 hotel+0.006
 talent+0.006
 city+0.006
 opera+0.006
 orchestra+0.006
Neg logit contributions
es-0.005
icked-0.004
 could-0.004
owed-0.003
iled-0.003
Token.
Token ID13
Feature activation+3.09e+00

Pos logit contributions
es+0.008
icked+0.007
ched+0.006
 could+0.006
iled+0.005
Neg logit contributions
 opera-0.013
 hotel-0.012
 talent-0.012
 mirror-0.012
 city-0.012
Token I
Token ID314
Feature activation+5.89e-01

Pos logit contributions
es+0.043
icked+0.039
owed+0.030
led+0.029
ched+0.028
Neg logit contributions
 city-0.071
 hotel-0.070
 museum-0.070
 talent-0.069
 opera-0.069
Token have
Token ID423
Feature activation-1.29e+00

Pos logit contributions
es+0.009
icked+0.008
 could+0.006
owed+0.006
iled+0.006
Neg logit contributions
 talent-0.013
 hotel-0.013
 city-0.013
 opera-0.013
 orchestra-0.013
Token fixed
Token ID5969
Feature activation-3.10e-01

Pos logit contributions
 hotel+0.028
 city+0.027
 opera+0.027
 orchestra+0.027
 talent+0.027
Neg logit contributions
es-0.020
icked-0.019
 could-0.016
ed-0.014
ched-0.014
Token the
Token ID262
Feature activation-1.65e+01

Pos logit contributions
 talent+0.007
 hotel+0.007
 city+0.007
 opera+0.007
 orchestra+0.007
Neg logit contributions
es-0.005
icked-0.004
 could-0.003
owed-0.003
iled-0.003
Token important
Token ID1593
Feature activation-1.40e+01

Pos logit contributions
 talent+0.253
reating+0.243
 actor+0.241
 circus+0.238
 humor+0.235
Neg logit contributions
 could-0.310
 in-0.298
 on-0.297
 there-0.296
es-0.275
Token roof
Token ID9753
Feature activation+3.85e+00

Pos logit contributions
 talent+0.178
 orchestra+0.173
 circus+0.167
Ta+0.165
 audience+0.165
Neg logit contributions
es-0.279
 in-0.276
 there-0.274
 could-0.273
 on-0.270
Token.
Token ID13
Feature activation+3.35e+00

Pos logit contributions
es+0.054
icked+0.051
 could+0.036
owed+0.035
iled+0.035
Neg logit contributions
 hotel-0.088
 city-0.088
 opera-0.087
 talent-0.087
 airport-0.085
Token Let
Token ID3914
Feature activation+2.65e+00

Pos logit contributions
es+0.047
icked+0.042
owed+0.032
led+0.030
ed+0.029
Neg logit contributions
 city-0.078
 talent-0.077
 opera-0.076
 hotel-0.076
 museum-0.075
Token's
Token ID338
Feature activation-1.96e+00

Pos logit contributions
es+0.038
icked+0.036
owed+0.027
iled+0.026
 could+0.025
Neg logit contributions
 opera-0.061
 hotel-0.061
 city-0.060
 talent-0.060
 airport-0.059
Token going
Token ID1016
Feature activation+2.12e+00

Pos logit contributions
 hotel+0.048
 talent+0.048
 city+0.048
 opera+0.047
 orchestra+0.047
Neg logit contributions
es-0.039
icked-0.036
 could-0.030
iled-0.027
 on-0.027
Token to
Token ID284
Feature activation-1.56e+00

Pos logit contributions
es+0.029
icked+0.026
owed+0.019
 could+0.018
iled+0.018
Neg logit contributions
 talent-0.051
 hotel-0.051
 city-0.051
 opera-0.050
 airport-0.049
Token help
Token ID1037
Feature activation+2.78e+00

Pos logit contributions
 tant+0.030
 hotel+0.030
 orchestra+0.030
 talent+0.030
 city+0.029
Neg logit contributions
es-0.023
icked-0.020
 could-0.020
 they-0.019
 there-0.018
Token us
Token ID514
Feature activation-5.62e-01

Pos logit contributions
es+0.042
icked+0.040
 could+0.030
owed+0.030
iled+0.028
Neg logit contributions
 hotel-0.062
 talent-0.062
 city-0.061
 opera-0.061
 orchestra-0.059
Token fix
Token ID4259
Feature activation+1.39e+00

Pos logit contributions
 hotel+0.011
 talent+0.011
 city+0.011
 opera+0.011
 airport+0.010
Neg logit contributions
es-0.010
icked-0.010
 could-0.008
owed-0.007
ed-0.007
Token the
Token ID262
Feature activation-1.65e+01

Pos logit contributions
es+0.020
icked+0.017
 could+0.014
owed+0.013
iled+0.012
Neg logit contributions
 talent-0.032
 hotel-0.032
 city-0.032
 opera-0.031
 orchestra-0.031
Token screen
Token ID3159
Feature activation+4.66e+00

Pos logit contributions
 former+0.241
reating+0.218
 orchestra+0.204
 priest+0.202
 talent+0.201
Neg logit contributions
 on-0.325
es-0.308
 in-0.307
 could-0.307
 there-0.302
Token."
Token ID526
Feature activation+3.93e+00

Pos logit contributions
es+0.065
icked+0.063
owed+0.045
 could+0.044
iled+0.044
Neg logit contributions
 hotel-0.107
 city-0.107
 talent-0.105
 opera-0.105
 airport-0.103
Token
Token ID198
Feature activation+3.64e-01

Pos logit contributions
es+0.065
icked+0.063
owed+0.050
ched+0.046
iled+0.045
Neg logit contributions
 city-0.080
 talent-0.079
 hotel-0.079
 mirror-0.076
 opera-0.076
Token
Token ID198
Feature activation+4.88e-01

Pos logit contributions
es+0.005
icked+0.004
 could+0.003
owed+0.003
ed+0.003
Neg logit contributions
 talent-0.009
 hotel-0.009
 city-0.009
 opera-0.009
 orchestra-0.009
TokenThe
Token ID464
Feature activation-1.24e+01

Pos logit contributions
es+0.008
icked+0.007
 could+0.006
iled+0.006
owed+0.006
Neg logit contributions
 hotel-0.010
 talent-0.010
 city-0.010
 opera-0.010
 orchestra-0.010
Token let
Token ID1309
Feature activation+1.04e+00

Pos logit contributions
 hotel+0.017
 talent+0.017
 city+0.017
 opera+0.017
 airport+0.016
Neg logit contributions
es-0.021
icked-0.019
owed-0.016
 could-0.016
ed-0.015
Token me
Token ID502
Feature activation-5.67e-01

Pos logit contributions
es+0.021
icked+0.020
owed+0.017
 could+0.016
iled+0.016
Neg logit contributions
 opera-0.018
 talent-0.018
 hotel-0.018
 city-0.017
 airport-0.017
Token help
Token ID1037
Feature activation+1.46e+00

Pos logit contributions
 talent+0.009
 hotel+0.009
 opera+0.009
 city+0.009
 airport+0.008
Neg logit contributions
es-0.013
icked-0.012
 could-0.010
ed-0.010
owed-0.010
Token you
Token ID345
Feature activation-1.74e+00

Pos logit contributions
es+0.031
icked+0.031
ed+0.025
owed+0.025
iled+0.024
Neg logit contributions
 talent-0.025
 opera-0.024
 city-0.023
 hotel-0.023
 mistake-0.022
Token carry
Token ID3283
Feature activation+3.29e-01

Pos logit contributions
 hotel+0.029
 talent+0.029
 opera+0.029
 city+0.028
 former+0.028
Neg logit contributions
es-0.036
icked-0.035
 could-0.028
ed-0.028
owed-0.028
Token the
Token ID262
Feature activation-1.64e+01

Pos logit contributions
es+0.005
icked+0.005
owed+0.004
 could+0.004
iled+0.004
Neg logit contributions
 talent-0.007
 hotel-0.007
 city-0.007
 opera-0.007
 airport-0.007
Token ac
Token ID936
Feature activation-6.19e+00

Pos logit contributions
 orchestra+0.327
 opera+0.326
 talent+0.319
 hotel+0.319
 city+0.311
Neg logit contributions
es-0.268
icked-0.246
 could-0.241
 on-0.214
 there-0.205
Tokenorn
Token ID1211
Feature activation+1.31e+00

Pos logit contributions
 talent+0.103
 hotel+0.102
 city+0.101
 opera+0.098
 museum+0.097
Neg logit contributions
es-0.123
icked-0.118
owed-0.097
 could-0.095
iled-0.092
Token home
Token ID1363
Feature activation+3.85e+00

Pos logit contributions
es+0.022
icked+0.022
owed+0.016
iled+0.016
 could+0.016
Neg logit contributions
 hotel-0.026
 talent-0.026
 city-0.026
 opera-0.025
 former-0.025
Token?
Token ID30
Feature activation+4.05e+00

Pos logit contributions
es+0.060
icked+0.059
iled+0.043
ched+0.042
owed+0.042
Neg logit contributions
 hotel-0.082
 talent-0.082
 city-0.081
 opera-0.080
 former-0.079
Token I
Token ID314
Feature activation+8.17e-01

Pos logit contributions
es+0.061
icked+0.056
led+0.048
owed+0.045
ged+0.042
Neg logit contributions
 talent-0.082
 former-0.081
 city-0.080
 opera-0.079
 orchestra-0.079
Token did
Token ID750
Feature activation+1.40e+00

Pos logit contributions
es+0.026
icked+0.023
 could+0.018
owed+0.017
iled+0.016
Neg logit contributions
 talent-0.045
 hotel-0.045
 city-0.044
 opera-0.044
 orchestra-0.043
Token not
Token ID407
Feature activation-2.56e+00

Pos logit contributions
es+0.018
icked+0.016
 could+0.012
owed+0.012
iled+0.011
Neg logit contributions
 talent-0.034
 hotel-0.034
 city-0.034
 opera-0.034
 orchestra-0.033
Token want
Token ID765
Feature activation+4.91e-01

Pos logit contributions
 hotel+0.051
 city+0.050
 airport+0.049
 former+0.049
 talent+0.049
Neg logit contributions
es-0.044
icked-0.041
 could-0.035
owed-0.032
iled-0.032
Token to
Token ID284
Feature activation-3.48e+00

Pos logit contributions
es+0.004
icked+0.004
 could+0.003
 they+0.002
 on+0.002
Neg logit contributions
 former-0.014
 hotel-0.014
 orchestra-0.014
 city-0.014
 talent-0.013
Token share
Token ID2648
Feature activation+1.53e+00

Pos logit contributions
 hotel+0.068
 city+0.067
 airport+0.066
 talent+0.066
 former+0.065
Neg logit contributions
es-0.057
icked-0.054
 could-0.046
owed-0.043
 they-0.042
Token the
Token ID262
Feature activation-1.64e+01

Pos logit contributions
es+0.020
icked+0.017
 could+0.013
owed+0.011
 on+0.011
Neg logit contributions
 talent-0.038
 hotel-0.038
 city-0.037
 orchestra-0.037
 opera-0.037
Token seal
Token ID13810
Feature activation+1.11e+00

Pos logit contributions
 former+0.290
 apartment+0.245
 airport+0.242
 orchestra+0.235
 city+0.235
Neg logit contributions
es-0.311
 on-0.292
 there-0.287
 with-0.277
icked-0.272
Token.
Token ID13
Feature activation+2.64e+00

Pos logit contributions
es+0.013
icked+0.011
 could+0.008
owed+0.008
iled+0.007
Neg logit contributions
 hotel-0.028
 talent-0.028
 city-0.028
 opera-0.028
 orchestra-0.027
Token
Token ID198
Feature activation+4.61e-01

Pos logit contributions
es+0.038
icked+0.034
owed+0.027
iled+0.024
 could+0.024
Neg logit contributions
 city-0.062
 talent-0.061
 hotel-0.060
 opera-0.059
 museum-0.059
Token
Token ID198
Feature activation+9.20e-01

Pos logit contributions
es+0.006
icked+0.006
owed+0.004
 could+0.004
iled+0.004
Neg logit contributions
 hotel-0.011
 talent-0.011
 city-0.011
 opera-0.011
 airport-0.010
TokenHe
Token ID1544
Feature activation+1.81e+00

Pos logit contributions
es+0.014
icked+0.013
owed+0.010
 could+0.010
ed+0.009
Neg logit contributions
 city-0.020
 talent-0.020
 hotel-0.020
 opera-0.019
 airport-0.019
Token!
Token ID0
Feature activation+2.71e+00

Pos logit contributions
es+0.039
icked+0.038
owed+0.029
 could+0.025
ed+0.025
Neg logit contributions
 talent-0.067
 opera-0.067
 mistake-0.067
 city-0.066
 hotel-0.064
Token You
Token ID921
Feature activation+5.83e-01

Pos logit contributions
es+0.042
icked+0.038
owed+0.032
led+0.030
ed+0.028
Neg logit contributions
 city-0.056
 talent-0.055
 zoo-0.054
 opera-0.054
 hotel-0.054
Token need
Token ID761
Feature activation-2.28e-01

Pos logit contributions
es+0.009
icked+0.008
owed+0.007
 could+0.006
iled+0.006
Neg logit contributions
 talent-0.012
 city-0.012
 hotel-0.012
 opera-0.012
 airport-0.012
Token to
Token ID284
Feature activation-2.47e+00

Pos logit contributions
 hotel+0.006
 city+0.006
 orchestra+0.006
 opera+0.006
 airport+0.006
Neg logit contributions
es-0.002
icked-0.002
 could-0.002
iled-0.001
ched-0.001
Token share
Token ID2648
Feature activation+2.47e+00

Pos logit contributions
 hotel+0.054
 city+0.052
 orchestra+0.051
 airport+0.051
 talent+0.050
Neg logit contributions
es-0.036
icked-0.034
 could-0.028
iled-0.027
bed-0.027
Token the
Token ID262
Feature activation-1.64e+01

Pos logit contributions
es+0.035
icked+0.030
 could+0.024
owed+0.022
iled+0.022
Neg logit contributions
 hotel-0.058
 talent-0.058
 city-0.057
 opera-0.057
 orchestra-0.056
Token ball
Token ID2613
Feature activation+3.02e+00

Pos logit contributions
 opera+0.262
 hotel+0.262
 talent+0.258
 orchestra+0.258
 priest+0.258
Neg logit contributions
es-0.333
icked-0.306
 could-0.282
 on-0.264
 there-0.261
Token."
Token ID526
Feature activation+4.04e+00

Pos logit contributions
es+0.036
icked+0.035
 could+0.024
owed+0.024
iled+0.021
Neg logit contributions
 talent-0.075
 hotel-0.075
 city-0.074
 opera-0.074
 mistake-0.071
Token Buddy
Token ID36896
Feature activation+3.92e+00

Pos logit contributions
icked+0.065
es+0.058
owed+0.056
bled+0.051
ppers+0.051
Neg logit contributions
 zoo-0.076
 city-0.074
 park-0.071
 talent-0.070
 playground-0.069
Token and
Token ID290
Feature activation-2.60e+00

Pos logit contributions
icked+0.063
es+0.062
owed+0.047
umbered+0.044
hot+0.044
Neg logit contributions
 mistake-0.073
 talent-0.073
 playground-0.071
 hotel-0.071
 city-0.070
Token Wh
Token ID854
Feature activation-2.85e+00

Pos logit contributions
 hotel+0.051
 city+0.050
 opera+0.050
 talent+0.050
 zoo+0.049
Neg logit contributions
es-0.044
icked-0.041
owed-0.034
iled-0.032
 could-0.032
Token learned
Token ID4499
Feature activation-1.23e-01

Pos logit contributions
es+0.017
icked+0.016
 could+0.015
 suggested+0.012
 they+0.011
Neg logit contributions
 hotel-0.027
 opera-0.027
 orchestra-0.026
 city-0.026
 talent-0.026
Token to
Token ID284
Feature activation-2.94e+00

Pos logit contributions
 hotel+0.004
 city+0.004
 orchestra+0.004
 airport+0.003
 former+0.003
Neg logit contributions
es-0.001
icked-0.001
 they-0.001
 could-0.001
 on-0.001
Token be
Token ID307
Feature activation-3.46e+00

Pos logit contributions
 hotel+0.071
 airport+0.069
 orchestra+0.068
 city+0.068
 tant+0.066
Neg logit contributions
es-0.034
icked-0.031
 could-0.028
 with-0.027
bed-0.026
Token careful
Token ID8161
Feature activation+2.48e+00

Pos logit contributions
 hotel+0.052
 city+0.051
 talent+0.050
 opera+0.050
 airport+0.049
Neg logit contributions
es-0.079
icked-0.074
 could-0.065
owed-0.061
iled-0.061
Token of
Token ID286
Feature activation-3.48e+00

Pos logit contributions
icked+0.036
es+0.035
owed+0.025
 could+0.025
oped+0.024
Neg logit contributions
 talent-0.054
 opera-0.053
 mistake-0.052
 city-0.052
 rules-0.051
Token the
Token ID262
Feature activation-1.64e+01

Pos logit contributions
 orchestra+0.065
 hotel+0.065
 talent+0.063
 city+0.063
 former+0.062
Neg logit contributions
es-0.065
icked-0.057
 could-0.051
 they-0.047
 on-0.046
Token crabs
Token ID49172
Feature activation+3.07e+00

Pos logit contributions
 orchestra+0.297
 passenger+0.295
 former+0.288
 apartment+0.283
 opera+0.281
Neg logit contributions
 there-0.261
 could-0.256
 on-0.242
 in-0.234
 they-0.228
Token.
Token ID13
Feature activation+2.48e+00

Pos logit contributions
icked+0.044
es+0.042
owed+0.033
ed+0.031
bed+0.030
Neg logit contributions
 hotel-0.067
 city-0.067
 opera-0.067
 talent-0.066
 museum-0.065
Token<|endoftext|>
Token ID50256
Feature activation+1.28e+00

Pos logit contributions
es+0.034
icked+0.031
owed+0.024
 could+0.022
ed+0.021
Neg logit contributions
 talent-0.059
 city-0.058
 hotel-0.058
 opera-0.057
 former-0.057
TokenBen
Token ID11696
Feature activation+3.05e+00

Pos logit contributions
icked+0.024
es+0.024
owed+0.022
ppers+0.020
iled+0.020
Neg logit contributions
 city-0.022
 hotel-0.022
 museum-0.022
 zoo-0.021
 park-0.021
Token and
Token ID290
Feature activation-2.29e-01

Pos logit contributions
es+0.050
icked+0.049
owed+0.039
 neither+0.036
othe+0.034
Neg logit contributions
 city-0.060
 hotel-0.060
 museum-0.059
 talent-0.059
 park-0.058
Token she
Token ID673
Feature activation+3.07e+00

Pos logit contributions
es+0.018
icked+0.015
owed+0.010
iled+0.009
 could+0.009
Neg logit contributions
 talent-0.056
 opera-0.055
 hotel-0.055
 city-0.055
 airport-0.054
Token would
Token ID561
Feature activation+1.42e+00

Pos logit contributions
es+0.050
icked+0.047
owed+0.036
iled+0.035
 could+0.035
Neg logit contributions
 talent-0.063
 hotel-0.061
 city-0.061
 opera-0.061
 airport-0.059
Token try
Token ID1949
Feature activation+2.44e+00

Pos logit contributions
es+0.028
icked+0.026
 could+0.022
owed+0.021
iled+0.021
Neg logit contributions
 hotel-0.025
 city-0.025
 talent-0.025
 opera-0.024
 orchestra-0.024
Token to
Token ID284
Feature activation-2.48e+00

Pos logit contributions
es+0.031
icked+0.028
 could+0.021
owed+0.019
iled+0.019
Neg logit contributions
 hotel-0.060
 talent-0.060
 city-0.060
 opera-0.059
 orchestra-0.059
Token fix
Token ID4259
Feature activation+1.77e+00

Pos logit contributions
 hotel+0.054
 city+0.051
 airport+0.050
 orchestra+0.050
 tant+0.049
Neg logit contributions
es-0.038
icked-0.035
 could-0.032
 with-0.030
 in-0.029
Token the
Token ID262
Feature activation-1.64e+01

Pos logit contributions
es+0.025
icked+0.021
 could+0.017
owed+0.015
iled+0.015
Neg logit contributions
 talent-0.042
 hotel-0.041
 city-0.041
 orchestra-0.040
 former-0.040
Token train
Token ID4512
Feature activation+2.33e+00

Pos logit contributions
 orchestra+0.264
 former+0.262
 talent+0.252
 actor+0.251
 hotel+0.251
Neg logit contributions
es-0.302
 on-0.274
 there-0.272
icked-0.271
 they-0.269
Token.
Token ID13
Feature activation+2.81e+00

Pos logit contributions
es+0.030
icked+0.028
 could+0.020
owed+0.019
iled+0.019
Neg logit contributions
 hotel-0.056
 talent-0.056
 city-0.056
 opera-0.056
 airport-0.054
Token She
Token ID1375
Feature activation+1.48e+00

Pos logit contributions
es+0.037
icked+0.034
owed+0.026
iled+0.023
 could+0.023
Neg logit contributions
 talent-0.069
 city-0.068
 hotel-0.068
 opera-0.067
 former-0.066
Token said
Token ID531
Feature activation+1.94e+00

Pos logit contributions
es+0.019
icked+0.017
 could+0.012
owed+0.012
iled+0.012
Neg logit contributions
 talent-0.036
 hotel-0.035
 city-0.035
 opera-0.035
 airport-0.034
Token they
Token ID484
Feature activation+2.65e+00

Pos logit contributions
es+0.018
icked+0.016
owed+0.010
iled+0.009
 could+0.009
Neg logit contributions
 opera-0.054
 talent-0.054
 hotel-0.053
 city-0.053
 airport-0.052
Token They
Token ID1119
Feature activation+1.45e+00

Pos logit contributions
es+0.039
icked+0.034
owed+0.027
 could+0.024
ched+0.023
Neg logit contributions
 city-0.067
 talent-0.065
 hotel-0.065
 opera-0.064
 museum-0.063
Token discuss
Token ID2112
Feature activation+4.14e+00

Pos logit contributions
es+0.023
icked+0.022
 could+0.021
owed+0.017
iled+0.017
Neg logit contributions
 hotel-0.029
 talent-0.029
 opera-0.028
 former-0.028
 orchestra-0.028
Token how
Token ID703
Feature activation-8.21e-01

Pos logit contributions
es+0.060
icked+0.056
 could+0.042
owed+0.041
iled+0.040
Neg logit contributions
 talent-0.094
 hotel-0.094
 city-0.093
 opera-0.093
 airport-0.090
Token to
Token ID284
Feature activation-2.45e+00

Pos logit contributions
 talent+0.019
 hotel+0.019
 city+0.019
 opera+0.019
 orchestra+0.018
Neg logit contributions
es-0.012
icked-0.011
 could-0.008
owed-0.008
iled-0.007
Token share
Token ID2648
Feature activation+2.60e+00

Pos logit contributions
 hotel+0.052
 orchestra+0.051
 city+0.051
 opera+0.050
 airport+0.050
Neg logit contributions
es-0.038
icked-0.035
 could-0.030
bed-0.027
owed-0.027
Token the
Token ID262
Feature activation-1.64e+01

Pos logit contributions
es+0.034
icked+0.030
 could+0.023
owed+0.022
iled+0.021
Neg logit contributions
 hotel-0.063
 talent-0.063
 city-0.062
 opera-0.062
 orchestra-0.061
Token sausage
Token ID31889
Feature activation+2.32e+00

Pos logit contributions
 opera+0.327
 orchestra+0.324
 hotel+0.321
 talent+0.317
 city+0.317
Neg logit contributions
es-0.272
icked-0.240
 could-0.213
 on-0.202
bed-0.195
Token.
Token ID13
Feature activation+2.89e+00

Pos logit contributions
icked+0.032
es+0.030
owed+0.024
 could+0.023
iled+0.021
Neg logit contributions
 talent-0.052
 hotel-0.051
 city-0.050
 mistake-0.050
 opera-0.050
Token
Token ID198
Feature activation+3.06e-01

Pos logit contributions
es+0.041
icked+0.037
owed+0.029
 could+0.026
iled+0.025
Neg logit contributions
 city-0.069
 talent-0.068
 hotel-0.067
 opera-0.066
 zoo-0.065
Token
Token ID198
Feature activation+8.78e-01

Pos logit contributions
es+0.004
icked+0.004
owed+0.003
 could+0.003
ed+0.003
Neg logit contributions
 talent-0.007
 city-0.007
 hotel-0.007
 opera-0.007
 museum-0.007
TokenThey
Token ID2990
Feature activation+1.84e+00

Pos logit contributions
es+0.013
icked+0.012
owed+0.009
 could+0.008
ed+0.008
Neg logit contributions
 city-0.020
 talent-0.020
 hotel-0.019
 opera-0.019
 playground-0.019
Token I
Token ID314
Feature activation+1.38e+00

Pos logit contributions
es+0.038
icked+0.032
owed+0.026
ched+0.024
 could+0.023
Neg logit contributions
 talent-0.058
 opera-0.057
 city-0.057
 mirror-0.056
 museum-0.056
Token should
Token ID815
Feature activation+4.50e-01

Pos logit contributions
es+0.021
icked+0.019
 could+0.016
owed+0.015
iled+0.014
Neg logit contributions
 hotel-0.030
 talent-0.030
 city-0.030
 opera-0.030
 orchestra-0.029
Token not
Token ID407
Feature activation-2.22e+00

Pos logit contributions
es+0.007
icked+0.006
 could+0.005
owed+0.005
iled+0.004
Neg logit contributions
 hotel-0.010
 talent-0.010
 city-0.010
 opera-0.010
 orchestra-0.010
Token have
Token ID423
Feature activation-3.09e+00

Pos logit contributions
 talent+0.040
 opera+0.039
 city+0.039
 hotel+0.038
 museum+0.037
Neg logit contributions
es-0.044
icked-0.040
owed-0.033
 could-0.033
ed-0.033
Token taken
Token ID2077
Feature activation-1.17e+00

Pos logit contributions
 talent+0.065
 opera+0.062
 hotel+0.061
 city+0.061
 mistake+0.059
Neg logit contributions
es-0.053
icked-0.047
owed-0.038
 could-0.037
iled-0.036
Token the
Token ID262
Feature activation-1.63e+01

Pos logit contributions
 hotel+0.028
 city+0.028
 former+0.028
 orchestra+0.027
 airport+0.027
Neg logit contributions
es-0.016
icked-0.015
 could-0.012
 on-0.011
ed-0.010
Token boot
Token ID6297
Feature activation+3.46e+00

Pos logit contributions
 former+0.368
 orchestra+0.359
 opera+0.345
 priest+0.342
 talent+0.334
Neg logit contributions
 could-0.213
 on-0.207
 there-0.198
es-0.189
icked-0.183
Token.
Token ID13
Feature activation+2.59e+00

Pos logit contributions
es+0.050
icked+0.047
owed+0.035
 could+0.035
iled+0.033
Neg logit contributions
 hotel-0.076
 opera-0.076
 talent-0.074
 city-0.074
 mistake-0.073
Token That
Token ID1320
Feature activation-1.42e+00

Pos logit contributions
es+0.039
icked+0.033
owed+0.027
led+0.025
ched+0.024
Neg logit contributions
 talent-0.058
 opera-0.057
 city-0.056
 mirror-0.056
 memory-0.055
Token was
Token ID373
Feature activation-2.57e+00

Pos logit contributions
 former+0.036
 talent+0.036
 orchestra+0.035
 hotel+0.035
 opera+0.035
Neg logit contributions
es-0.018
icked-0.014
 could-0.013
ched-0.010
 on-0.010
Token rude
Token ID22066
Feature activation+2.13e+00

Pos logit contributions
 hotel+0.056
 city+0.056
 talent+0.055
 orchestra+0.054
 opera+0.054
Neg logit contributions
es-0.040
icked-0.037
 could-0.031
owed-0.027
iled-0.027
TokenCan
Token ID6090
Feature activation+3.70e+00

Pos logit contributions
 city+0.007
 talent+0.007
 opera+0.007
 hotel+0.007
 airport+0.007
Neg logit contributions
es-0.006
icked-0.006
owed-0.005
 could-0.005
iled-0.004
Token you
Token ID345
Feature activation-1.27e+00

Pos logit contributions
es+0.068
icked+0.064
owed+0.053
ed+0.053
iled+0.050
Neg logit contributions
 museum-0.067
 talent-0.067
 opera-0.067
 city-0.066
 hotel-0.065
Token help
Token ID1037
Feature activation+1.52e+00

Pos logit contributions
 talent+0.021
 hotel+0.020
 opera+0.020
 city+0.020
 orchestra+0.019
Neg logit contributions
es-0.027
icked-0.025
 could-0.021
owed-0.021
ed-0.021
Token me
Token ID502
Feature activation-8.70e-01

Pos logit contributions
es+0.040
icked+0.040
owed+0.035
ed+0.035
iled+0.033
Neg logit contributions
 talent-0.017
 opera-0.017
 city-0.016
 mistake-0.015
 hotel-0.015
Token split
Token ID6626
Feature activation+1.17e+00

Pos logit contributions
 talent+0.015
 opera+0.015
 mistake+0.015
 hotel+0.014
 city+0.014
Neg logit contributions
es-0.018
icked-0.016
ed-0.014
 could-0.014
owed-0.013
Token the
Token ID262
Feature activation-1.63e+01

Pos logit contributions
es+0.022
icked+0.021
owed+0.018
 could+0.017
iled+0.016
Neg logit contributions
 city-0.021
 opera-0.021
 talent-0.021
 hotel-0.021
 airport-0.020
Token fruit
Token ID8234
Feature activation+1.40e+00

Pos logit contributions
 orchestra+0.281
 opera+0.280
 hotel+0.280
 talent+0.279
 former+0.269
Neg logit contributions
es-0.323
icked-0.307
 could-0.268
ed-0.248
 on-0.246
Token?"
Token ID1701
Feature activation+3.12e+00

Pos logit contributions
es+0.024
icked+0.023
owed+0.020
ged+0.019
ched+0.019
Neg logit contributions
 hotel-0.027
 city-0.026
 museum-0.026
 park-0.026
 beach-0.025
Token The
Token ID383
Feature activation-1.26e+01

Pos logit contributions
es+0.050
icked+0.049
owed+0.039
iled+0.035
ed+0.035
Neg logit contributions
 talent-0.067
 opera-0.064
 city-0.064
 hotel-0.063
 zoo-0.062
Token cow
Token ID9875
Feature activation+5.78e+00

Pos logit contributions
 hotel+0.200
 talent+0.198
 former+0.196
 city+0.193
 orchestra+0.192
Neg logit contributions
es-0.266
icked-0.249
 could-0.218
 they-0.200
iled-0.200
Token tried
Token ID3088
Feature activation+3.77e+00

Pos logit contributions
es+0.091
icked+0.084
uts+0.067
iled+0.067
hot+0.066
Neg logit contributions
 talent-0.108
 opera-0.107
 mistake-0.106
 mirror-0.104
 hotel-0.104
Token and
Token ID290
Feature activation-6.17e-01

Pos logit contributions
es+0.022
icked+0.020
owed+0.016
 could+0.015
iled+0.015
Neg logit contributions
 talent-0.032
 opera-0.031
 hotel-0.031
 city-0.031
 mirror-0.030
Token helped
Token ID4193
Feature activation+9.03e-01

Pos logit contributions
 talent+0.013
 opera+0.012
 hotel+0.012
 mirror+0.012
 playground+0.012
Neg logit contributions
es-0.010
icked-0.008
iled-0.007
owed-0.007
hot-0.007
Token her
Token ID607
Feature activation-4.87e+00

Pos logit contributions
es+0.020
icked+0.018
 could+0.016
owed+0.015
iled+0.015
Neg logit contributions
 talent-0.014
 hotel-0.014
 city-0.014
 opera-0.014
 orchestra-0.013
Token dad
Token ID9955
Feature activation+1.90e+00

Pos logit contributions
 hotel+0.065
 talent+0.065
 opera+0.064
 city+0.064
 orchestra+0.062
Neg logit contributions
es-0.117
icked-0.110
 could-0.097
owed-0.094
iled-0.092
Token fix
Token ID4259
Feature activation-8.39e-01

Pos logit contributions
es+0.026
icked+0.024
 could+0.019
owed+0.017
iled+0.017
Neg logit contributions
 talent-0.044
 hotel-0.044
 opera-0.044
 city-0.043
 airport-0.042
Token the
Token ID262
Feature activation-1.63e+01

Pos logit contributions
 talent+0.020
 hotel+0.020
 city+0.020
 opera+0.020
 orchestra+0.020
Neg logit contributions
es-0.011
icked-0.010
 could-0.008
owed-0.007
ed-0.007
Token fence
Token ID13990
Feature activation+3.95e+00

Pos logit contributions
 orchestra+0.278
 hotel+0.275
 actor+0.272
 talent+0.271
 priest+0.271
Neg logit contributions
es-0.291
 could-0.271
icked-0.264
 on-0.262
 there-0.245
Token.
Token ID13
Feature activation+2.20e+00

Pos logit contributions
es+0.054
icked+0.052
 could+0.037
owed+0.037
iled+0.035
Neg logit contributions
 city-0.090
 hotel-0.090
 opera-0.089
 talent-0.088
 airport-0.087
Token She
Token ID1375
Feature activation+1.47e+00

Pos logit contributions
es+0.026
icked+0.023
owed+0.016
 could+0.016
iled+0.015
Neg logit contributions
 talent-0.056
 hotel-0.056
 city-0.056
 opera-0.055
 orchestra-0.054
Token had
Token ID550
Feature activation-1.17e-01

Pos logit contributions
es+0.020
icked+0.018
 could+0.014
owed+0.013
iled+0.012
Neg logit contributions
 hotel-0.035
 talent-0.035
 city-0.035
 opera-0.035
 orchestra-0.034
Token fun
Token ID1257
Feature activation+4.41e-01

Pos logit contributions
 talent+0.002
 hotel+0.002
 city+0.002
 opera+0.002
 orchestra+0.002
Neg logit contributions
es-0.002
icked-0.002
 could-0.002
owed-0.002
iled-0.001
Token
Token ID26391
Feature activation-5.93e-01

Pos logit contributions
 talent+0.024
 opera+0.023
 city+0.023
 hotel+0.022
 orchestra+0.022
Neg logit contributions
es-0.029
icked-0.027
 could-0.022
owed-0.021
bed-0.021
Token
Token ID8151
Feature activation+4.66e+00

Pos logit contributions
 city+0.012
 classroom+0.011
 talent+0.011
 zoo+0.011
 hotel+0.011
Neg logit contributions
icked-0.010
es-0.009
led-0.008
owed-0.008
bed-0.008
Tokens
Token ID82
Feature activation+8.53e-02

Pos logit contributions
es+0.060
icked+0.057
bed+0.044
owed+0.041
umbered+0.040
Neg logit contributions
 hotel-0.098
 city-0.098
 museum-0.095
 classroom-0.094
 talent-0.094
Token a
Token ID257
Feature activation-9.03e+00

Pos logit contributions
es+0.002
icked+0.001
 could+0.001
owed+0.001
iled+0.001
Neg logit contributions
 talent-0.002
 hotel-0.002
 city-0.002
 opera-0.002
 orchestra-0.002
Token surprise
Token ID5975
Feature activation+1.50e+00

Pos logit contributions
 former+0.128
reating+0.127
 airport+0.125
 apartment+0.124
 tant+0.123
Neg logit contributions
 could-0.164
 on-0.160
es-0.153
 with-0.148
 in-0.147
Token.
Token ID13
Feature activation+4.33e+00

Pos logit contributions
es+0.022
icked+0.020
owed+0.015
iled+0.015
bed+0.015
Neg logit contributions
 hotel-0.034
 opera-0.034
 talent-0.034
 city-0.033
 orchestra-0.032
Token I
Token ID314
Feature activation+1.26e+00

Pos logit contributions
es+0.064
icked+0.059
owed+0.048
led+0.045
bed+0.043
Neg logit contributions
 city-0.095
 talent-0.093
 hotel-0.093
 museum-0.093
 orchestra-0.092
Tokenâ
Token ID22940
Feature activation-2.14e+00

Pos logit contributions
es+0.022
icked+0.020
 could+0.017
owed+0.016
iled+0.015
Neg logit contributions
 hotel-0.025
 talent-0.025
 city-0.025
 opera-0.025
 orchestra-0.024
Token
Token ID26391
Feature activation-3.14e-01

Pos logit contributions
 talent+0.036
 opera+0.034
 city+0.034
 orchestra+0.034
 hotel+0.033
Neg logit contributions
es-0.046
icked-0.042
 could-0.035
bed-0.033
owed-0.033
Token
Token ID8151
Feature activation+4.77e+00

Pos logit contributions
 city+0.006
 classroom+0.006
 playground+0.006
 zoo+0.006
 hotel+0.006
Neg logit contributions
icked-0.005
es-0.005
led-0.004
owed-0.004
ched-0.004
Tokenll
Token ID297
Feature activation+5.82e-01

Pos logit contributions
es+0.071
icked+0.066
 could+0.049
bed+0.049
owed+0.049
Neg logit contributions
 hotel-0.100
 city-0.099
 talent-0.096
 opera-0.095
 playground-0.094
Token to
Token ID284
Feature activation-2.36e+00

Pos logit contributions
 opera+0.001
 city+0.001
 hotel+0.001
 talent+0.001
 zoo+0.001
Neg logit contributions
es-0.001
icked-0.001
owed-0.001
 could-0.001
iled-0.001
Token the
Token ID262
Feature activation-1.19e+01

Pos logit contributions
 tant+0.061
 talent+0.060
 orchestra+0.060
 hotel+0.059
 city+0.058
Neg logit contributions
es-0.022
icked-0.018
 they-0.016
 there-0.015
 on-0.015
Token park
Token ID3952
Feature activation+3.51e+00

Pos logit contributions
 orchestra+0.169
 tant+0.169
 talent+0.148
 alphabet+0.141
 ey+0.138
Neg logit contributions
 could-0.245
es-0.237
 there-0.233
 in-0.224
 on-0.224
Token that
Token ID326
Feature activation-1.39e+00

Pos logit contributions
es+0.049
icked+0.046
 could+0.033
owed+0.032
iled+0.031
Neg logit contributions
 hotel-0.083
 city-0.082
 talent-0.082
 opera-0.082
 airport-0.080
Token day
Token ID1110
Feature activation+3.37e+00

Pos logit contributions
 hotel+0.020
 city+0.020
 opera+0.019
 talent+0.019
 airport+0.018
Neg logit contributions
es-0.033
icked-0.032
owed-0.027
iled-0.026
 could-0.026
Token.
Token ID13
Feature activation+4.10e+00

Pos logit contributions
icked+0.054
es+0.054
owed+0.039
iled+0.037
ched+0.037
Neg logit contributions
 city-0.071
 hotel-0.071
 opera-0.070
 talent-0.070
 airport-0.069
Token They
Token ID1119
Feature activation+1.58e+00

Pos logit contributions
es+0.055
icked+0.050
 could+0.038
owed+0.036
iled+0.034
Neg logit contributions
 talent-0.098
 hotel-0.098
 city-0.097
 opera-0.096
 orchestra-0.094
Token cried
Token ID16896
Feature activation+1.93e+00

Pos logit contributions
es+0.021
icked+0.019
 could+0.016
owed+0.014
iled+0.013
Neg logit contributions
 talent-0.038
 hotel-0.038
 city-0.037
 opera-0.037
 orchestra-0.037
Token and
Token ID290
Feature activation+4.50e-01

Pos logit contributions
es+0.027
icked+0.025
 could+0.019
owed+0.018
iled+0.017
Neg logit contributions
 opera-0.044
 talent-0.044
 hotel-0.044
 city-0.044
 former-0.043
Token cried
Token ID16896
Feature activation+1.81e+00

Pos logit contributions
es+0.006
icked+0.006
owed+0.004
 could+0.004
iled+0.004
Neg logit contributions
 talent-0.010
 hotel-0.010
 city-0.010
 opera-0.010
 orchestra-0.010
Token until
Token ID1566
Feature activation+3.69e-01

Pos logit contributions
es+0.025
icked+0.023
 could+0.017
owed+0.017
iled+0.016
Neg logit contributions
 opera-0.041
 talent-0.041
 hotel-0.041
 city-0.040
 former-0.040
Token mom
Token ID1995
Feature activation+2.59e+00

Pos logit contributions
 orchestra+0.084
 opera+0.083
 hotel+0.083
 talent+0.081
 city+0.080
Neg logit contributions
es-0.133
 could-0.112
 on-0.110
icked-0.110
bed-0.109
Token.
Token ID13
Feature activation+3.13e+00

Pos logit contributions
icked+0.039
es+0.039
ched+0.028
 could+0.028
ed+0.027
Neg logit contributions
 city-0.055
 opera-0.055
 hotel-0.055
 talent-0.053
 airport-0.053
Token She
Token ID1375
Feature activation+1.86e+00

Pos logit contributions
es+0.047
icked+0.042
owed+0.032
ched+0.030
 could+0.030
Neg logit contributions
 city-0.071
 talent-0.069
 hotel-0.069
 classroom-0.068
 opera-0.068
Token told
Token ID1297
Feature activation+2.22e+00

Pos logit contributions
es+0.027
icked+0.024
owed+0.018
 could+0.018
iled+0.017
Neg logit contributions
 talent-0.043
 hotel-0.042
 city-0.042
 opera-0.042
 orchestra-0.041
Token her
Token ID607
Feature activation-2.80e+00

Pos logit contributions
es+0.030
icked+0.026
 could+0.020
owed+0.019
 they+0.019
Neg logit contributions
 hotel-0.053
 city-0.053
 talent-0.053
 former-0.052
 museum-0.051
Token mom
Token ID1995
Feature activation+3.77e+00

Pos logit contributions
 talent+0.044
 hotel+0.044
 city+0.044
 opera+0.043
 orchestra+0.042
Neg logit contributions
es-0.061
icked-0.057
 could-0.050
owed-0.047
iled-0.046
Token all
Token ID477
Feature activation+9.22e-02

Pos logit contributions
es+0.053
icked+0.050
 could+0.037
owed+0.036
iled+0.036
Neg logit contributions
 hotel-0.085
 talent-0.085
 city-0.085
 opera-0.085
 airport-0.083
Token about
Token ID546
Feature activation-2.99e-01

Pos logit contributions
es+0.001
icked+0.001
 could+0.001
owed+0.001
 they+0.000
Neg logit contributions
 hotel-0.003
 former-0.002
 city-0.002
 talent-0.002
 airport-0.002
Token her
Token ID607
Feature activation-6.96e+00

Pos logit contributions
 hotel+0.007
 city+0.007
 former+0.007
 talent+0.007
 orchestra+0.007
Neg logit contributions
es-0.004
icked-0.003
 could-0.003
 they-0.003
 on-0.002
Token adventure
Token ID8855
Feature activation+3.76e+00

Pos logit contributions
 hotel+0.089
 passenger+0.087
 former+0.087
 priest+0.087
 city+0.085
Neg logit contributions
es-0.156
 could-0.136
 on-0.134
icked-0.134
 they-0.132
Token with
Token ID351
Feature activation-5.58e-01

Pos logit contributions
icked+0.052
es+0.050
owed+0.034
iled+0.034
 could+0.033
Neg logit contributions
 opera-0.088
 city-0.087
 talent-0.087
 hotel-0.087
 airport-0.085
Token the
Token ID262
Feature activation-1.43e+01

Pos logit contributions
es+0.046
icked+0.042
 could+0.033
owed+0.032
iled+0.031
Neg logit contributions
 hotel-0.067
 talent-0.067
 city-0.067
 opera-0.066
 orchestra-0.064
Token tree
Token ID5509
Feature activation+3.91e+00

Pos logit contributions
 orchestra+0.241
 talent+0.239
 hotel+0.230
 opera+0.227
 former+0.224
Neg logit contributions
es-0.274
 could-0.251
icked-0.244
 on-0.230
 in-0.218
Token again
Token ID757
Feature activation+1.57e+00

Pos logit contributions
es+0.053
icked+0.050
 could+0.036
owed+0.035
iled+0.034
Neg logit contributions
 city-0.092
 hotel-0.092
 talent-0.091
 opera-0.091
 airport-0.089
Token.
Token ID13
Feature activation+3.59e+00

Pos logit contributions
icked+0.024
es+0.023
owed+0.017
ched+0.016
ed+0.015
Neg logit contributions
 city-0.036
 talent-0.035
 hotel-0.034
 opera-0.034
 former-0.034
Token His
Token ID2399
Feature activation-6.94e+00

Pos logit contributions
es+0.048
icked+0.042
owed+0.031
 could+0.030
iled+0.029
Neg logit contributions
 city-0.087
 talent-0.087
 hotel-0.087
 opera-0.085
 airport-0.083
Token dad
Token ID9955
Feature activation+4.36e+00

Pos logit contributions
 opera+0.120
 orchestra+0.118
 former+0.118
 hotel+0.113
 zoo+0.113
Neg logit contributions
es-0.125
icked-0.118
 could-0.114
 on-0.105
 they-0.101
Token warned
Token ID7728
Feature activation+4.28e+00

Pos logit contributions
es+0.063
icked+0.062
iled+0.045
owed+0.044
bed+0.043
Neg logit contributions
 hotel-0.091
 city-0.090
 opera-0.090
 airport-0.089
 talent-0.089
Token him
Token ID683
Feature activation+2.35e+00

Pos logit contributions
es+0.057
icked+0.052
 could+0.039
owed+0.037
iled+0.036
Neg logit contributions
 hotel-0.102
 talent-0.102
 opera-0.102
 city-0.102
 airport-0.098
Token against
Token ID1028
Feature activation+2.29e-01

Pos logit contributions
icked+0.032
es+0.032
owed+0.023
iled+0.023
oped+0.022
Neg logit contributions
 talent-0.051
 mistake-0.051
 opera-0.051
 hotel-0.050
 city-0.050
Token it
Token ID340
Feature activation+2.50e+00

Pos logit contributions
es+0.003
icked+0.003
 could+0.002
owed+0.002
iled+0.002
Neg logit contributions
 hotel-0.005
 talent-0.005
 city-0.005
 opera-0.005
 orchestra-0.005
Token,
Token ID11
Feature activation+2.25e+00

Pos logit contributions
es+0.032
icked+0.032
 could+0.022
owed+0.022
iled+0.021
Neg logit contributions
 hotel-0.058
 talent-0.058
 city-0.058
 opera-0.058
 mistake-0.056
Token wanted
Token ID2227
Feature activation+1.39e+00

Pos logit contributions
es+0.015
icked+0.014
owed+0.011
 could+0.011
iled+0.011
Neg logit contributions
 talent-0.014
 hotel-0.014
 city-0.014
 opera-0.014
 orchestra-0.013
Token a
Token ID257
Feature activation-7.97e+00

Pos logit contributions
es+0.012
icked+0.009
 could+0.007
 they+0.006
 on+0.005
Neg logit contributions
 orchestra-0.039
 hotel-0.039
 former-0.039
 city-0.039
 talent-0.038
Token watch
Token ID2342
Feature activation+2.58e+00

Pos logit contributions
 former+0.121
 orchestra+0.117
 stations+0.108
 angles+0.107
opl+0.105
Neg logit contributions
 on-0.138
 they-0.138
 could-0.136
es-0.134
 there-0.131
Token.
Token ID13
Feature activation+3.23e+00

Pos logit contributions
es+0.035
icked+0.034
iled+0.024
 could+0.024
owed+0.023
Neg logit contributions
 opera-0.061
 hotel-0.060
 city-0.060
 talent-0.060
 airport-0.059
Token The
Token ID383
Feature activation-9.70e+00

Pos logit contributions
es+0.049
icked+0.045
ched+0.032
iled+0.032
owed+0.031
Neg logit contributions
 city-0.076
 talent-0.074
 classroom-0.073
 hotel-0.073
 opera-0.073
Token watch
Token ID2342
Feature activation+4.17e+00

Pos logit contributions
 former+0.163
 hotel+0.147
 tant+0.143
 city+0.142
 talent+0.140
Neg logit contributions
es-0.189
 could-0.179
icked-0.177
 on-0.172
owed-0.167
Token was
Token ID373
Feature activation-8.99e-01

Pos logit contributions
es+0.060
icked+0.057
iled+0.042
 Remy+0.039
owed+0.039
Neg logit contributions
 opera-0.093
 hotel-0.093
 city-0.092
 talent-0.091
 airport-0.090
Token very
Token ID845
Feature activation-4.24e+00

Pos logit contributions
 hotel+0.018
 city+0.017
 talent+0.017
 orchestra+0.017
 former+0.017
Neg logit contributions
es-0.016
icked-0.015
 could-0.013
 on-0.012
owed-0.012
Token attractive
Token ID10966
Feature activation+7.13e-01

Pos logit contributions
 hotel+0.068
 city+0.068
 zoo+0.067
 orchestra+0.066
 airport+0.066
Neg logit contributions
icked-0.082
es-0.080
 could-0.075
owed-0.069
 on-0.069
Token and
Token ID290
Feature activation+6.83e-01

Pos logit contributions
icked+0.010
es+0.009
owed+0.007
ched+0.007
 could+0.006
Neg logit contributions
 opera-0.017
 hotel-0.017
 city-0.017
 talent-0.017
 airport-0.017
Token she
Token ID673
Feature activation+1.67e+00

Pos logit contributions
es+0.014
icked+0.013
owed+0.011
iled+0.010
 could+0.010
Neg logit contributions
 talent-0.012
 city-0.012
 hotel-0.012
 opera-0.012
 orchestra-0.011
Token in
Token ID287
Feature activation-1.31e+00

Pos logit contributions
es+0.066
icked+0.065
iled+0.047
owed+0.045
bed+0.044
Neg logit contributions
 talent-0.103
 opera-0.101
 hotel-0.101
 city-0.099
 mirror-0.095
Token the
Token ID262
Feature activation-9.33e+00

Pos logit contributions
 talent+0.033
 orchestra+0.032
 hotel+0.032
 former+0.032
 opera+0.032
Neg logit contributions
es-0.016
icked-0.012
 could-0.011
 on-0.010
 there-0.010
Token frame
Token ID5739
Feature activation+3.86e+00

Pos logit contributions
reating+0.133
 actor+0.130
 priest+0.128
 orchestra+0.128
 hotel+0.123
Neg logit contributions
 on-0.182
 in-0.173
 could-0.166
 with-0.164
es-0.157
Token.
Token ID13
Feature activation+3.52e+00

Pos logit contributions
es+0.047
icked+0.042
 could+0.030
owed+0.029
iled+0.028
Neg logit contributions
 talent-0.096
 hotel-0.096
 city-0.095
 opera-0.095
 orchestra-0.093
Token<|endoftext|>
Token ID50256
Feature activation+1.51e+00

Pos logit contributions
es+0.061
icked+0.053
owed+0.045
led+0.041
ched+0.041
Neg logit contributions
 city-0.073
 talent-0.070
 classroom-0.069
 museum-0.069
 hotel-0.069
TokenOnce
Token ID7454
Feature activation-2.71e+00

Pos logit contributions
icked+0.026
es+0.025
owed+0.023
ppers+0.020
iled+0.020
Neg logit contributions
 city-0.029
 hotel-0.029
 museum-0.028
 park-0.028
 zoo-0.028
Token upon
Token ID2402
Feature activation+4.54e-01

Pos logit contributions
 hotel+0.044
 city+0.043
 talent+0.042
 opera+0.041
 classroom+0.040
Neg logit contributions
es-0.058
icked-0.053
owed-0.045
iled-0.045
ched-0.044
Token a
Token ID257
Feature activation-4.70e+00

Pos logit contributions
es+0.008
icked+0.007
 could+0.006
owed+0.006
iled+0.006
Neg logit contributions
 talent-0.009
 hotel-0.009
 city-0.009
 opera-0.009
 airport-0.009
Token time
Token ID640
Feature activation+1.21e+00

Pos logit contributions
 talent+0.056
 hotel+0.056
 city+0.055
 opera+0.054
 orchestra+0.051
Neg logit contributions
es-0.120
icked-0.113
 could-0.099
owed-0.097
iled-0.095
Token,
Token ID11
Feature activation-4.69e-01

Pos logit contributions
es+0.018
icked+0.017
ched+0.014
owed+0.013
hot+0.013
Neg logit contributions
 hotel-0.025
 city-0.025
 museum-0.024
 talent-0.024
 opera-0.024
Token in
Token ID287
Feature activation-3.09e+00

Pos logit contributions
 city+0.011
 hotel+0.011
 opera+0.011
 museum+0.010
 talent+0.010
Neg logit contributions
es-0.007
icked-0.005
uts-0.004
owed-0.004
ppers-0.004
Token not
Token ID407
Feature activation-2.50e+00

Pos logit contributions
 hotel+0.063
 talent+0.063
 city+0.063
 opera+0.061
 orchestra+0.060
Neg logit contributions
es-0.056
icked-0.053
 could-0.043
owed-0.041
iled-0.040
Token yours
Token ID12431
Feature activation+2.26e+00

Pos logit contributions
 hotel+0.032
 city+0.031
 talent+0.030
 former+0.030
 airport+0.029
Neg logit contributions
es-0.061
icked-0.058
 could-0.052
owed-0.050
iled-0.049
Token!"
Token ID2474
Feature activation+2.67e+00

Pos logit contributions
es+0.036
icked+0.035
owed+0.027
hot+0.027
iled+0.026
Neg logit contributions
 hotel-0.045
 talent-0.045
 opera-0.045
 city-0.044
 bus-0.043
Token Ben
Token ID3932
Feature activation+3.36e+00

Pos logit contributions
es+0.037
icked+0.033
 could+0.025
owed+0.024
iled+0.023
Neg logit contributions
 talent-0.064
 hotel-0.063
 city-0.063
 opera-0.063
 orchestra-0.061
Token yelled
Token ID22760
Feature activation+2.92e+00

Pos logit contributions
es+0.052
icked+0.051
owed+0.038
iled+0.037
 could+0.036
Neg logit contributions
 talent-0.065
 opera-0.065
 orchestra-0.064
 hotel-0.064
 mistake-0.063
Token.
Token ID13
Feature activation+2.43e+00

Pos logit contributions
es+0.044
icked+0.041
 could+0.035
owed+0.032
ppers+0.030
Neg logit contributions
 opera-0.060
 talent-0.059
 mistake-0.058
 hotel-0.057
 orchestra-0.057
Token
Token ID198
Feature activation+3.27e-01

Pos logit contributions
es+0.036
icked+0.033
owed+0.028
 could+0.024
iled+0.024
Neg logit contributions
 talent-0.053
 hotel-0.052
 city-0.052
 opera-0.051
 orchestra-0.051
Token
Token ID198
Feature activation+7.24e-01

Pos logit contributions
es+0.004
icked+0.004
owed+0.003
 could+0.003
iled+0.003
Neg logit contributions
 talent-0.008
 hotel-0.008
 city-0.008
 opera-0.008
 orchestra-0.008
TokenThe
Token ID464
Feature activation-1.16e+01

Pos logit contributions
es+0.012
icked+0.011
 could+0.009
iled+0.009
owed+0.008
Neg logit contributions
 hotel-0.015
 talent-0.015
 city-0.015
 opera-0.015
 airport-0.015
Token man
Token ID582
Feature activation+4.96e+00

Pos logit contributions
 former+0.229
 apartment+0.189
 perspective+0.185
 city+0.185
 tant+0.180
Neg logit contributions
 on-0.191
es-0.175
 could-0.173
 there-0.172
 they-0.171
Token tried
Token ID3088
Feature activation+3.62e+00

Pos logit contributions
es+0.073
icked+0.068
owed+0.050
 could+0.050
iled+0.049
Neg logit contributions
 hotel-0.108
 opera-0.107
 city-0.106
 talent-0.106
 airport-0.104
Token.
Token ID13
Feature activation+3.26e+00

Pos logit contributions
icked+0.054
es+0.050
owed+0.041
ched+0.041
 could+0.041
Neg logit contributions
 opera-0.069
 mistake-0.065
 mirror-0.064
 hotel-0.064
 city-0.064
Token She
Token ID1375
Feature activation+1.20e+00

Pos logit contributions
es+0.048
icked+0.045
owed+0.039
ched+0.033
ppers+0.033
Neg logit contributions
 city-0.072
 talent-0.070
 hotel-0.070
 classroom-0.070
 mirror-0.070
Token was
Token ID373
Feature activation-2.30e+00

Pos logit contributions
es+0.018
icked+0.016
 could+0.012
owed+0.012
iled+0.011
Neg logit contributions
 talent-0.027
 hotel-0.027
 city-0.027
 opera-0.027
 orchestra-0.026
Token very
Token ID845
Feature activation-4.66e+00

Pos logit contributions
 hotel+0.046
 talent+0.045
 city+0.045
 opera+0.045
 orchestra+0.044
Neg logit contributions
es-0.041
icked-0.038
 could-0.031
owed-0.030
iled-0.029
Token troubled
Token ID17840
Feature activation+1.88e+00

Pos logit contributions
 hotel+0.076
 city+0.075
 talent+0.074
 opera+0.073
 airport+0.073
Neg logit contributions
es-0.100
icked-0.094
 could-0.081
owed-0.077
iled-0.077
Token.
Token ID13
Feature activation+2.97e+00

Pos logit contributions
icked+0.029
es+0.029
owed+0.023
ched+0.022
 could+0.021
Neg logit contributions
 opera-0.040
 city-0.039
 hotel-0.039
 talent-0.039
 mirror-0.038
Token She
Token ID1375
Feature activation+1.33e+00

Pos logit contributions
es+0.044
icked+0.041
owed+0.035
ched+0.030
ppers+0.029
Neg logit contributions
 city-0.067
 talent-0.065
 hotel-0.065
 classroom-0.064
 mirror-0.064
Token did
Token ID750
Feature activation+1.32e+00

Pos logit contributions
es+0.019
icked+0.017
 could+0.013
owed+0.012
iled+0.012
Neg logit contributions
 hotel-0.031
 talent-0.031
 city-0.031
 opera-0.031
 orchestra-0.030
Token not
Token ID407
Feature activation-1.93e+00

Pos logit contributions
es+0.017
icked+0.015
 could+0.011
owed+0.011
iled+0.010
Neg logit contributions
 hotel-0.033
 talent-0.032
 city-0.032
 opera-0.032
 orchestra-0.031
Token know
Token ID760
Feature activation+1.36e+00

Pos logit contributions
 hotel+0.035
 city+0.034
 talent+0.034
 opera+0.033
 former+0.033
Neg logit contributions
es-0.038
icked-0.035
 could-0.030
owed-0.029
iled-0.028
Token what
Token ID644
Feature activation-2.82e-01

Pos logit contributions
es+0.020
icked+0.019
 could+0.014
owed+0.014
iled+0.014
Neg logit contributions
 hotel-0.030
 opera-0.030
 city-0.030
 talent-0.030
 airport-0.029
Token that
Token ID326
Feature activation+3.75e-01

Pos logit contributions
es+0.026
icked+0.023
 could+0.016
owed+0.015
iled+0.014
Neg logit contributions
 talent-0.060
 hotel-0.060
 city-0.060
 opera-0.060
 orchestra-0.058
Token if
Token ID611
Feature activation+1.25e+00

Pos logit contributions
es+0.005
icked+0.004
 could+0.003
owed+0.003
iled+0.003
Neg logit contributions
 talent-0.009
 hotel-0.009
 city-0.009
 opera-0.009
 airport-0.009
Token he
Token ID339
Feature activation+1.37e+00

Pos logit contributions
es+0.012
icked+0.011
 could+0.007
owed+0.006
iled+0.006
Neg logit contributions
 talent-0.034
 hotel-0.034
 city-0.034
 opera-0.034
 orchestra-0.033
Token was
Token ID373
Feature activation-2.82e+00

Pos logit contributions
es+0.020
icked+0.018
iled+0.013
owed+0.013
bed+0.013
Neg logit contributions
 talent-0.030
 hotel-0.030
 city-0.030
 opera-0.030
 airport-0.029
Token ever
Token ID1683
Feature activation-2.83e+00

Pos logit contributions
 talent+0.050
 opera+0.049
 hotel+0.048
 city+0.048
 airport+0.046
Neg logit contributions
es-0.056
icked-0.052
owed-0.043
 could-0.043
iled-0.042
Token feeling
Token ID4203
Feature activation-1.94e+00

Pos logit contributions
 talent+0.055
 opera+0.054
 hotel+0.053
 city+0.053
 mistake+0.052
Neg logit contributions
es-0.052
icked-0.049
iled-0.037
owed-0.037
bed-0.036
Token miserable
Token ID22444
Feature activation+1.39e+00

Pos logit contributions
 talent+0.032
 hotel+0.032
 city+0.031
 opera+0.031
 orchestra+0.030
Neg logit contributions
es-0.041
icked-0.038
 could-0.032
owed-0.032
iled-0.031
Token again
Token ID757
Feature activation+2.24e+00

Pos logit contributions
es+0.018
icked+0.017
owed+0.012
iled+0.011
 could+0.011
Neg logit contributions
 hotel-0.034
 talent-0.033
 opera-0.033
 city-0.033
 airport-0.032
Token,
Token ID11
Feature activation+1.81e+00

Pos logit contributions
icked+0.033
es+0.031
owed+0.023
ched+0.021
iled+0.021
Neg logit contributions
 talent-0.052
 city-0.051
 hotel-0.050
 opera-0.050
 former-0.050
Token he
Token ID339
Feature activation+1.98e+00

Pos logit contributions
es+0.021
icked+0.019
owed+0.013
 could+0.012
iled+0.012
Neg logit contributions
 talent-0.047
 hotel-0.047
 city-0.047
 opera-0.046
 airport-0.045
Token could
Token ID714
Feature activation+3.45e-01

Pos logit contributions
es+0.027
icked+0.025
iled+0.018
owed+0.018
bed+0.017
Neg logit contributions
 talent-0.046
 hotel-0.044
 opera-0.044
 city-0.044
 memory-0.043
Tokenmy
Token ID1820
Feature activation+3.88e+00

Pos logit contributions
es+0.032
icked+0.031
 could+0.025
iled+0.025
bed+0.024
Neg logit contributions
 talent-0.021
 mistake-0.020
 opera-0.020
 mirror-0.020
 city-0.019
Token.
Token ID13
Feature activation+3.88e+00

Pos logit contributions
es+0.058
icked+0.058
 could+0.044
umbered+0.042
 Remy+0.042
Neg logit contributions
 mistake-0.077
 talent-0.076
 opera-0.074
 mirror-0.073
 hotel-0.072
Token "
Token ID366
Feature activation+3.41e-01

Pos logit contributions
es+0.069
icked+0.066
owed+0.055
led+0.049
ched+0.048
Neg logit contributions
 city-0.076
 playground-0.073
 talent-0.073
 classroom-0.072
 zoo-0.072
TokenLet
Token ID5756
Feature activation+2.49e+00

Pos logit contributions
es+0.004
icked+0.004
 could+0.003
iled+0.003
ched+0.003
Neg logit contributions
 hotel-0.009
 opera-0.008
 city-0.008
 talent-0.008
 airport-0.008
Token me
Token ID502
Feature activation+1.11e+00

Pos logit contributions
es+0.039
icked+0.036
owed+0.028
iled+0.026
 could+0.025
Neg logit contributions
 opera-0.055
 talent-0.055
 city-0.054
 hotel-0.054
 airport-0.053
Token try
Token ID1949
Feature activation+3.47e+00

Pos logit contributions
es+0.023
icked+0.022
 could+0.018
owed+0.018
iled+0.017
Neg logit contributions
 talent-0.018
 hotel-0.018
 city-0.018
 opera-0.018
 orchestra-0.017
Token,"
Token ID553
Feature activation+3.29e+00

Pos logit contributions
es+0.044
icked+0.042
owed+0.030
 could+0.030
ed+0.028
Neg logit contributions
 talent-0.085
 city-0.084
 hotel-0.084
 opera-0.084
 airport-0.081
Token said
Token ID531
Feature activation+2.96e+00

Pos logit contributions
es+0.056
icked+0.055
owed+0.042
iled+0.040
ed+0.038
Neg logit contributions
 talent-0.065
 city-0.062
 opera-0.061
 mirror-0.061
 mistake-0.061
Token Billy
Token ID15890
Feature activation+4.22e+00

Pos logit contributions
es+0.050
icked+0.045
owed+0.037
iled+0.036
 could+0.035
Neg logit contributions
 talent-0.059
 opera-0.059
 city-0.057
 hotel-0.057
 orchestra-0.056
Token.
Token ID13
Feature activation+4.23e+00

Pos logit contributions
es+0.062
icked+0.061
umbered+0.046
 could+0.044
 Remy+0.044
Neg logit contributions
 talent-0.082
 mistake-0.079
 mirror-0.078
 opera-0.077
 model-0.076
Token Billy
Token ID15890
Feature activation+3.54e+00

Pos logit contributions
es+0.077
icked+0.073
owed+0.060
ched+0.056
led+0.056
Neg logit contributions
 city-0.080
 playground-0.077
 zoo-0.076
 classroom-0.075
 former-0.074
TokenAmy
Token ID40797
Feature activation+3.38e+00

Pos logit contributions
es+0.015
icked+0.015
owed+0.012
ed+0.011
 could+0.011
Neg logit contributions
 city-0.016
 talent-0.016
 opera-0.016
 hotel-0.016
 orchestra-0.015
Token then
Token ID788
Feature activation+2.97e+00

Pos logit contributions
es+0.051
icked+0.048
owed+0.035
 could+0.033
iled+0.033
Neg logit contributions
 talent-0.074
 hotel-0.073
 opera-0.073
 city-0.072
 airport-0.071
Token wanted
Token ID2227
Feature activation+1.56e+00

Pos logit contributions
es+0.044
icked+0.041
owed+0.030
iled+0.029
 could+0.029
Neg logit contributions
 talent-0.066
 opera-0.066
 hotel-0.066
 city-0.065
 airport-0.064
Token to
Token ID284
Feature activation-1.97e+00

Pos logit contributions
es+0.013
icked+0.009
 could+0.007
 on+0.006
 they+0.005
Neg logit contributions
 former-0.045
 hotel-0.045
 city-0.045
 orchestra-0.045
 talent-0.043
Token be
Token ID307
Feature activation-3.69e+00

Pos logit contributions
 hotel+0.037
 city+0.036
 former+0.035
 airport+0.035
 tant+0.035
Neg logit contributions
es-0.034
icked-0.031
 could-0.029
 on-0.025
owed-0.025
Token even
Token ID772
Feature activation-4.76e+00

Pos logit contributions
 hotel+0.067
 city+0.066
 talent+0.066
 opera+0.064
 airport+0.063
Neg logit contributions
es-0.070
icked-0.065
 could-0.055
owed-0.052
iled-0.051
Token more
Token ID517
Feature activation-5.54e+00

Pos logit contributions
 hotel+0.081
 city+0.080
 talent+0.078
 opera+0.076
 airport+0.076
Neg logit contributions
es-0.097
icked-0.089
 could-0.079
owed-0.075
ed-0.072
Token helpful
Token ID7613
Feature activation-5.19e-01

Pos logit contributions
 hotel+0.080
 talent+0.080
 city+0.079
 opera+0.078
 orchestra+0.075
Neg logit contributions
es-0.127
icked-0.119
 could-0.104
owed-0.101
iled-0.099
Token.
Token ID13
Feature activation+3.62e+00

Pos logit contributions
 talent+0.013
 opera+0.013
 hotel+0.013
 city+0.012
 orchestra+0.012
Neg logit contributions
es-0.007
icked-0.006
owed-0.005
 could-0.004
ched-0.004
Token She
Token ID1375
Feature activation+1.94e+00

Pos logit contributions
es+0.045
icked+0.041
owed+0.028
 could+0.028
iled+0.027
Neg logit contributions
 city-0.090
 talent-0.090
 hotel-0.089
 opera-0.089
 orchestra-0.087
Token grabbed
Token ID13176
Feature activation+1.12e+00

Pos logit contributions
es+0.027
icked+0.025
owed+0.018
 could+0.018
iled+0.017
Neg logit contributions
 talent-0.045
 hotel-0.045
 city-0.044
 opera-0.044
 airport-0.043
Token new
Token ID649
Feature activation-3.49e-01

Pos logit contributions
 talent+0.023
 hotel+0.022
 opera+0.022
 city+0.022
 airport+0.020
Neg logit contributions
es-0.048
icked-0.046
owed-0.040
 could-0.039
iled-0.039
Token.
Token ID13
Feature activation+4.22e+00

Pos logit contributions
 talent+0.008
 hotel+0.008
 city+0.008
 opera+0.008
 airport+0.008
Neg logit contributions
es-0.005
icked-0.004
owed-0.003
 could-0.003
iled-0.003
Token Suddenly
Token ID24975
Feature activation+2.76e+00

Pos logit contributions
es+0.068
icked+0.061
owed+0.048
ched+0.043
iled+0.043
Neg logit contributions
 city-0.096
 hotel-0.093
 talent-0.092
 playground-0.091
 museum-0.090
Token there
Token ID612
Feature activation+4.03e+00

Pos logit contributions
es+0.037
icked+0.037
owed+0.029
iled+0.027
ched+0.026
Neg logit contributions
 hotel-0.064
 city-0.062
 opera-0.062
 airport-0.061
 talent-0.060
Token was
Token ID373
Feature activation-1.07e+00

Pos logit contributions
icked+0.070
es+0.068
iled+0.056
ppers+0.056
owed+0.052
Neg logit contributions
 hotel-0.079
 city-0.077
 airport-0.074
 opera-0.074
 beach-0.070
Token an
Token ID281
Feature activation-1.03e+01

Pos logit contributions
 orchestra+0.026
 talent+0.026
 hotel+0.026
 city+0.026
 opera+0.025
Neg logit contributions
es-0.013
icked-0.011
 could-0.009
 on-0.008
 they-0.008
Token emergency
Token ID6334
Feature activation+2.57e+00

Pos logit contributions
 former+0.116
 hotel+0.115
 talent+0.114
 city+0.108
 tant+0.107
Neg logit contributions
es-0.239
icked-0.235
 in-0.202
iled-0.202
 could-0.201
Token.
Token ID13
Feature activation+4.52e+00

Pos logit contributions
es+0.049
icked+0.047
 could+0.038
owed+0.038
iled+0.036
Neg logit contributions
 hotel-0.047
 city-0.046
 talent-0.046
 opera-0.046
 airport-0.044
Token The
Token ID383
Feature activation-1.11e+01

Pos logit contributions
es+0.081
icked+0.075
owed+0.064
ppers+0.057
ched+0.057
Neg logit contributions
 city-0.091
 hotel-0.088
 museum-0.085
 talent-0.084
 airport-0.084
Token family
Token ID1641
Feature activation+3.23e+00

Pos logit contributions
 talent+0.190
 orchestra+0.187
opl+0.182
 former+0.177
Ta+0.177
Neg logit contributions
 in-0.168
 on-0.161
 they-0.160
 could-0.159
 there-0.158
Token started
Token ID2067
Feature activation+2.46e+00

Pos logit contributions
es+0.045
icked+0.042
owed+0.031
iled+0.029
 could+0.028
Neg logit contributions
 hotel-0.074
 city-0.074
 opera-0.073
 talent-0.072
 airport-0.071
Token day
Token ID1110
Feature activation+1.74e+00

Pos logit contributions
 former+0.038
 talent+0.037
 orchestra+0.036
 hotel+0.036
 airport+0.035
Neg logit contributions
es-0.054
icked-0.051
 could-0.047
owed-0.045
iled-0.044
Token he
Token ID339
Feature activation+1.61e+00

Pos logit contributions
es+0.031
icked+0.027
ppers+0.024
owed+0.024
ched+0.023
Neg logit contributions
 city-0.032
 hotel-0.031
 sand-0.030
 museum-0.030
 beach-0.029
Token wanted
Token ID2227
Feature activation+2.03e+00

Pos logit contributions
es+0.025
icked+0.023
owed+0.018
 could+0.017
iled+0.017
Neg logit contributions
 hotel-0.036
 city-0.035
 talent-0.035
 opera-0.035
 airport-0.034
Token to
Token ID284
Feature activation-1.91e+00

Pos logit contributions
es+0.017
icked+0.014
 could+0.011
 on+0.008
 they+0.008
Neg logit contributions
 former-0.057
 orchestra-0.057
 talent-0.056
 hotel-0.056
 city-0.056
Token show
Token ID905
Feature activation+1.34e+00

Pos logit contributions
 talent+0.038
 former+0.037
 hotel+0.037
 tant+0.037
 orchestra+0.037
Neg logit contributions
es-0.030
icked-0.028
 could-0.025
 they-0.022
owed-0.022
Token his
Token ID465
Feature activation-7.89e+00

Pos logit contributions
es+0.018
icked+0.017
 could+0.013
owed+0.011
 on+0.011
Neg logit contributions
 city-0.031
 hotel-0.031
 former-0.031
 talent-0.031
 orchestra-0.030
Token Mom
Token ID11254
Feature activation+2.75e+00

Pos logit contributions
 former+0.146
 orchestra+0.146
reating+0.144
Ta+0.141
 tant+0.137
Neg logit contributions
es-0.114
 could-0.104
 they-0.104
icked-0.103
 on-0.098
Token how
Token ID703
Feature activation-2.03e+00

Pos logit contributions
icked+0.057
es+0.057
bed+0.046
iled+0.046
ched+0.046
Neg logit contributions
 opera-0.043
 hotel-0.043
 city-0.042
 talent-0.041
 bus-0.041
Token brave
Token ID14802
Feature activation+2.01e+00

Pos logit contributions
 former+0.042
 hotel+0.042
 opera+0.041
 talent+0.041
 orchestra+0.041
Neg logit contributions
es-0.032
icked-0.030
 could-0.027
 they-0.024
ed-0.024
Token he
Token ID339
Feature activation+1.14e+00

Pos logit contributions
es+0.026
icked+0.025
owed+0.019
iled+0.018
ched+0.017
Neg logit contributions
 opera-0.049
 hotel-0.048
 city-0.048
 talent-0.047
 bus-0.046
Token was
Token ID373
Feature activation-9.29e-01

Pos logit contributions
es+0.014
icked+0.014
iled+0.010
owed+0.010
bed+0.009
Neg logit contributions
 hotel-0.027
 city-0.027
 opera-0.026
 airport-0.026
 talent-0.026
Token,
Token ID11
Feature activation+7.02e-01

Pos logit contributions
icked+0.085
es+0.082
owed+0.059
ched+0.058
iled+0.054
Neg logit contributions
 city-0.136
 talent-0.133
 hotel-0.131
 opera-0.131
 zoo-0.131
Token going
Token ID1016
Feature activation+1.12e+00

Pos logit contributions
es+0.014
icked+0.013
owed+0.010
iled+0.010
ed+0.010
Neg logit contributions
 city-0.013
 hotel-0.013
 beach-0.013
 zoo-0.013
 playground-0.013
Token high
Token ID1029
Feature activation+1.91e-01

Pos logit contributions
es+0.018
icked+0.017
owed+0.013
iled+0.012
ched+0.012
Neg logit contributions
 city-0.025
 hotel-0.024
 talent-0.024
 zoo-0.024
 opera-0.024
Token up
Token ID510
Feature activation+6.06e-01

Pos logit contributions
icked+0.003
es+0.003
owed+0.002
iled+0.002
ched+0.002
Neg logit contributions
 city-0.004
 talent-0.004
 opera-0.004
 hotel-0.004
 beach-0.004
Token in
Token ID287
Feature activation-7.64e-01

Pos logit contributions
es+0.010
icked+0.010
owed+0.008
iled+0.007
ched+0.007
Neg logit contributions
 city-0.013
 hotel-0.012
 talent-0.012
 opera-0.012
 zoo-0.012
Token the
Token ID262
Feature activation-7.39e+00

Pos logit contributions
 talent+0.019
 orchestra+0.019
 former+0.019
 opera+0.019
 hotel+0.019
Neg logit contributions
es-0.009
icked-0.006
 could-0.006
 there-0.005
 on-0.005
Token air
Token ID1633
Feature activation+4.98e+00

Pos logit contributions
 talent+0.106
 orchestra+0.102
 priest+0.102
 mistake+0.101
 tant+0.099
Neg logit contributions
es-0.153
 could-0.149
icked-0.139
 on-0.136
 there-0.133
Token with
Token ID351
Feature activation-1.40e+00

Pos logit contributions
es+0.064
icked+0.059
 could+0.042
owed+0.041
iled+0.039
Neg logit contributions
 talent-0.122
 hotel-0.122
 city-0.121
 opera-0.120
 airport-0.117
Token every
Token ID790
Feature activation-5.97e+00

Pos logit contributions
 hotel+0.034
 airport+0.034
 opera+0.033
 orchestra+0.033
 talent+0.033
Neg logit contributions
es-0.018
icked-0.017
 could-0.013
 on-0.012
 there-0.012
Token jump
Token ID4391
Feature activation+4.48e+00

Pos logit contributions
 talent+0.082
 hotel+0.080
 opera+0.080
 city+0.080
 former+0.079
Neg logit contributions
es-0.136
icked-0.129
 could-0.118
owed-0.109
ed-0.108
Token.
Token ID13
Feature activation+3.79e+00

Pos logit contributions
es+0.060
icked+0.058
owed+0.045
iled+0.040
ppers+0.039
Neg logit contributions
 hotel-0.098
 opera-0.097
 city-0.096
 beach-0.095
 talent-0.095
Token reminded
Token ID14516
Feature activation+2.34e+00

Pos logit contributions
es+0.061
icked+0.056
owed+0.044
iled+0.042
bed+0.041
Neg logit contributions
 hotel-0.080
 opera-0.079
 airport-0.079
 city-0.079
 talent-0.078
Token him
Token ID683
Feature activation+1.92e+00

Pos logit contributions
es+0.035
icked+0.032
 could+0.025
owed+0.024
iled+0.023
Neg logit contributions
 opera-0.053
 talent-0.053
 hotel-0.052
 city-0.051
 airport-0.050
Token that
Token ID326
Feature activation+2.37e-01

Pos logit contributions
es+0.028
icked+0.026
iled+0.020
owed+0.020
oped+0.019
Neg logit contributions
 talent-0.044
 opera-0.042
 hotel-0.042
 city-0.040
 mistake-0.040
Token quiet
Token ID5897
Feature activation-1.08e-01

Pos logit contributions
es+0.003
icked+0.003
owed+0.002
iled+0.002
ed+0.002
Neg logit contributions
 hotel-0.006
 city-0.005
 opera-0.005
 talent-0.005
 airport-0.005
Token was
Token ID373
Feature activation-2.17e+00

Pos logit contributions
 hotel+0.002
 city+0.002
 talent+0.002
 opera+0.002
 airport+0.002
Neg logit contributions
es-0.002
icked-0.002
owed-0.002
 could-0.002
iled-0.002
Token an
Token ID281
Feature activation-1.04e+01

Pos logit contributions
 talent+0.040
 opera+0.039
 hotel+0.039
 city+0.038
 airport+0.037
Neg logit contributions
es-0.043
icked-0.039
owed-0.033
 could-0.031
iled-0.031
Token important
Token ID1593
Feature activation-9.03e+00

Pos logit contributions
 talent+0.127
 tant+0.122
 former+0.121
 hotel+0.120
 city+0.119
Neg logit contributions
es-0.223
icked-0.223
 could-0.196
iled-0.194
 in-0.194
Token part
Token ID636
Feature activation+1.84e+00

Pos logit contributions
 orchestra+0.123
 former+0.119
 city+0.117
 airport+0.116
 opera+0.114
Neg logit contributions
es-0.197
icked-0.179
 could-0.168
 on-0.162
iled-0.161
Token of
Token ID286
Feature activation-2.45e+00

Pos logit contributions
es+0.028
icked+0.026
owed+0.019
 could+0.019
iled+0.018
Neg logit contributions
 hotel-0.041
 talent-0.041
 city-0.041
 opera-0.041
 airport-0.039
Token being
Token ID852
Feature activation-3.87e+00

Pos logit contributions
 orchestra+0.057
 hotel+0.057
 talent+0.056
 city+0.056
 opera+0.055
Neg logit contributions
es-0.033
icked-0.028
 could-0.024
 they-0.021
 on-0.021
Token at
Token ID379
Feature activation-2.94e+00

Pos logit contributions
 talent+0.061
 opera+0.058
 hotel+0.057
 city+0.056
 orchestra+0.053
Neg logit contributions
es-0.085
icked-0.080
owed-0.068
 could-0.067
iled-0.065
Token,
Token ID11
Feature activation+3.17e+00

Pos logit contributions
es+0.033
icked+0.032
iled+0.025
o+0.025
owed+0.024
Neg logit contributions
 opera-0.053
 talent-0.051
 mirror-0.049
 new-0.048
 fashion-0.048
Token "
Token ID366
Feature activation-3.24e-01

Pos logit contributions
es+0.054
icked+0.051
owed+0.040
ched+0.038
iled+0.037
Neg logit contributions
 opera-0.063
 talent-0.063
 city-0.061
 orchestra-0.061
 airport-0.060
TokenI
Token ID40
Feature activation+3.21e-01

Pos logit contributions
 hotel+0.008
 talent+0.007
 city+0.007
 opera+0.007
 airport+0.007
Neg logit contributions
es-0.005
icked-0.004
 could-0.004
owed-0.003
iled-0.003
Token met
Token ID1138
Feature activation+3.14e+00

Pos logit contributions
es+0.006
icked+0.005
 could+0.004
owed+0.004
iled+0.004
Neg logit contributions
 talent-0.006
 hotel-0.006
 city-0.006
 opera-0.006
 orchestra-0.006
Token a
Token ID257
Feature activation-1.07e+01

Pos logit contributions
es+0.052
icked+0.047
 could+0.039
owed+0.037
ed+0.035
Neg logit contributions
 hotel-0.065
 talent-0.065
 city-0.064
 opera-0.063
 orchestra-0.062
Token new
Token ID649
Feature activation-1.20e+01

Pos logit contributions
 former+0.148
 ey+0.146
 tant+0.140
 apartment+0.132
 terminal+0.129
Neg logit contributions
 they-0.204
 could-0.202
 on-0.201
es-0.197
 there-0.196
Token friend
Token ID1545
Feature activation+3.55e+00

Pos logit contributions
 tant+0.176
 former+0.175
 ey+0.172
 hotel+0.169
 terminal+0.162
Neg logit contributions
es-0.233
 with-0.215
 on-0.212
 they-0.209
,-0.207
Token named
Token ID3706
Feature activation+8.64e-01

Pos logit contributions
icked+0.050
es+0.049
owed+0.036
ched+0.034
bed+0.034
Neg logit contributions
 opera-0.081
 city-0.079
 hotel-0.079
 talent-0.079
 zoo-0.077
Token Max
Token ID5436
Feature activation+4.44e+00

Pos logit contributions
es+0.012
icked+0.011
 could+0.008
owed+0.008
iled+0.008
Neg logit contributions
 talent-0.020
 hotel-0.020
 opera-0.020
 city-0.020
 orchestra-0.019
Token.
Token ID13
Feature activation+3.16e+00

Pos logit contributions
icked+0.070
es+0.067
owed+0.053
ched+0.052
iled+0.052
Neg logit contributions
 opera-0.091
 hotel-0.091
 city-0.089
 zoo-0.088
 airport-0.087
Token He
Token ID679
Feature activation+1.86e+00

Pos logit contributions
es+0.045
icked+0.043
owed+0.033
led+0.032
ed+0.031
Neg logit contributions
 city-0.071
 opera-0.070
 hotel-0.069
 orchestra-0.069
 talent-0.069
Token soup
Token ID17141
Feature activation+4.15e+00

Pos logit contributions
 orchestra+0.196
 opera+0.192
 talent+0.189
 city+0.185
 hotel+0.182
Neg logit contributions
es-0.242
icked-0.220
 could-0.208
 on-0.198
 in-0.187
Token.
Token ID13
Feature activation+2.71e+00

Pos logit contributions
icked+0.061
es+0.059
owed+0.048
ched+0.047
iled+0.046
Neg logit contributions
 hotel-0.088
 beach-0.084
 city-0.084
 opera-0.084
 talent-0.083
Token He
Token ID679
Feature activation+1.51e+00

Pos logit contributions
es+0.044
icked+0.039
owed+0.034
iled+0.030
led+0.030
Neg logit contributions
 city-0.057
 museum-0.057
 talent-0.056
 hotel-0.056
 classroom-0.055
Token looked
Token ID3114
Feature activation+1.46e+00

Pos logit contributions
es+0.024
icked+0.022
owed+0.017
iled+0.017
ed+0.016
Neg logit contributions
 talent-0.032
 hotel-0.031
 city-0.031
 opera-0.031
 airport-0.030
Token at
Token ID379
Feature activation+2.31e-01

Pos logit contributions
es+0.021
icked+0.018
owed+0.014
 could+0.013
iled+0.013
Neg logit contributions
 talent-0.034
 hotel-0.034
 opera-0.034
 city-0.033
 mirror-0.033
Token the
Token ID262
Feature activation-1.15e+01

Pos logit contributions
es+0.003
icked+0.002
 could+0.002
 on+0.001
ed+0.001
Neg logit contributions
 talent-0.006
 hotel-0.006
 former-0.006
 orchestra-0.006
 city-0.006
Token apple
Token ID17180
Feature activation+2.36e+00

Pos logit contributions
 orchestra+0.190
 opera+0.187
 talent+0.184
 city+0.180
 hotel+0.178
Neg logit contributions
es-0.235
icked-0.213
 could-0.202
 on-0.192
 in-0.181
Token piece
Token ID3704
Feature activation+3.18e+00

Pos logit contributions
icked+0.039
es+0.036
owed+0.031
iled+0.028
ched+0.028
Neg logit contributions
 hotel-0.046
 city-0.046
 beach-0.046
 zoo-0.045
 museum-0.045
Token.
Token ID13
Feature activation+2.87e+00

Pos logit contributions
es+0.046
icked+0.045
owed+0.034
iled+0.033
 could+0.031
Neg logit contributions
 hotel-0.066
 talent-0.065
 opera-0.065
 city-0.064
 mirror-0.063
Token He
Token ID679
Feature activation+1.59e+00

Pos logit contributions
es+0.046
icked+0.041
owed+0.036
led+0.032
iled+0.032
Neg logit contributions
 city-0.060
 museum-0.060
 talent-0.059
 classroom-0.058
 hotel-0.058
Token took
Token ID1718
Feature activation+2.06e-01

Pos logit contributions
es+0.025
icked+0.023
owed+0.018
iled+0.018
ed+0.017
Neg logit contributions
 talent-0.033
 hotel-0.033
 city-0.032
 opera-0.032
 airport-0.031
Token listen
Token ID6004
Feature activation+2.87e+00

Pos logit contributions
es+0.010
icked+0.009
 could+0.008
owed+0.007
ed+0.007
Neg logit contributions
 talent-0.014
 hotel-0.014
 city-0.014
 opera-0.013
 orchestra-0.013
Token.
Token ID13
Feature activation+4.22e+00

Pos logit contributions
es+0.038
icked+0.036
owed+0.025
 could+0.025
iled+0.024
Neg logit contributions
 talent-0.069
 opera-0.068
 hotel-0.067
 city-0.067
 orchestra-0.066
Token
Token ID198
Feature activation-2.26e-01

Pos logit contributions
es+0.062
icked+0.056
owed+0.043
 could+0.042
iled+0.039
Neg logit contributions
 city-0.096
 talent-0.096
 hotel-0.096
 opera-0.094
 former-0.092
Token
Token ID198
Feature activation+2.51e-01

Pos logit contributions
 talent+0.005
 hotel+0.005
 city+0.005
 opera+0.005
 orchestra+0.005
Neg logit contributions
es-0.003
icked-0.003
 could-0.002
owed-0.002
iled-0.002
TokenWhen
Token ID2215
Feature activation+1.96e+00

Pos logit contributions
es+0.004
icked+0.004
 could+0.003
iled+0.003
ched+0.003
Neg logit contributions
 hotel-0.005
 talent-0.005
 city-0.005
 opera-0.005
 orchestra-0.005
Token the
Token ID262
Feature activation-1.14e+01

Pos logit contributions
es+0.022
icked+0.019
 could+0.014
owed+0.013
iled+0.012
Neg logit contributions
 talent-0.051
 hotel-0.051
 city-0.051
 opera-0.051
 orchestra-0.050
Token naughty
Token ID45128
Feature activation-8.02e+00

Pos logit contributions
 former+0.153
 ey+0.148
 tant+0.145
 hotel+0.133
 apartment+0.129
Neg logit contributions
es-0.225
 on-0.224
 they-0.219
 could-0.212
 in-0.212
Token band
Token ID4097
Feature activation+3.29e+00

Pos logit contributions
 former+0.102
 talent+0.092
 tant+0.088
 hotel+0.087
 cockpit+0.086
Neg logit contributions
es-0.183
 could-0.161
icked-0.161
 they-0.158
 on-0.153
Token finished
Token ID5201
Feature activation+1.58e+00

Pos logit contributions
es+0.045
icked+0.040
 could+0.031
owed+0.030
iled+0.028
Neg logit contributions
 talent-0.078
 hotel-0.077
 city-0.077
 opera-0.076
 orchestra-0.075
Token their
Token ID511
Feature activation-1.11e+01

Pos logit contributions
es+0.019
icked+0.018
 could+0.013
owed+0.012
iled+0.011
Neg logit contributions
 talent-0.040
 hotel-0.040
 city-0.040
 opera-0.040
 airport-0.039
Token work
Token ID670
Feature activation+3.39e+00

Pos logit contributions
 priest+0.141
 ey+0.133
 hotel+0.131
reating+0.130
 passenger+0.129
Neg logit contributions
es-0.233
 on-0.209
 they-0.209
 could-0.206
 in-0.202
Token poured
Token ID19036
Feature activation+2.52e+00

Pos logit contributions
es+0.083
icked+0.079
iled+0.058
owed+0.058
hot+0.055
Neg logit contributions
 hotel-0.107
 city-0.105
 opera-0.103
 airport-0.100
 talent-0.100
Token down
Token ID866
Feature activation+2.58e+00

Pos logit contributions
es+0.046
icked+0.043
owed+0.035
 could+0.034
iled+0.034
Neg logit contributions
 hotel-0.047
 city-0.047
 talent-0.046
 opera-0.046
 airport-0.044
Token outside
Token ID2354
Feature activation+4.22e+00

Pos logit contributions
es+0.039
icked+0.036
 could+0.029
owed+0.028
iled+0.026
Neg logit contributions
 hotel-0.057
 talent-0.056
 city-0.056
 opera-0.056
 airport-0.054
Token.
Token ID13
Feature activation+3.80e+00

Pos logit contributions
es+0.057
icked+0.055
owed+0.039
 could+0.038
iled+0.037
Neg logit contributions
 hotel-0.100
 city-0.099
 opera-0.099
 talent-0.098
 airport-0.095
Token When
Token ID1649
Feature activation+1.44e+00

Pos logit contributions
es+0.057
icked+0.051
owed+0.038
iled+0.037
 could+0.036
Neg logit contributions
 hotel-0.087
 talent-0.086
 city-0.086
 opera-0.085
 former-0.083
Token the
Token ID262
Feature activation-1.07e+01

Pos logit contributions
es+0.017
icked+0.015
owed+0.011
 could+0.010
iled+0.010
Neg logit contributions
 hotel-0.038
 city-0.038
 talent-0.038
 opera-0.037
 airport-0.036
Token cup
Token ID6508
Feature activation+2.97e+00

Pos logit contributions
 former+0.150
 talent+0.146
 tant+0.144
 orchestra+0.143
 opera+0.129
Neg logit contributions
es-0.217
icked-0.217
 on-0.203
 they-0.202
 could-0.202
Tokencakes
Token ID37263
Feature activation+4.42e+00

Pos logit contributions
es+0.046
icked+0.043
owed+0.033
iled+0.032
 could+0.032
Neg logit contributions
 hotel-0.066
 city-0.064
 opera-0.064
 talent-0.063
 airport-0.062
Token were
Token ID547
Feature activation-2.13e+00

Pos logit contributions
es+0.076
icked+0.071
owed+0.056
iled+0.055
 could+0.050
Neg logit contributions
 hotel-0.091
 city-0.090
 opera-0.088
 airport-0.086
 talent-0.086
Token done
Token ID1760
Feature activation+2.00e+00

Pos logit contributions
 hotel+0.038
 city+0.037
 opera+0.037
 talent+0.037
 airport+0.036
Neg logit contributions
es-0.044
icked-0.039
owed-0.033
 could-0.033
iled-0.032
Token,
Token ID11
Feature activation+2.31e+00

Pos logit contributions
es+0.027
icked+0.027
owed+0.020
 could+0.020
ched+0.019
Neg logit contributions
 hotel-0.049
 opera-0.048
 city-0.047
 talent-0.046
 airport-0.045
Token side
Token ID1735
Feature activation+2.13e+00

Pos logit contributions
 talent+0.110
 opera+0.104
 hotel+0.104
 orchestra+0.102
 former+0.100
Neg logit contributions
es-0.171
icked-0.155
 could-0.143
iled-0.134
owed-0.132
Token,
Token ID11
Feature activation+1.83e+00

Pos logit contributions
es+0.028
icked+0.028
owed+0.019
ched+0.018
iled+0.018
Neg logit contributions
 hotel-0.052
 city-0.052
 opera-0.049
 talent-0.049
 airport-0.049
Token they
Token ID484
Feature activation+1.74e+00

Pos logit contributions
es+0.022
icked+0.020
 could+0.014
owed+0.014
iled+0.013
Neg logit contributions
 hotel-0.046
 city-0.046
 talent-0.046
 opera-0.045
 airport-0.044
Token said
Token ID531
Feature activation+1.67e+00

Pos logit contributions
es+0.025
icked+0.023
 could+0.018
owed+0.017
iled+0.016
Neg logit contributions
 talent-0.040
 hotel-0.040
 city-0.039
 opera-0.039
 orchestra-0.038
Token to
Token ID284
Feature activation+8.25e-01

Pos logit contributions
es+0.036
icked+0.033
owed+0.029
iled+0.029
 could+0.028
Neg logit contributions
 talent-0.026
 opera-0.025
 hotel-0.025
 city-0.024
 airport-0.023
Token the
Token ID262
Feature activation-1.22e+01

Pos logit contributions
es+0.009
icked+0.008
 could+0.007
 they+0.006
bed+0.006
Neg logit contributions
 talent-0.021
 hotel-0.020
 orchestra-0.020
 opera-0.020
 city-0.020
Token small
Token ID1402
Feature activation-1.13e+01

Pos logit contributions
 orchestra+0.174
 tant+0.173
 talent+0.168
 opera+0.166
 hotel+0.163
Neg logit contributions
 could-0.218
 on-0.201
 in-0.199
es-0.198
 there-0.196
Token boy
Token ID2933
Feature activation+3.94e+00

Pos logit contributions
 talent+0.161
 opera+0.156
 orchestra+0.152
 hotel+0.149
 former+0.148
Neg logit contributions
es-0.242
icked-0.217
 could-0.208
 on-0.195
iled-0.194
Token,
Token ID11
Feature activation+2.83e+00

Pos logit contributions
icked+0.049
es+0.048
ched+0.035
bed+0.034
led+0.034
Neg logit contributions
 hotel-0.088
 opera-0.088
 city-0.088
 talent-0.087
 zoo-0.086
Token "
Token ID366
Feature activation+6.12e-02

Pos logit contributions
es+0.046
icked+0.043
owed+0.034
ched+0.031
led+0.030
Neg logit contributions
 city-0.058
 opera-0.058
 talent-0.058
 hotel-0.057
 orchestra-0.056
TokenStay
Token ID25681
Feature activation-3.61e-01

Pos logit contributions
es+0.001
icked+0.001
 could+0.001
owed+0.001
iled+0.001
Neg logit contributions
 talent-0.001
 city-0.001
 hotel-0.001
 opera-0.001
 orchestra-0.001