TOP ACTIVATIONS
MAX = 0.247

thought for a moment before rep lying , " I think
show understanding , care and gent leness . <|endoftext|> Johnny was
thought for a moment before rep lying . " Yes I
cle vere r and cle vere r . Eventually the rabbit
You never know what dangers lur k around the corner .
and watched as the snake slit hered away . But he
running , but slower and gent ler ." The car was
one of the biggest and gent lest dinosaurs ever ," mom
in the park on a bree zy day . Mary was
. The next day they rep ainted the tank green ,
the shore , and the se ag ull s flying in
Gary lessons in kindness and gent leness . Gary was so
new number , louder and louder Pe aches â
. Suddenly , the worm slit hered away and the area
, it twisted around and slit hered away .
ignorant of the dangers that lur ked in the shadows .
The snake let go and slit hered away .
and soon noticed a narrow slit in the books he lf
shells . They hear the se ag ull s and the
he felt the healing power cour sing through his body .

MIN ACTIVATIONS
MIN = -0.221

. He showed Lily his toy gun . It was red
, Emma showed Lily her toy and they played together .
cooler . Mike showed his toy car to everyone who walked
Sally and showed her his toy pistol . Sally 's face
L ily handed her purse to Tim my , but
Everyday , she showed her purse to her friends . She
L ily showed the toy to her friend , Tim
Tim wanted to show his toy to his friends .
just buried his most prized possession a few inches underground .
the little girl find her toy . After searching for a
. Tom shows Mia his model car . He says ,
ily showed Sam her favorite toy , a magnet . "
It was his most prized possession , and he never let
so excited to show his toy trains to everyone . But
nice . He offers his toy train to Lily and Sam
She showed her model to her mom . "
Tim my gave her his toy makeup set to play with
So , Lily sold her toy to the woman .
and gave Tim my his toy back .
to show his friend his toy car . His friend liked

INTERVAL 0.130 - 0.247
CONTAINS 0.383%

Suddenly , he started to sne e ze . " A
made a loud and messy noise . " Hey
. The rocket makes another loud sound and lifts off .
the mill er heard loud noises outside . He knew it
who can help you when you need it . <|endoftext|> Once

INTERVAL 0.013 - 0.130
CONTAINS 37.578%

sad and went away . Later , Fred heard
very dark . The little bird was so high , it
, and he was trying to collect wood for his job
's hiding spot . <|endoftext|> John heard a noise . He
the sky 's voice . The wise man went

INTERVAL -0.104 - 0.013
CONTAINS 59.923%

shadow moved too ! Max thought it was funny . He
frustrated , when he spotted something in the bushes ! It
wet floor . He fell and hurt his knee . He
One day , a brave pirate went on a journey .
they both loved animals . One day , there was an

INTERVAL -0.221 - -0.104
CONTAINS 2.117%

a pron . " I do , I do
was a very happy seal who loved to hop around on
hug . She said : " It 's all right ,
mom my showed her a pair of sunglasses . They were
L ulu . " My tail is stuck !"
Token thought
Token ID1807
Feature activation-6.99e-02

Pos logit contributions
hon+0.021
 notice+0.018
 boom+0.017
 explode+0.017
 announcements+0.017
Neg logit contributions
 favourite-0.027
 possession-0.026
 favorite-0.025
 wrist-0.024
 purse-0.023
Token for
Token ID329
Feature activation-3.52e-02

Pos logit contributions
 possession+0.111
 favourite+0.108
 favorite+0.097
 purse+0.090
 wrist+0.085
Neg logit contributions
hon-0.138
 notice-0.118
 hon-0.117
 rep-0.116
 cal-0.115
Token a
Token ID257
Feature activation+1.73e-02

Pos logit contributions
 possession+0.074
 favourite+0.071
 favorite+0.066
 purse+0.064
 wrist+0.062
Neg logit contributions
hon-0.049
 notice-0.042
 rep-0.042
 hon-0.041
 cal-0.041
Token moment
Token ID2589
Feature activation-2.45e-02

Pos logit contributions
hon+0.028
 overcome+0.023
 cal+0.022
 announcements+0.022
 hon+0.021
Neg logit contributions
 favourite-0.034
 possession-0.034
 favorite-0.032
 purse-0.030
 brand-0.029
Token before
Token ID878
Feature activation+1.44e-02

Pos logit contributions
 possession+0.048
 favourite+0.047
 favorite+0.043
 purse+0.042
 wrist+0.040
Neg logit contributions
hon-0.038
 notice-0.032
 hon-0.031
 cal-0.031
 rep-0.031
Token rep
Token ID1128
Feature activation+2.47e-01

Pos logit contributions
hon+0.027
RO+0.023
 cal+0.022
rr+0.022
Hon+0.022
Neg logit contributions
 favourite-0.022
 possession-0.021
 purse-0.020
 brand-0.020
 favorite-0.019
Tokenlying
Token ID3157
Feature activation-5.73e-03

Pos logit contributions
hon+0.334
 notice+0.276
 hon+0.272
 rep+0.271
 cal+0.270
Neg logit contributions
 possession-0.532
 favourite-0.515
 favorite-0.479
 purse-0.468
 wrist-0.453
Token,
Token ID11
Feature activation-3.24e-02

Pos logit contributions
 possession+0.012
 favourite+0.012
 favorite+0.011
 purse+0.011
 wrist+0.010
Neg logit contributions
hon-0.008
 notice-0.006
 hon-0.006
 cal-0.006
 rep-0.006
Token "
Token ID366
Feature activation-1.03e-01

Pos logit contributions
 possession+0.031
 favourite+0.030
 favorite+0.026
 purse+0.023
 wrist+0.022
Neg logit contributions
hon-0.082
 notice-0.074
 cal-0.072
 hon-0.072
 rep-0.072
TokenI
Token ID40
Feature activation+4.57e-02

Pos logit contributions
 possession+0.172
 favourite+0.164
 favorite+0.149
 purse+0.144
 wrist+0.136
Neg logit contributions
hon-0.192
 notice-0.168
 rep-0.166
 hon-0.164
 cal-0.164
Token think
Token ID892
Feature activation-1.13e-02

Pos logit contributions
hon+0.073
 announcements+0.063
 louder+0.063
 boom+0.061
 thunder+0.061
Neg logit contributions
 favourite-0.085
 possession-0.084
 favorite-0.079
 favourites-0.071
 purse-0.071
Token show
Token ID905
Feature activation-2.26e-02

Pos logit contributions
hon+0.195
Jim+0.160
 announcements+0.157
 louder+0.155
 rep+0.154
Neg logit contributions
 favourite-0.226
 possession-0.220
 favorite-0.212
 purse-0.192
 favorites-0.190
Token understanding
Token ID4547
Feature activation-3.57e-03

Pos logit contributions
 possession+0.045
 favourite+0.044
 favorite+0.041
 purse+0.039
 wrist+0.038
Neg logit contributions
hon-0.034
 notice-0.029
 rep-0.028
 hon-0.028
 cal-0.028
Token,
Token ID11
Feature activation+8.05e-03

Pos logit contributions
 possession+0.007
 favourite+0.007
 favorite+0.006
 purse+0.006
 wrist+0.006
Neg logit contributions
hon-0.006
 notice-0.005
 rep-0.005
 hon-0.005
 cal-0.005
Token care
Token ID1337
Feature activation+3.59e-02

Pos logit contributions
hon+0.014
 notice+0.012
 rep+0.011
 hon+0.011
 oblig+0.011
Neg logit contributions
 possession-0.015
 favourite-0.014
 favorite-0.013
 purse-0.012
 wrist-0.012
Token and
Token ID290
Feature activation+2.06e-02

Pos logit contributions
hon+0.065
 notice+0.057
 rep+0.057
 hon+0.056
 cal+0.056
Neg logit contributions
 possession-0.060
 favourite-0.057
 favorite-0.052
 purse-0.051
 wrist-0.048
Token gent
Token ID25049
Feature activation+2.46e-01

Pos logit contributions
hon+0.032
 notice+0.026
 rep+0.026
 hon+0.026
 cal+0.026
Neg logit contributions
 possession-0.041
 favourite-0.039
 favorite-0.037
 purse-0.035
 wrist-0.034
Tokenleness
Token ID48795
Feature activation-2.22e-02

Pos logit contributions
hon+0.382
 slit+0.351
 thunder+0.342
 rep+0.341
 cal+0.338
Neg logit contributions
 possession-0.467
 favourite-0.399
 possessions-0.387
 favorite-0.365
attered-0.354
Token.
Token ID13
Feature activation+1.54e-02

Pos logit contributions
 possession+0.044
 favourite+0.042
 favorite+0.039
 purse+0.037
 wrist+0.036
Neg logit contributions
hon-0.035
 notice-0.029
 rep-0.029
 hon-0.028
 oblig-0.028
Token<|endoftext|>
Token ID50256
Feature activation+1.04e-03

Pos logit contributions
hon+0.029
 notice+0.026
 hon+0.025
 cal+0.025
 rep+0.025
Neg logit contributions
 possession-0.025
 favourite-0.024
 favorite-0.022
 purse-0.021
 wrist-0.020
TokenJohnny
Token ID44960
Feature activation+2.91e-02

Pos logit contributions
hon+0.002
 announcements+0.002
 louder+0.002
 notice+0.002
 hon+0.002
Neg logit contributions
 possession-0.001
 favourite-0.001
 favorite-0.001
robe-0.001
 purse-0.001
Token was
Token ID373
Feature activation-5.15e-02

Pos logit contributions
hon+0.056
 louder+0.050
 announcements+0.050
 notice+0.048
 oblig+0.048
Neg logit contributions
 possession-0.045
 favourite-0.043
 favorite-0.040
 purse-0.039
 wrist-0.037
Token thought
Token ID1807
Feature activation-7.55e-02

Pos logit contributions
hon+0.066
 notice+0.058
 announcements+0.057
 boom+0.056
 explode+0.055
Neg logit contributions
 favourite-0.071
 possession-0.071
 favorite-0.065
 wrist-0.061
 purse-0.060
Token for
Token ID329
Feature activation-4.24e-02

Pos logit contributions
 possession+0.099
 favourite+0.098
 favorite+0.086
 purse+0.075
 brand+0.072
Neg logit contributions
hon-0.169
 notice-0.151
 announcements-0.147
 hon-0.147
 rep-0.146
Token a
Token ID257
Feature activation+1.32e-02

Pos logit contributions
 possession+0.086
 favourite+0.083
 favorite+0.077
 purse+0.074
 wrist+0.072
Neg logit contributions
hon-0.064
 notice-0.053
 rep-0.052
 hon-0.052
 cal-0.052
Token moment
Token ID2589
Feature activation-3.29e-02

Pos logit contributions
hon+0.022
 announcements+0.018
 overcome+0.018
 cal+0.018
 hon+0.017
Neg logit contributions
 favourite-0.025
 possession-0.025
 favorite-0.023
 purse-0.021
 brand-0.021
Token before
Token ID878
Feature activation+6.33e-03

Pos logit contributions
 possession+0.059
 favourite+0.057
 favorite+0.053
 purse+0.050
 wrist+0.048
Neg logit contributions
hon-0.058
 notice-0.049
 cal-0.047
 hon-0.047
 announcements-0.047
Token rep
Token ID1128
Feature activation+2.46e-01

Pos logit contributions
hon+0.012
RO+0.010
rr+0.010
Hon+0.010
 cal+0.010
Neg logit contributions
 favourite-0.009
 possession-0.009
 brand-0.008
 favorite-0.008
 wallet-0.008
Tokenlying
Token ID3157
Feature activation-1.09e-02

Pos logit contributions
hon+0.331
 notice+0.274
 rep+0.270
 hon+0.269
 cal+0.267
Neg logit contributions
 possession-0.532
 favourite-0.514
 favorite-0.480
 purse-0.467
 wrist-0.452
Token.
Token ID13
Feature activation-2.80e-02

Pos logit contributions
 possession+0.022
 favourite+0.021
 favorite+0.020
 purse+0.019
 wrist+0.018
Neg logit contributions
hon-0.017
 notice-0.014
RO-0.014
 hon-0.014
 announcements-0.013
Token "
Token ID366
Feature activation-1.03e-01

Pos logit contributions
 possession+0.037
 favourite+0.036
 favorite+0.032
 purse+0.029
 wrist+0.028
Neg logit contributions
hon-0.061
 notice-0.055
 hon-0.054
 rep-0.053
 cal-0.053
TokenYes
Token ID5297
Feature activation+9.47e-02

Pos logit contributions
 possession+0.190
 favourite+0.181
 favorite+0.167
 purse+0.163
 wrist+0.154
Neg logit contributions
hon-0.173
 notice-0.149
 rep-0.147
 cal-0.145
 hon-0.145
Token I
Token ID314
Feature activation+1.97e-03

Pos logit contributions
hon+0.170
 announcements+0.147
 notice+0.143
 overcome+0.142
RO+0.142
Neg logit contributions
 favourite-0.170
 possession-0.165
 favorite-0.159
 purse-0.146
 brand-0.138
Token cle
Token ID1190
Feature activation+9.46e-02

Pos logit contributions
 possession+0.060
 favourite+0.059
 favorite+0.054
 purse+0.051
 brand+0.047
Neg logit contributions
hon-0.064
 rep-0.054
 notice-0.054
 oblig-0.053
 announcements-0.053
Tokenvere
Token ID4119
Feature activation+2.23e-01

Pos logit contributions
hon+0.161
 notice+0.145
 thunder+0.145
 hon+0.143
 cal+0.142
Neg logit contributions
 possession-0.166
 favourite-0.158
 favorite-0.139
 purse-0.135
 wrist-0.134
Tokenr
Token ID81
Feature activation+9.06e-03

Pos logit contributions
hon+0.282
 cal+0.246
 rep+0.240
 announcements+0.237
 hon+0.236
Neg logit contributions
 possession-0.502
 favourite-0.450
 purse-0.420
 favorite-0.419
 wrist-0.407
Token and
Token ID290
Feature activation-2.53e-02

Pos logit contributions
hon+0.016
 cal+0.014
RO+0.014
Run+0.014
 notice+0.014
Neg logit contributions
 possession-0.016
 favourite-0.015
 favorite-0.014
 purse-0.013
 wrist-0.012
Token cle
Token ID1190
Feature activation+1.27e-01

Pos logit contributions
 possession+0.050
 favourite+0.049
 favorite+0.045
 brand+0.043
 purse+0.042
Neg logit contributions
hon-0.042
 rep-0.031
rr-0.031
Jim-0.031
 notice-0.031
Tokenvere
Token ID4119
Feature activation+2.39e-01

Pos logit contributions
hon+0.198
 thunder+0.182
 notice+0.180
 rep+0.175
 cal+0.174
Neg logit contributions
 possession-0.235
 favourite-0.223
 favorite-0.198
 wrist-0.194
 purse-0.190
Tokenr
Token ID81
Feature activation+2.71e-02

Pos logit contributions
hon+0.318
 cal+0.285
 slit+0.276
 rep+0.274
 announcements+0.273
Neg logit contributions
 possession-0.522
 favourite-0.452
 purse-0.423
 favorite-0.419
 wrist-0.413
Token.
Token ID13
Feature activation-7.72e-03

Pos logit contributions
hon+0.048
Run+0.043
 cal+0.042
RO+0.042
 rep+0.041
Neg logit contributions
 possession-0.048
 favourite-0.046
 favorite-0.042
 possessions-0.037
 purse-0.037
Token Eventually
Token ID16178
Feature activation+8.44e-02

Pos logit contributions
 possession+0.011
 favourite+0.011
 favorite+0.009
 purse+0.009
 wrist+0.008
Neg logit contributions
hon-0.016
 notice-0.014
 hon-0.014
 rep-0.014
 cal-0.014
Token the
Token ID262
Feature activation+5.90e-02

Pos logit contributions
hon+0.181
rr+0.157
 announcements+0.147
RO+0.142
Hon+0.142
Neg logit contributions
 possession-0.111
 favourite-0.108
 purse-0.097
 microscope-0.089
 favorite-0.087
Token rabbit
Token ID22746
Feature activation-5.50e-03

Pos logit contributions
hon+0.121
 notice+0.106
 hon+0.104
 cal+0.103
 rep+0.103
Neg logit contributions
 possession-0.089
 favourite-0.087
 favorite-0.079
 purse-0.074
 wrist-0.069
Token You
Token ID921
Feature activation+4.74e-02

Pos logit contributions
 possession+0.024
 favourite+0.023
 favorite+0.021
 purse+0.020
 wrist+0.019
Neg logit contributions
hon-0.030
 notice-0.026
 rep-0.026
 hon-0.026
 cal-0.026
Token never
Token ID1239
Feature activation+6.60e-02

Pos logit contributions
hon+0.087
 louder+0.077
 rep+0.076
 announcements+0.076
 oblig+0.074
Neg logit contributions
 possession-0.073
 favourite-0.073
 favorite-0.068
 purse-0.064
 wallet-0.058
Token know
Token ID760
Feature activation-4.26e-02

Pos logit contributions
hon+0.103
 announcements+0.087
Jim+0.085
 oblig+0.083
 louder+0.082
Neg logit contributions
 possession-0.119
 favourite-0.113
 favorite-0.110
 purse-0.102
 wallet-0.100
Token what
Token ID644
Feature activation-9.70e-02

Pos logit contributions
 possession+0.063
 favourite+0.060
 favorite+0.054
 purse+0.051
 wrist+0.047
Neg logit contributions
hon-0.087
 notice-0.078
 oblig-0.076
 rep-0.076
 hon-0.075
Token dangers
Token ID16169
Feature activation+9.73e-02

Pos logit contributions
 possession+0.179
 favourite+0.172
 favorite+0.160
 purse+0.151
 wrist+0.143
Neg logit contributions
hon-0.164
 notice-0.141
 rep-0.139
 hon-0.138
 cal-0.137
Token lur
Token ID20605
Feature activation+2.37e-01

Pos logit contributions
hon+0.169
 rep+0.146
 oblig+0.145
 announcements+0.144
 cal+0.144
Neg logit contributions
 possession-0.160
 favourite-0.150
 favorite-0.139
 purse-0.133
robe-0.127
Tokenk
Token ID74
Feature activation+2.48e-02

Pos logit contributions
hon+0.403
 rep+0.368
 cal+0.362
 notice+0.352
 overcome+0.352
Neg logit contributions
 possession-0.410
 favourite-0.387
 favorite-0.362
 purse-0.339
attered-0.329
Token around
Token ID1088
Feature activation-4.07e-02

Pos logit contributions
hon+0.038
 rep+0.034
 slit+0.034
 cal+0.033
 oblig+0.033
Neg logit contributions
 possession-0.046
 favourite-0.044
 favorite-0.041
 purse-0.039
 wrist-0.038
Token the
Token ID262
Feature activation+3.96e-02

Pos logit contributions
 possession+0.079
 favourite+0.075
 favorite+0.069
 purse+0.067
 wrist+0.064
Neg logit contributions
hon-0.064
 rep-0.053
 cal-0.053
 hon-0.053
 oblig-0.053
Token corner
Token ID5228
Feature activation-1.18e-01

Pos logit contributions
hon+0.074
 notice+0.068
 cal+0.067
 hon+0.066
 rep+0.066
Neg logit contributions
 possession-0.062
 favourite-0.058
 favorite-0.053
 purse-0.051
 wrist-0.051
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
 possession+0.232
 favourite+0.222
 favorite+0.208
 purse+0.198
 wrist+0.193
Neg logit contributions
hon-0.184
 rep-0.153
 notice-0.153
 hon-0.152
 oblig-0.151
Token and
Token ID290
Feature activation-4.11e-02

Pos logit contributions
 possession+0.126
 favourite+0.120
 favorite+0.110
 purse+0.106
 wrist+0.100
Neg logit contributions
hon-0.127
 notice-0.110
 rep-0.109
 cal-0.108
 oblig-0.107
Token watched
Token ID7342
Feature activation+7.52e-02

Pos logit contributions
 possession+0.081
 favourite+0.078
 favorite+0.074
 purse+0.072
 wrist+0.069
Neg logit contributions
hon-0.063
rr-0.054
 oblig-0.052
 rep-0.050
 notice-0.049
Token as
Token ID355
Feature activation+3.58e-02

Pos logit contributions
hon+0.142
 announcements+0.121
rr+0.121
 notice+0.119
 oblig+0.117
Neg logit contributions
 favourite-0.116
 possession-0.111
 favorite-0.106
 wrist-0.093
 purse-0.091
Token the
Token ID262
Feature activation+7.16e-02

Pos logit contributions
hon+0.063
rr+0.058
 oblig+0.058
 announcements+0.056
 notice+0.054
Neg logit contributions
 possession-0.058
 favourite-0.054
 favorite-0.052
 attic-0.045
 purse-0.044
Token snake
Token ID17522
Feature activation+1.46e-02

Pos logit contributions
hon+0.135
 notice+0.118
 rep+0.116
 cal+0.115
 hon+0.114
Neg logit contributions
 possession-0.118
 favourite-0.114
 favorite-0.104
 purse-0.099
 wrist-0.093
Token slit
Token ID40724
Feature activation+2.35e-01

Pos logit contributions
hon+0.022
 oblig+0.019
rr+0.019
 rep+0.019
Jim+0.018
Neg logit contributions
 favourite-0.027
 favorite-0.026
 possession-0.025
 purse-0.023
 wrist-0.022
Tokenhered
Token ID6083
Feature activation+3.89e-02

Pos logit contributions
hon+0.342
 announcements+0.305
 cal+0.300
 rep+0.299
 thunder+0.297
Neg logit contributions
 favourite-0.436
 possession-0.436
 purse-0.404
 favorite-0.395
attered-0.383
Token away
Token ID1497
Feature activation-1.94e-02

Pos logit contributions
hon+0.077
 rep+0.073
 oblig+0.069
 cal+0.066
 announcements+0.066
Neg logit contributions
 possession-0.062
 favourite-0.058
 favorite-0.053
 purse-0.048
 item-0.045
Token.
Token ID13
Feature activation-9.75e-03

Pos logit contributions
 possession+0.030
 favourite+0.029
 favorite+0.027
attered+0.023
 purse+0.023
Neg logit contributions
hon-0.039
 oblig-0.034
Jim-0.034
rr-0.032
 announcements-0.032
Token But
Token ID887
Feature activation+1.34e-02

Pos logit contributions
 possession+0.015
 favourite+0.014
 favorite+0.013
 purse+0.012
 wrist+0.012
Neg logit contributions
hon-0.019
 notice-0.017
 rep-0.017
 hon-0.017
 cal-0.017
Token he
Token ID339
Feature activation+3.01e-02

Pos logit contributions
hon+0.021
 notice+0.018
 rep+0.018
 cal+0.017
 oblig+0.017
Neg logit contributions
 possession-0.026
 favourite-0.026
 favorite-0.024
 purse-0.023
 wrist-0.022
Token running
Token ID2491
Feature activation+6.41e-02

Pos logit contributions
 possession+0.090
 favourite+0.089
 favorite+0.083
 purse+0.077
 brand+0.074
Neg logit contributions
hon-0.075
 notice-0.062
 oblig-0.061
 cal-0.060
 announcements-0.060
Token,
Token ID11
Feature activation-5.35e-03

Pos logit contributions
hon+0.116
 rep+0.104
 oblig+0.104
 notice+0.100
 cal+0.099
Neg logit contributions
 possession-0.109
 favourite-0.106
 favorite-0.098
 purse-0.090
attered-0.085
Token but
Token ID475
Feature activation-3.68e-03

Pos logit contributions
 favourite+0.009
 possession+0.009
 favorite+0.009
 purse+0.008
 wrist+0.008
Neg logit contributions
hon-0.009
 oblig-0.008
 notice-0.008
 rep-0.008
 cal-0.008
Token slower
Token ID13611
Feature activation+1.27e-01

Pos logit contributions
 possession+0.007
 favourite+0.007
 favorite+0.006
 purse+0.006
attered+0.006
Neg logit contributions
hon-0.005
 notice-0.005
 rep-0.005
 hon-0.005
 cal-0.005
Token and
Token ID290
Feature activation+5.92e-03

Pos logit contributions
hon+0.209
 oblig+0.171
RO+0.170
 cal+0.165
 notice+0.165
Neg logit contributions
 possession-0.254
 favourite-0.236
 favorite-0.221
 wrist-0.211
 purse-0.207
Token gent
Token ID25049
Feature activation+2.34e-01

Pos logit contributions
hon+0.009
 oblig+0.008
 rep+0.007
 notice+0.007
 announcements+0.007
Neg logit contributions
 possession-0.012
 favourite-0.011
 favorite-0.011
 purse-0.010
 wrist-0.010
Tokenler
Token ID1754
Feature activation+1.97e-02

Pos logit contributions
hon+0.340
 thunder+0.320
 cal+0.319
 slit+0.313
 overcome+0.310
Neg logit contributions
 possession-0.452
 favourite-0.389
 possessions-0.372
 favorite-0.357
attered-0.357
Token."
Token ID526
Feature activation+3.23e-02

Pos logit contributions
hon+0.031
 rep+0.025
Jim+0.025
 announcements+0.025
 notice+0.025
Neg logit contributions
 possession-0.038
 favourite-0.036
 favorite-0.034
robe-0.032
 purse-0.031
Token The
Token ID383
Feature activation+8.89e-03

Pos logit contributions
hon+0.065
 announcements+0.058
 notice+0.057
 boom+0.057
 hon+0.057
Neg logit contributions
 possession-0.047
 favourite-0.046
 favorite-0.041
 purse-0.040
 wrist-0.039
Token car
Token ID1097
Feature activation-1.91e-02

Pos logit contributions
hon+0.016
 notice+0.014
 rep+0.013
 hon+0.013
 cal+0.013
Neg logit contributions
 possession-0.015
 favourite-0.015
 favorite-0.014
 purse-0.013
 wrist-0.013
Token was
Token ID373
Feature activation-1.15e-02

Pos logit contributions
 favourite+0.037
 possession+0.035
 favorite+0.035
 purse+0.031
 wrist+0.030
Neg logit contributions
hon-0.030
 notice-0.027
 boom-0.025
 oblig-0.025
 rep-0.025
Token one
Token ID530
Feature activation-2.75e-02

Pos logit contributions
 possession+0.010
 favourite+0.009
 favorite+0.009
 purse+0.008
 wrist+0.008
Neg logit contributions
hon-0.008
 notice-0.007
 rep-0.007
 cal-0.007
 hon-0.007
Token of
Token ID286
Feature activation+5.67e-02

Pos logit contributions
 possession+0.052
 favourite+0.050
 favorite+0.046
 purse+0.044
 wrist+0.043
Neg logit contributions
hon-0.045
 notice-0.038
 rep-0.038
 cal-0.037
 hon-0.037
Token the
Token ID262
Feature activation+4.82e-02

Pos logit contributions
hon+0.082
 notice+0.069
 rep+0.067
 cal+0.067
 hon+0.066
Neg logit contributions
 possession-0.118
 favourite-0.113
 favorite-0.105
 purse-0.101
 wrist-0.098
Token biggest
Token ID4094
Feature activation-8.91e-03

Pos logit contributions
hon+0.090
 notice+0.076
 rep+0.074
 cal+0.074
 oblig+0.074
Neg logit contributions
 possession-0.080
 favourite-0.080
 favorite-0.074
 purse-0.069
 wrist-0.065
Token and
Token ID290
Feature activation+1.93e-02

Pos logit contributions
 possession+0.016
 favourite+0.015
 favorite+0.014
 purse+0.013
 wrist+0.013
Neg logit contributions
hon-0.016
 notice-0.013
 cal-0.013
 overcome-0.013
 rep-0.013
Token gent
Token ID25049
Feature activation+2.34e-01

Pos logit contributions
hon+0.035
 notice+0.031
 rep+0.030
 overcome+0.029
 oblig+0.029
Neg logit contributions
 possession-0.033
 favourite-0.032
 favorite-0.030
 purse-0.027
 brand-0.026
Tokenlest
Token ID32712
Feature activation-1.45e-02

Pos logit contributions
hon+0.316
 overcome+0.300
 cal+0.300
 slit+0.297
 thunder+0.291
Neg logit contributions
 possession-0.490
 favourite-0.428
 possessions-0.403
 favorite-0.398
 item-0.386
Token dinosaurs
Token ID27199
Feature activation+2.41e-02

Pos logit contributions
 possession+0.027
 favourite+0.026
 favorite+0.024
 purse+0.023
 wrist+0.022
Neg logit contributions
hon-0.024
 notice-0.021
 rep-0.020
 cal-0.020
 overcome-0.020
Token ever
Token ID1683
Feature activation+1.18e-01

Pos logit contributions
hon+0.035
 rep+0.029
 cal+0.029
 notice+0.029
 announcements+0.028
Neg logit contributions
 possession-0.049
 favourite-0.048
 favorite-0.045
 purse-0.042
 wrist-0.041
Token,"
Token ID553
Feature activation+7.13e-02

Pos logit contributions
hon+0.203
Jim+0.177
 oblig+0.173
Hon+0.173
 slit+0.172
Neg logit contributions
 possession-0.210
 favourite-0.198
 favorite-0.197
 favorites-0.168
 possessions-0.166
Token mom
Token ID1995
Feature activation+4.73e-02

Pos logit contributions
hon+0.115
 notice+0.101
 cal+0.097
 overcome+0.095
 announcements+0.095
Neg logit contributions
 possession-0.133
 favourite-0.129
 favorite-0.121
 purse-0.120
 wrist-0.111
Token in
Token ID287
Feature activation-1.92e-02

Pos logit contributions
hon+0.040
 cal+0.035
 notice+0.034
 rep+0.034
 hon+0.034
Neg logit contributions
 possession-0.027
 favourite-0.027
 favorite-0.024
 purse-0.022
 wrist-0.021
Token the
Token ID262
Feature activation+9.01e-03

Pos logit contributions
 possession+0.048
 favourite+0.047
 favorite+0.044
 purse+0.043
attered+0.042
Neg logit contributions
hon-0.018
 notice-0.015
 rep-0.015
 hon-0.014
 cal-0.014
Token park
Token ID3952
Feature activation-1.88e-02

Pos logit contributions
hon+0.017
 notice+0.015
 rep+0.015
 hon+0.015
 cal+0.015
Neg logit contributions
 possession-0.015
 favourite-0.014
 favorite-0.013
 purse-0.012
 wrist-0.012
Token on
Token ID319
Feature activation-6.35e-03

Pos logit contributions
 possession+0.039
 favourite+0.038
 favorite+0.035
 purse+0.034
 wrist+0.033
Neg logit contributions
hon-0.028
 cal-0.023
 notice-0.023
 hon-0.022
 rep-0.022
Token a
Token ID257
Feature activation+2.73e-02

Pos logit contributions
 possession+0.014
 favourite+0.014
 favorite+0.013
 purse+0.012
 wrist+0.012
Neg logit contributions
hon-0.008
 notice-0.007
 hon-0.007
 cal-0.007
 rep-0.007
Token bree
Token ID20780
Feature activation+2.33e-01

Pos logit contributions
hon+0.049
 rep+0.042
 notice+0.041
 cal+0.041
 oblig+0.041
Neg logit contributions
 possession-0.048
 favourite-0.047
 favorite-0.043
 purse-0.041
 wrist-0.038
Tokenzy
Token ID7357
Feature activation+1.05e-02

Pos logit contributions
hon+0.383
 notice+0.327
 rep+0.323
 cal+0.323
 hon+0.318
Neg logit contributions
 possession-0.437
 favourite-0.420
 favorite-0.387
 purse-0.375
 wrist-0.362
Token day
Token ID1110
Feature activation+1.24e-02

Pos logit contributions
hon+0.019
 cal+0.017
 notice+0.016
 oblig+0.016
 announcements+0.016
Neg logit contributions
 possession-0.018
 favourite-0.018
 favorite-0.016
 purse-0.016
 wrist-0.015
Token.
Token ID13
Feature activation-5.55e-02

Pos logit contributions
hon+0.021
 cal+0.018
 hon+0.017
 oblig+0.017
 slit+0.017
Neg logit contributions
 favourite-0.023
 possession-0.023
 favorite-0.021
 purse-0.020
 wrist-0.019
Token Mary
Token ID5335
Feature activation+2.72e-02

Pos logit contributions
 possession+0.123
 favourite+0.115
 favorite+0.107
 purse+0.106
 wrist+0.103
Neg logit contributions
hon-0.073
 notice-0.064
 rep-0.060
 hon-0.059
 cal-0.058
Token was
Token ID373
Feature activation-4.49e-02

Pos logit contributions
hon+0.045
 notice+0.038
 hon+0.038
 rep+0.038
 cal+0.037
Neg logit contributions
 possession-0.051
 favourite-0.048
 favorite-0.045
 purse-0.043
 wrist-0.041
Token.
Token ID13
Feature activation-4.49e-03

Pos logit contributions
hon+0.034
RO+0.030
 notice+0.030
Run+0.029
 slit+0.029
Neg logit contributions
 favourite-0.030
 possession-0.029
 favorite-0.027
 brand-0.023
 item-0.022
Token The
Token ID383
Feature activation-2.69e-03

Pos logit contributions
 possession+0.008
 favourite+0.007
 favorite+0.007
 purse+0.007
 wrist+0.006
Neg logit contributions
hon-0.008
 notice-0.007
 rep-0.007
 hon-0.007
 cal-0.007
Token next
Token ID1306
Feature activation+7.16e-02

Pos logit contributions
 possession+0.005
 favourite+0.004
 purse+0.004
 favorite+0.004
 wrist+0.004
Neg logit contributions
hon-0.004
 hon-0.004
 rep-0.004
 notice-0.004
 cal-0.004
Token day
Token ID1110
Feature activation+1.63e-02

Pos logit contributions
hon+0.153
 announcements+0.139
 notice+0.136
 overcome+0.134
 cal+0.132
Neg logit contributions
 favourite-0.102
 possession-0.101
 favorite-0.094
 wallet-0.076
 purse-0.076
Token they
Token ID484
Feature activation+6.62e-02

Pos logit contributions
hon+0.029
rr+0.024
 oblig+0.024
 announcements+0.024
 boom+0.023
Neg logit contributions
 favourite-0.029
 possession-0.027
 favorite-0.026
 purse-0.024
 wallet-0.022
Token rep
Token ID1128
Feature activation+2.33e-01

Pos logit contributions
hon+0.120
 announcements+0.098
 rep+0.097
 louder+0.097
 oblig+0.097
Neg logit contributions
 favourite-0.106
 possession-0.104
 favorite-0.099
 purse-0.091
 favourites-0.087
Tokenainted
Token ID14215
Feature activation+1.57e-02

Pos logit contributions
hon+0.394
 notice+0.340
 rep+0.335
 hon+0.333
 cal+0.332
Neg logit contributions
 possession-0.427
 favourite-0.410
 favorite-0.377
 purse-0.363
 wrist-0.348
Token the
Token ID262
Feature activation+1.70e-02

Pos logit contributions
hon+0.028
 oblig+0.023
rr+0.022
RO+0.022
 cal+0.022
Neg logit contributions
 possession-0.028
 favourite-0.027
 favorite-0.025
 purse-0.024
 wrist-0.023
Token tank
Token ID6873
Feature activation-4.72e-02

Pos logit contributions
hon+0.031
 notice+0.026
 cal+0.025
 oblig+0.025
RO+0.024
Neg logit contributions
 favourite-0.030
 possession-0.029
 favorite-0.028
 purse-0.025
 wallet-0.025
Token green
Token ID4077
Feature activation-4.97e-02

Pos logit contributions
 possession+0.079
 favourite+0.078
 favorite+0.072
 purse+0.067
 brand+0.063
Neg logit contributions
hon-0.087
 announcements-0.073
 oblig-0.072
RO-0.072
 rep-0.071
Token,
Token ID11
Feature activation-1.70e-02

Pos logit contributions
 possession+0.090
 favourite+0.088
 favorite+0.081
 purse+0.076
 wrist+0.072
Neg logit contributions
hon-0.085
 notice-0.074
 cal-0.072
 oblig-0.072
 rep-0.071
Token the
Token ID262
Feature activation+4.49e-02

Pos logit contributions
hon+0.030
 oblig+0.024
 rep+0.024
 notice+0.024
 cal+0.023
Neg logit contributions
 possession-0.042
 favourite-0.042
 favorite-0.039
 purse-0.037
 wrist-0.036
Token shore
Token ID15191
Feature activation+3.92e-02

Pos logit contributions
hon+0.086
 rep+0.075
 notice+0.074
 oblig+0.073
 cal+0.073
Neg logit contributions
 possession-0.072
 favourite-0.070
 favorite-0.065
 purse-0.061
 wrist-0.059
Token,
Token ID11
Feature activation+1.05e-02

Pos logit contributions
hon+0.070
 oblig+0.061
RO+0.060
 notice+0.060
 cal+0.059
Neg logit contributions
 possession-0.064
 favourite-0.063
 favorite-0.060
 purse-0.056
 wrist-0.056
Token and
Token ID290
Feature activation+2.17e-02

Pos logit contributions
hon+0.017
 oblig+0.014
 notice+0.014
 rep+0.014
 cal+0.014
Neg logit contributions
 possession-0.019
 favourite-0.019
 favorite-0.018
 purse-0.017
 wrist-0.017
Token the
Token ID262
Feature activation+6.75e-02

Pos logit contributions
hon+0.031
 oblig+0.025
 rep+0.025
 notice+0.024
 cal+0.024
Neg logit contributions
 possession-0.045
 favourite-0.044
 favorite-0.042
 purse-0.039
 wrist-0.038
Token se
Token ID384
Feature activation+2.33e-01

Pos logit contributions
hon+0.120
 oblig+0.101
 notice+0.099
 overcome+0.098
 rep+0.097
Neg logit contributions
 favourite-0.118
 possession-0.117
 favorite-0.111
 purse-0.104
 wallet-0.099
Tokenag
Token ID363
Feature activation+1.18e-01

Pos logit contributions
 rep+0.370
hon+0.335
 cal+0.330
 thunder+0.329
 notice+0.327
Neg logit contributions
 possession-0.444
 favourite-0.404
 favorite-0.388
attered-0.365
shirt-0.355
Tokenull
Token ID724
Feature activation+1.00e-01

Pos logit contributions
hon+0.115
 cal+0.097
 rep+0.094
 notice+0.092
 oblig+0.086
Neg logit contributions
 possession-0.298
 favourite-0.285
 favorite-0.271
 purse-0.254
attered-0.252
Tokens
Token ID82
Feature activation-3.80e-02

Pos logit contributions
hon+0.213
 oblig+0.202
 notice+0.198
 cal+0.198
 rep+0.197
Neg logit contributions
 favourite-0.124
 possession-0.118
 favorite-0.114
 purse-0.096
attered-0.095
Token flying
Token ID7348
Feature activation+6.02e-02

Pos logit contributions
 favourite+0.060
 favorite+0.056
 possession+0.054
 purse+0.049
 wrist+0.047
Neg logit contributions
hon-0.072
 oblig-0.066
 cal-0.062
rr-0.061
 announcements-0.061
Token in
Token ID287
Feature activation+2.82e-02

Pos logit contributions
hon+0.126
 oblig+0.116
 rep+0.112
 notice+0.110
 announcements+0.107
Neg logit contributions
 possession-0.087
 favourite-0.086
 favorite-0.082
attered-0.068
 purse-0.065
Token Gary
Token ID10936
Feature activation+1.44e-02

Pos logit contributions
 favourite+0.009
 possession+0.009
 favorite+0.008
 favorites+0.007
 favourites+0.007
Neg logit contributions
hon-0.009
 rep-0.007
 slit-0.007
 notice-0.007
RO-0.007
Token lessons
Token ID11658
Feature activation+7.41e-03

Pos logit contributions
hon+0.029
 notice+0.025
 rep+0.025
 hon+0.025
 cal+0.024
Neg logit contributions
 possession-0.022
 favourite-0.021
 favorite-0.020
 purse-0.018
 wrist-0.017
Token in
Token ID287
Feature activation-1.80e-03

Pos logit contributions
hon+0.012
 notice+0.010
 rep+0.010
 cal+0.009
 oblig+0.009
Neg logit contributions
 possession-0.015
 favourite-0.014
 favorite-0.013
 purse-0.012
 wrist-0.012
Token kindness
Token ID23887
Feature activation+1.67e-02

Pos logit contributions
 possession+0.004
 favourite+0.004
 favorite+0.003
 purse+0.003
 wrist+0.003
Neg logit contributions
hon-0.003
 rep-0.002
 cal-0.002
 hon-0.002
 notice-0.002
Token and
Token ID290
Feature activation-9.32e-03

Pos logit contributions
hon+0.027
 notice+0.022
 rep+0.022
 oblig+0.022
 hon+0.022
Neg logit contributions
 possession-0.033
 favourite-0.031
 favorite-0.029
 purse-0.027
 wrist-0.027
Token gent
Token ID25049
Feature activation+2.32e-01

Pos logit contributions
 possession+0.017
 favourite+0.017
 favorite+0.016
 purse+0.014
 wrist+0.014
Neg logit contributions
hon-0.016
 notice-0.013
 rep-0.013
 oblig-0.013
 cal-0.013
Tokenleness
Token ID48795
Feature activation-2.83e-02

Pos logit contributions
hon+0.363
 cal+0.350
 thunder+0.349
 rep+0.342
 slit+0.341
Neg logit contributions
 possession-0.427
 possessions-0.360
 favourite-0.349
attered-0.331
 favorite-0.321
Token.
Token ID13
Feature activation-1.03e-02

Pos logit contributions
 possession+0.056
 favourite+0.054
 favorite+0.051
 purse+0.047
 wrist+0.046
Neg logit contributions
hon-0.044
 notice-0.038
 rep-0.036
 oblig-0.036
 cal-0.035
Token Gary
Token ID10936
Feature activation+5.90e-02

Pos logit contributions
 possession+0.019
 favourite+0.018
 favorite+0.017
 purse+0.016
 wrist+0.016
Neg logit contributions
hon-0.017
 notice-0.015
 rep-0.014
 hon-0.014
 cal-0.014
Token was
Token ID373
Feature activation-1.32e-02

Pos logit contributions
hon+0.114
 boom+0.099
 notice+0.099
 rep+0.098
 announcements+0.097
Neg logit contributions
 favourite-0.093
 possession-0.091
 favorite-0.086
 wrist-0.073
 purse-0.072
Token so
Token ID523
Feature activation+2.06e-02

Pos logit contributions
 favourite+0.022
 possession+0.022
 favorite+0.020
 brand+0.018
 purse+0.018
Neg logit contributions
hon-0.025
Run-0.021
rr-0.020
 boom-0.020
 slit-0.020
Token new
Token ID649
Feature activation-4.84e-02

Pos logit contributions
 possession+0.009
 favourite+0.009
 favorite+0.008
 purse+0.008
 item+0.007
Neg logit contributions
hon-0.008
 rep-0.007
 announcements-0.007
 cal-0.007
 boom-0.006
Token number
Token ID1271
Feature activation-4.57e-02

Pos logit contributions
 possession+0.083
 favourite+0.082
 favorite+0.074
 purse+0.068
 favorites+0.066
Neg logit contributions
hon-0.090
 notice-0.076
 rep-0.076
 cal-0.076
 overcome-0.075
Token,
Token ID11
Feature activation-4.76e-03

Pos logit contributions
 favourite+0.086
 possession+0.086
 favorite+0.080
 purse+0.075
 wrist+0.071
Neg logit contributions
hon-0.073
 notice-0.062
 cal-0.060
 rep-0.060
RO-0.060
Token louder
Token ID27089
Feature activation+2.16e-01

Pos logit contributions
 favourite+0.009
 possession+0.008
 favorite+0.008
 purse+0.008
 wrist+0.007
Neg logit contributions
hon-0.008
rr-0.006
 oblig-0.006
 notice-0.006
RO-0.006
Token and
Token ID290
Feature activation+2.03e-02

Pos logit contributions
hon+0.446
RO+0.394
 cal+0.388
 oblig+0.378
 rep+0.375
Neg logit contributions
 possession-0.311
 favourite-0.295
 favorite-0.270
 wrist-0.245
 purse-0.232
Token louder
Token ID27089
Feature activation+2.32e-01

Pos logit contributions
hon+0.032
rr+0.027
RO+0.025
 oblig+0.024
iver+0.023
Neg logit contributions
 favourite-0.037
 favorite-0.034
 possession-0.033
 brand-0.033
 purse-0.029
Token Pe
Token ID2631
Feature activation+1.17e-01

Pos logit contributions
hon+0.454
RO+0.398
 cal+0.393
 oblig+0.383
Jim+0.380
Neg logit contributions
 possession-0.343
 favourite-0.330
 favorite-0.300
 wrist-0.266
 purse-0.248
Tokenaches
Token ID3694
Feature activation+4.78e-02

Pos logit contributions
hon+0.184
 notice+0.184
 thunder+0.174
 boom+0.172
 rep+0.171
Neg logit contributions
 possession-0.194
 favourite-0.194
 favorite-0.179
belt-0.176
 purse-0.175
Tokenâ
Token ID22940
Feature activation+1.44e-01

Pos logit contributions
hon+0.079
 announcements+0.069
Hon+0.067
 cal+0.067
 rep+0.067
Neg logit contributions
 favourite-0.074
 favorite-0.068
 possession-0.066
attered-0.065
robe-0.063
Token
Token ID26391
Feature activation+8.04e-02

Pos logit contributions
hon+0.210
 notice+0.199
 louder+0.193
 announcements+0.190
 swarm+0.187
Neg logit contributions
 possession-0.258
 favourite-0.240
 wrist-0.230
attered-0.230
 purse-0.223
Token
Token ID8151
Feature activation+7.30e-02

Pos logit contributions
hon+0.171
 louder+0.168
 cal+0.162
 rep+0.157
 notice+0.157
Neg logit contributions
 favourite-0.100
 possession-0.099
 favorite-0.087
 purse-0.084
 wrist-0.082
Token.
Token ID13
Feature activation-1.28e-03

Pos logit contributions
 possession+0.000
 favourite+0.000
 favorite+0.000
 purse+0.000
 brand+0.000
Neg logit contributions
hon-0.000
 oblig-0.000
 announcements-0.000
RO-0.000
 hon-0.000
Token Suddenly
Token ID24975
Feature activation+2.34e-02

Pos logit contributions
 possession+0.002
 favourite+0.002
 favorite+0.002
 purse+0.002
 wrist+0.002
Neg logit contributions
hon-0.002
 notice-0.002
 hon-0.002
 cal-0.002
 rep-0.002
Token,
Token ID11
Feature activation+1.25e-02

Pos logit contributions
hon+0.046
 announcements+0.038
rr+0.037
 hon+0.037
RO+0.037
Neg logit contributions
 favourite-0.037
 possession-0.036
 favorite-0.032
 purse-0.030
 microscope-0.029
Token the
Token ID262
Feature activation+4.51e-02

Pos logit contributions
hon+0.024
rr+0.020
 announcements+0.020
qu+0.019
 hon+0.019
Neg logit contributions
 favourite-0.021
 possession-0.020
 favorite-0.018
 brand-0.017
 purse-0.016
Token worm
Token ID23849
Feature activation+1.02e-02

Pos logit contributions
hon+0.091
 notice+0.078
 hon+0.077
 announcements+0.077
 rep+0.077
Neg logit contributions
 favourite-0.069
 possession-0.069
 favorite-0.063
 purse-0.060
 wallet-0.055
Token slit
Token ID40724
Feature activation+2.32e-01

Pos logit contributions
hon+0.016
 oblig+0.013
 rep+0.013
 notice+0.013
 announcements+0.013
Neg logit contributions
 favourite-0.020
 possession-0.019
 favorite-0.018
 purse-0.017
 wrist-0.016
Tokenhered
Token ID6083
Feature activation+2.97e-02

Pos logit contributions
hon+0.357
 announcements+0.311
 cal+0.306
 rep+0.304
 notice+0.304
Neg logit contributions
 favourite-0.412
 possession-0.399
 purse-0.377
robe-0.363
 favorite-0.361
Token away
Token ID1497
Feature activation-2.71e-02

Pos logit contributions
hon+0.062
 rep+0.056
 oblig+0.054
 notice+0.053
 cal+0.053
Neg logit contributions
 possession-0.044
 favourite-0.042
 favorite-0.038
 purse-0.035
attered-0.033
Token and
Token ID290
Feature activation-2.43e-02

Pos logit contributions
 possession+0.041
 favourite+0.040
 favorite+0.036
 purse+0.033
 brand+0.032
Neg logit contributions
hon-0.055
 oblig-0.047
 announcements-0.046
rr-0.046
Jim-0.046
Token the
Token ID262
Feature activation+5.04e-02

Pos logit contributions
 possession+0.048
 favourite+0.046
 favorite+0.042
 purse+0.040
 brand+0.039
Neg logit contributions
hon-0.040
 announcements-0.030
 oblig-0.030
 hon-0.030
 notice-0.030
Token area
Token ID1989
Feature activation-2.56e-02

Pos logit contributions
hon+0.102
 notice+0.087
 hon+0.087
 rep+0.086
 announcements+0.086
Neg logit contributions
 possession-0.077
 favourite-0.076
 favorite-0.069
 purse-0.066
 wrist-0.061
Token,
Token ID11
Feature activation-1.70e-02

Pos logit contributions
 possession+0.117
 favourite+0.115
 favorite+0.111
 purse+0.104
 wrist+0.098
Neg logit contributions
hon-0.098
 cal-0.085
 announcements-0.085
 rep-0.084
 oblig-0.084
Token it
Token ID340
Feature activation-3.43e-02

Pos logit contributions
 favourite+0.028
 possession+0.028
 favorite+0.026
 purse+0.024
 wrist+0.023
Neg logit contributions
hon-0.030
 oblig-0.026
 overcome-0.025
 notice-0.025
 rep-0.025
Token twisted
Token ID19074
Feature activation+1.03e-02

Pos logit contributions
 favourite+0.054
 favorite+0.052
 possession+0.050
attered+0.042
 purse+0.041
Neg logit contributions
hon-0.062
 oblig-0.056
 rep-0.055
 notice-0.054
 announcements-0.053
Token around
Token ID1088
Feature activation-5.97e-02

Pos logit contributions
hon+0.018
 oblig+0.016
 rep+0.016
 notice+0.016
 overcome+0.015
Neg logit contributions
 possession-0.018
 favourite-0.017
 favorite-0.016
 purse-0.015
 brand-0.014
Token and
Token ID290
Feature activation-2.10e-02

Pos logit contributions
 possession+0.116
 favourite+0.111
 favorite+0.103
 purse+0.097
 wrist+0.093
Neg logit contributions
hon-0.097
 rep-0.078
 oblig-0.078
 cal-0.078
 announcements-0.076
Token slit
Token ID40724
Feature activation+2.32e-01

Pos logit contributions
 possession+0.039
 favourite+0.038
 favorite+0.036
 purse+0.033
 brand+0.032
Neg logit contributions
hon-0.035
 oblig-0.028
 rep-0.028
rr-0.027
 notice-0.027
Tokenhered
Token ID6083
Feature activation+2.38e-02

Pos logit contributions
hon+0.362
 announcements+0.325
 cal+0.318
 rep+0.312
 thunder+0.312
Neg logit contributions
 favourite-0.407
 possession-0.404
 purse-0.369
robe-0.365
 favorite-0.363
Token away
Token ID1497
Feature activation-2.15e-02

Pos logit contributions
hon+0.049
 rep+0.045
 oblig+0.042
 cal+0.041
 overcome+0.040
Neg logit contributions
 possession-0.037
 favourite-0.034
 favorite-0.032
 purse-0.029
 wrist-0.027
Token.
Token ID13
Feature activation-6.80e-03

Pos logit contributions
 possession+0.036
 favourite+0.034
 favorite+0.031
 purse+0.029
robe+0.027
Neg logit contributions
hon-0.042
 oblig-0.035
Jim-0.034
 announcements-0.033
rr-0.033
Token
Token ID198
Feature activation+3.76e-02

Pos logit contributions
 possession+0.011
 favourite+0.010
 favorite+0.009
 purse+0.009
 wrist+0.009
Neg logit contributions
hon-0.013
 notice-0.012
 cal-0.011
 hon-0.011
 announcements-0.011
Token
Token ID198
Feature activation+3.24e-02

Pos logit contributions
hon+0.069
 notice+0.061
 rep+0.060
 cal+0.060
 hon+0.059
Neg logit contributions
 possession-0.061
 favourite-0.059
 favorite-0.053
 purse-0.051
 wrist-0.048
Token ignorant
Token ID20109
Feature activation-7.51e-03

Pos logit contributions
 possession+0.032
 favourite+0.031
 favorite+0.029
 purse+0.027
 wrist+0.026
Neg logit contributions
hon-0.028
 notice-0.023
 rep-0.023
 hon-0.023
 cal-0.023
Token of
Token ID286
Feature activation+4.93e-03

Pos logit contributions
 possession+0.014
 favourite+0.014
 favorite+0.013
 purse+0.012
 wrist+0.012
Neg logit contributions
hon-0.012
 notice-0.010
 hon-0.010
 rep-0.010
 cal-0.010
Token the
Token ID262
Feature activation+2.40e-02

Pos logit contributions
hon+0.007
 notice+0.006
 rep+0.006
 hon+0.005
 cal+0.005
Neg logit contributions
 possession-0.011
 favourite-0.010
 favorite-0.010
 purse-0.009
 wrist-0.009
Token dangers
Token ID16169
Feature activation+9.90e-02

Pos logit contributions
hon+0.045
 rep+0.039
 notice+0.038
 oblig+0.038
 cal+0.038
Neg logit contributions
 possession-0.040
 favourite-0.039
 favorite-0.036
 purse-0.034
 favorites-0.031
Token that
Token ID326
Feature activation-2.14e-02

Pos logit contributions
hon+0.178
 rep+0.159
 oblig+0.156
 notice+0.153
 overcome+0.153
Neg logit contributions
 possession-0.168
 favourite-0.153
 favorite-0.142
 purse-0.142
 wrist-0.126
Token lur
Token ID20605
Feature activation+2.31e-01

Pos logit contributions
 possession+0.040
 favourite+0.038
 favorite+0.036
 purse+0.035
robe+0.032
Neg logit contributions
hon-0.035
 rep-0.029
 oblig-0.029
 cal-0.029
 louder-0.029
Tokenked
Token ID9091
Feature activation-1.12e-02

Pos logit contributions
hon+0.404
 rep+0.372
 cal+0.364
 notice+0.353
 oblig+0.353
Neg logit contributions
 possession-0.394
 favourite-0.372
 favorite-0.349
 purse-0.329
attered-0.319
Token in
Token ID287
Feature activation-2.18e-03

Pos logit contributions
 possession+0.018
 favourite+0.018
 favorite+0.017
 purse+0.015
attered+0.014
Neg logit contributions
hon-0.021
 oblig-0.019
 rep-0.018
 notice-0.018
 cal-0.017
Token the
Token ID262
Feature activation+2.60e-02

Pos logit contributions
 possession+0.005
 favourite+0.004
 favorite+0.004
 purse+0.004
 wrist+0.004
Neg logit contributions
hon-0.003
 rep-0.002
 oblig-0.002
 hon-0.002
 cal-0.002
Token shadows
Token ID16187
Feature activation+2.36e-02

Pos logit contributions
hon+0.050
 rep+0.044
 oblig+0.043
 notice+0.042
 overcome+0.042
Neg logit contributions
 possession-0.042
 favourite-0.040
 favorite-0.037
 purse-0.036
 wallet-0.033
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
hon+0.040
 oblig+0.035
 rep+0.035
 notice+0.034
 cal+0.033
Neg logit contributions
 possession-0.042
 favourite-0.041
 favorite-0.038
 purse-0.036
 wrist-0.034
Token The
Token ID383
Feature activation+9.08e-03

Pos logit contributions
 possession+0.003
 favourite+0.003
 favorite+0.002
 purse+0.002
 wrist+0.002
Neg logit contributions
hon-0.004
 notice-0.004
 rep-0.004
 cal-0.004
 hon-0.004
Token snake
Token ID17522
Feature activation-1.21e-02

Pos logit contributions
hon+0.015
 hon+0.014
 louder+0.013
 notice+0.013
 boom+0.013
Neg logit contributions
 possession-0.017
 favourite-0.016
 favorite-0.014
 purse-0.014
attered-0.014
Token let
Token ID1309
Feature activation+9.11e-02

Pos logit contributions
 favourite+0.023
 possession+0.023
 favorite+0.022
 purse+0.021
 wrist+0.020
Neg logit contributions
hon-0.018
 rep-0.016
 oblig-0.015
 notice-0.015
 announcements-0.015
Token go
Token ID467
Feature activation+9.91e-02

Pos logit contributions
hon+0.137
 rep+0.129
 oblig+0.119
 announcements+0.116
rr+0.114
Neg logit contributions
 favourite-0.165
 possession-0.163
 favorite-0.160
 purse-0.157
robe-0.141
Token and
Token ID290
Feature activation-1.25e-02

Pos logit contributions
hon+0.159
 rep+0.142
 announcements+0.138
 cal+0.133
 notice+0.133
Neg logit contributions
 possession-0.185
 favourite-0.173
 favorite-0.162
 purse-0.161
 wrist-0.148
Token slit
Token ID40724
Feature activation+2.30e-01

Pos logit contributions
 possession+0.018
 favourite+0.017
 purse+0.017
 favorite+0.016
 wallet+0.015
Neg logit contributions
hon-0.023
rr-0.023
 announcements-0.020
 rep-0.019
 oblig-0.019
Tokenhered
Token ID6083
Feature activation+3.33e-02

Pos logit contributions
hon+0.326
 rep+0.284
 announcements+0.275
 cal+0.275
 notice+0.273
Neg logit contributions
 possession-0.458
 favourite-0.447
 favorite-0.414
 purse-0.412
 wrist-0.387
Token away
Token ID1497
Feature activation-1.86e-02

Pos logit contributions
hon+0.062
 rep+0.062
 oblig+0.058
 cal+0.054
 announcements+0.053
Neg logit contributions
 possession-0.054
 favourite-0.048
 favorite-0.047
 purse-0.045
 wrist-0.040
Token.
Token ID13
Feature activation+8.33e-04

Pos logit contributions
 possession+0.027
 favourite+0.024
 favorite+0.024
 purse+0.021
 where+0.020
Neg logit contributions
hon-0.038
 oblig-0.034
Jim-0.032
 announcements-0.031
Andrew-0.031
Token
Token ID198
Feature activation+4.96e-02

Pos logit contributions
hon+0.002
 notice+0.001
 rep+0.001
 cal+0.001
 hon+0.001
Neg logit contributions
 possession-0.001
 favourite-0.001
 favorite-0.001
 purse-0.001
 wrist-0.001
Token
Token ID198
Feature activation+4.47e-02

Pos logit contributions
hon+0.082
 notice+0.071
 rep+0.070
 hon+0.069
 cal+0.069
Neg logit contributions
 possession-0.092
 favourite-0.088
 favorite-0.081
 purse-0.078
 wrist-0.075
Token and
Token ID290
Feature activation-3.14e-03

Pos logit contributions
 possession+0.032
 favourite+0.031
 favorite+0.029
 purse+0.027
 wrist+0.026
Neg logit contributions
hon-0.035
 notice-0.030
 rep-0.030
 cal-0.030
 hon-0.029
Token soon
Token ID2582
Feature activation+6.08e-02

Pos logit contributions
 possession+0.006
 favourite+0.006
 favorite+0.006
 purse+0.005
 wrist+0.005
Neg logit contributions
hon-0.005
 notice-0.004
 rep-0.004
 cal-0.004
 hon-0.004
Token noticed
Token ID6810
Feature activation-4.06e-02

Pos logit contributions
hon+0.114
rr+0.102
 boom+0.096
 oblig+0.094
 rep+0.093
Neg logit contributions
 favourite-0.099
 possession-0.095
 favorite-0.092
 purse-0.080
 wallet-0.078
Token a
Token ID257
Feature activation+4.54e-02

Pos logit contributions
 possession+0.069
 favourite+0.067
 favorite+0.062
 purse+0.057
 brand+0.054
Neg logit contributions
hon-0.075
 notice-0.065
 oblig-0.063
 rep-0.062
 cal-0.062
Token narrow
Token ID7135
Feature activation+4.85e-02

Pos logit contributions
hon+0.075
 notice+0.067
 hon+0.066
 rep+0.066
 cal+0.066
Neg logit contributions
 possession-0.082
 favourite-0.078
 favorite-0.072
 purse-0.069
 wrist-0.067
Token slit
Token ID40724
Feature activation+2.30e-01

Pos logit contributions
hon+0.093
 notice+0.086
 hon+0.086
 rep+0.084
 cal+0.083
Neg logit contributions
 possession-0.072
 favourite-0.071
 favorite-0.064
 purse-0.058
attered-0.057
Token in
Token ID287
Feature activation+5.57e-04

Pos logit contributions
hon+0.359
 cal+0.314
 notice+0.312
 announcements+0.305
 rep+0.304
Neg logit contributions
 favourite-0.393
 possession-0.388
 purse-0.368
robe-0.357
 favorite-0.344
Token the
Token ID262
Feature activation+3.60e-02

Pos logit contributions
hon+0.001
 rep+0.001
 oblig+0.001
 notice+0.001
 overcome+0.001
Neg logit contributions
 possession-0.001
 favourite-0.001
 favorite-0.001
 purse-0.001
 wrist-0.001
Token books
Token ID3835
Feature activation-1.08e-02

Pos logit contributions
 thunder+0.065
 notice+0.063
 cal+0.062
 boom+0.061
 hon+0.060
Neg logit contributions
 possession-0.053
 favourite-0.051
uggets-0.046
 wrist-0.045
 favorite-0.044
Tokenhe
Token ID258
Feature activation-9.57e-03

Pos logit contributions
 possession+0.016
 favourite+0.015
 purse+0.014
 favorite+0.014
 wrist+0.013
Neg logit contributions
hon-0.021
 oblig-0.018
 cal-0.018
 rep-0.018
 announcements-0.018
Tokenlf
Token ID1652
Feature activation-3.01e-02

Pos logit contributions
 possession+0.015
 favourite+0.014
 favorite+0.013
 purse+0.013
 wrist+0.012
Neg logit contributions
hon-0.019
 cal-0.016
 rep-0.016
 notice-0.016
 hon-0.016
Token shells
Token ID19679
Feature activation+4.37e-02

Pos logit contributions
hon+0.112
 notice+0.095
 oblig+0.095
 rep+0.094
 overcome+0.092
Neg logit contributions
 possession-0.102
 favourite-0.101
 favorite-0.094
 purse-0.089
 wrist-0.084
Token.
Token ID13
Feature activation+1.37e-02

Pos logit contributions
hon+0.074
 oblig+0.066
 announcements+0.065
 cal+0.064
RO+0.064
Neg logit contributions
 possession-0.072
 favourite-0.071
 favorite-0.068
 purse-0.066
 wrist-0.063
Token They
Token ID1119
Feature activation+8.08e-02

Pos logit contributions
hon+0.024
 notice+0.020
 rep+0.020
 hon+0.020
 cal+0.020
Neg logit contributions
 possession-0.025
 favourite-0.024
 favorite-0.022
 purse-0.021
 wrist-0.020
Token hear
Token ID3285
Feature activation+1.14e-01

Pos logit contributions
hon+0.124
 louder+0.100
 oblig+0.098
 rep+0.097
rr+0.097
Neg logit contributions
 favourite-0.146
 favorite-0.141
 wrist-0.132
 purse-0.132
 possession-0.130
Token the
Token ID262
Feature activation+5.60e-02

Pos logit contributions
hon+0.199
 oblig+0.177
 overcome+0.175
 notice+0.170
 rep+0.167
Neg logit contributions
 favourite-0.193
 favorite-0.187
 possession-0.183
 purse-0.167
 brand-0.158
Token se
Token ID384
Feature activation+2.29e-01

Pos logit contributions
hon+0.093
 notice+0.077
 oblig+0.076
 overcome+0.076
RO+0.075
Neg logit contributions
 favourite-0.101
 possession-0.099
 favorite-0.097
 purse-0.090
 wallet-0.088
Tokenag
Token ID363
Feature activation+1.08e-01

Pos logit contributions
 rep+0.380
hon+0.337
 thunder+0.331
 overcome+0.326
 notice+0.324
Neg logit contributions
 possession-0.417
 favourite-0.380
 favorite-0.375
shirt-0.346
attered-0.335
Tokenull
Token ID724
Feature activation+9.36e-02

Pos logit contributions
hon+0.110
 cal+0.096
 rep+0.095
 notice+0.093
 oblig+0.086
Neg logit contributions
 possession-0.265
 favourite-0.251
 favorite-0.240
robe-0.224
 wrist-0.223
Tokens
Token ID82
Feature activation-3.66e-02

Pos logit contributions
 oblig+0.191
Jim+0.189
hon+0.186
 rep+0.186
 notice+0.179
Neg logit contributions
 favorite-0.098
 favourite-0.097
 possession-0.089
 purse-0.082
 brand-0.076
Token and
Token ID290
Feature activation+1.56e-02

Pos logit contributions
 favourite+0.038
 favorite+0.038
 possession+0.036
 wrist+0.036
 purse+0.033
Neg logit contributions
hon-0.079
 oblig-0.078
RO-0.075
 swarm-0.074
Jim-0.074
Token the
Token ID262
Feature activation+6.46e-02

Pos logit contributions
hon+0.023
qu+0.020
rr+0.019
Jim+0.019
 oblig+0.018
Neg logit contributions
 favourite-0.029
 favorite-0.029
 possession-0.028
 wrist-0.027
 purse-0.027
Token he
Token ID339
Feature activation+4.11e-02

Pos logit contributions
hon+0.001
rr+0.001
 oblig+0.001
 announcements+0.001
 notice+0.001
Neg logit contributions
 favourite-0.001
 possession-0.001
 favorite-0.001
 purse-0.001
 brand-0.001
Token felt
Token ID2936
Feature activation+1.99e-02

Pos logit contributions
hon+0.070
 rep+0.058
 notice+0.057
 oblig+0.057
 announcements+0.057
Neg logit contributions
 favourite-0.073
 possession-0.070
 favorite-0.068
 wrist-0.060
 brand-0.060
Token the
Token ID262
Feature activation+4.28e-02

Pos logit contributions
hon+0.031
 rep+0.026
 notice+0.026
 hon+0.025
 announcements+0.025
Neg logit contributions
 possession-0.039
 favourite-0.038
 favorite-0.035
 purse-0.034
 wrist-0.032
Token healing
Token ID11516
Feature activation+4.06e-02

Pos logit contributions
hon+0.081
 notice+0.066
 announcements+0.065
 hon+0.065
 oblig+0.065
Neg logit contributions
 favourite-0.074
 possession-0.072
 favorite-0.067
 purse-0.061
 wrist-0.058
Token power
Token ID1176
Feature activation+1.86e-02

Pos logit contributions
hon+0.073
 notice+0.063
 rep+0.062
 hon+0.061
 cal+0.061
Neg logit contributions
 possession-0.072
 favourite-0.068
 favorite-0.062
 purse-0.060
 wrist-0.057
Token cour
Token ID1093
Feature activation+2.29e-01

Pos logit contributions
hon+0.032
 notice+0.027
 announcements+0.026
 rep+0.026
 hon+0.026
Neg logit contributions
 possession-0.035
 favourite-0.033
 favorite-0.030
 purse-0.029
 brand-0.028
Tokensing
Token ID12215
Feature activation+8.84e-02

Pos logit contributions
hon+0.380
 notice+0.327
 rep+0.322
 hon+0.321
 cal+0.316
Neg logit contributions
 possession-0.422
 favourite-0.404
 favorite-0.372
 purse-0.362
 wrist-0.343
Token through
Token ID832
Feature activation+5.31e-03

Pos logit contributions
hon+0.164
 rep+0.148
 oblig+0.145
 notice+0.139
 overcome+0.137
Neg logit contributions
 possession-0.149
 favourite-0.138
 favorite-0.129
 purse-0.114
 item-0.110
Token his
Token ID465
Feature activation-1.62e-02

Pos logit contributions
hon+0.008
 oblig+0.007
 announcements+0.006
 rep+0.006
 overcome+0.006
Neg logit contributions
 possession-0.011
 favourite-0.010
 favorite-0.009
 purse-0.009
 wrist-0.009
Token body
Token ID1767
Feature activation+4.35e-03

Pos logit contributions
 possession+0.024
 favourite+0.023
 favorite+0.020
 purse+0.019
 wrist+0.018
Neg logit contributions
hon-0.034
 notice-0.030
 rep-0.030
 hon-0.029
 cal-0.029
Token.
Token ID13
Feature activation+2.23e-03

Pos logit contributions
hon+0.007
 notice+0.006
RO+0.006
 oblig+0.006
 announcements+0.006
Neg logit contributions
 possession-0.008
 favourite-0.008
 favorite-0.007
 purse-0.007
 wrist-0.007
Token.
Token ID13
Feature activation-4.02e-02

Pos logit contributions
hon+0.034
RO+0.031
 notice+0.029
Jim+0.029
 announcements+0.029
Neg logit contributions
 favourite-0.028
 possession-0.027
 favorite-0.027
 purse-0.024
 wrist-0.023
Token He
Token ID679
Feature activation-2.46e-02

Pos logit contributions
 favourite+0.059
 possession+0.058
 favorite+0.055
 purse+0.049
robe+0.046
Neg logit contributions
hon-0.080
 announcements-0.069
 hon-0.069
 notice-0.068
 overcome-0.068
Token showed
Token ID3751
Feature activation-1.21e-01

Pos logit contributions
 possession+0.052
 favourite+0.051
 favorite+0.047
 purse+0.046
 wrist+0.044
Neg logit contributions
hon-0.034
 notice-0.029
 rep-0.028
 cal-0.027
 oblig-0.027
Token Lily
Token ID20037
Feature activation-6.56e-02

Pos logit contributions
 possession+0.250
 favourite+0.242
 favorite+0.226
 purse+0.217
 wrist+0.206
Neg logit contributions
hon-0.178
 notice-0.150
 rep-0.149
 hon-0.146
 cal-0.144
Token his
Token ID465
Feature activation-1.40e-01

Pos logit contributions
 possession+0.129
 favourite+0.125
 favorite+0.115
 purse+0.111
 wrist+0.107
Neg logit contributions
hon-0.101
 notice-0.086
 hon-0.085
 cal-0.084
 rep-0.084
Token toy
Token ID13373
Feature activation-2.21e-01

Pos logit contributions
 possession+0.225
 favourite+0.207
attered+0.186
 purse+0.180
 favorite+0.179
Neg logit contributions
hon-0.252
 hon-0.234
 rep-0.230
 notice-0.224
 sne-0.222
Token gun
Token ID2485
Feature activation-7.63e-02

Pos logit contributions
 possession+0.422
 favourite+0.408
 favourites+0.356
 favorite+0.356
 favorites+0.352
Neg logit contributions
hon-0.342
 hon-0.316
 louder-0.294
 boom-0.287
 rep-0.287
Token.
Token ID13
Feature activation-4.30e-02

Pos logit contributions
 possession+0.172
 favourite+0.165
 favorite+0.152
 purse+0.149
 wrist+0.145
Neg logit contributions
hon-0.095
 hon-0.080
 notice-0.077
 rep-0.077
 louder-0.077
Token It
Token ID632
Feature activation-1.02e-01

Pos logit contributions
 possession+0.076
 favourite+0.074
 favorite+0.069
 purse+0.065
 wrist+0.063
Neg logit contributions
hon-0.074
 notice-0.063
 rep-0.063
 hon-0.063
 cal-0.062
Token was
Token ID373
Feature activation-2.44e-02

Pos logit contributions
 possession+0.177
 favourite+0.173
 favorite+0.160
 purse+0.151
 wrist+0.143
Neg logit contributions
hon-0.177
 notice-0.155
 rep-0.151
 oblig-0.150
 cal-0.149
Token red
Token ID2266
Feature activation-7.05e-02

Pos logit contributions
 possession+0.049
 favourite+0.046
 favorite+0.042
 purse+0.042
 wrist+0.041
Neg logit contributions
hon-0.037
 hon-0.032
 louder-0.032
 rep-0.031
 notice-0.031
Token,
Token ID11
Feature activation-6.83e-03

Pos logit contributions
 possession+0.077
 favourite+0.076
 favorite+0.071
 purse+0.069
 wrist+0.065
Neg logit contributions
hon-0.046
 hon-0.036
 cal-0.035
 rep-0.035
 notice-0.035
Token Emma
Token ID18966
Feature activation+1.44e-02

Pos logit contributions
 possession+0.014
 favourite+0.013
 favorite+0.012
 purse+0.012
 wrist+0.012
Neg logit contributions
hon-0.010
 notice-0.009
 rep-0.008
 hon-0.008
 cal-0.008
Token showed
Token ID3751
Feature activation-1.10e-01

Pos logit contributions
hon+0.024
 notice+0.020
 rep+0.020
 cal+0.020
 hon+0.020
Neg logit contributions
 possession-0.027
 favourite-0.026
 favorite-0.024
 purse-0.023
 wrist-0.022
Token Lily
Token ID20037
Feature activation-6.43e-02

Pos logit contributions
 possession+0.242
 favourite+0.226
 wrist+0.212
attered+0.211
 purse+0.209
Neg logit contributions
hon-0.120
 louder-0.114
 cal-0.111
 notice-0.110
 thunder-0.104
Token her
Token ID607
Feature activation-1.49e-01

Pos logit contributions
 possession+0.131
 favourite+0.123
attered+0.113
 favorite+0.111
 purse+0.109
Neg logit contributions
hon-0.086
 overcome-0.078
 cal-0.077
 notice-0.076
 hon-0.076
Token toy
Token ID13373
Feature activation-2.20e-01

Pos logit contributions
attered+0.199
 possession+0.188
resses+0.164
rolley+0.162
umes+0.162
Neg logit contributions
 hon-0.260
 cal-0.253
 sne-0.250
hon-0.249
 mad-0.247
Token and
Token ID290
Feature activation-4.62e-02

Pos logit contributions
 possession+0.419
 favourite+0.397
 wrist+0.373
 favourites+0.365
shirt+0.361
Neg logit contributions
hon-0.284
 hon-0.281
 louder-0.249
 sne-0.249
 boom-0.247
Token they
Token ID484
Feature activation+6.10e-02

Pos logit contributions
 possession+0.099
 favourite+0.095
 favorite+0.088
 purse+0.085
 wrist+0.083
Neg logit contributions
hon-0.061
 notice-0.054
 rep-0.053
 hon-0.052
 cal-0.051
Token played
Token ID2826
Feature activation+2.14e-02

Pos logit contributions
hon+0.103
 notice+0.086
 rep+0.086
 cal+0.086
 hon+0.084
Neg logit contributions
 possession-0.111
 favourite-0.109
 favorite-0.101
 purse-0.096
 wrist-0.092
Token together
Token ID1978
Feature activation+3.39e-02

Pos logit contributions
hon+0.035
 notice+0.030
 rep+0.029
 hon+0.029
 cal+0.029
Neg logit contributions
 possession-0.040
 favourite-0.039
 favorite-0.036
 purse-0.035
 wrist-0.033
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
hon+0.054
 notice+0.046
 rep+0.046
 hon+0.045
 cal+0.045
Neg logit contributions
 possession-0.065
 favourite-0.062
 favorite-0.058
 purse-0.056
 wrist-0.053
Token cooler
Token ID19346
Feature activation+2.39e-02

Pos logit contributions
hon+0.060
 notice+0.053
 rep+0.053
 hon+0.052
 cal+0.052
Neg logit contributions
 possession-0.042
 favourite-0.040
 favorite-0.036
 purse-0.034
 wrist-0.033
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
hon+0.037
 notice+0.031
 rep+0.030
 cal+0.030
 hon+0.030
Neg logit contributions
 possession-0.048
 favourite-0.046
 favorite-0.043
 purse-0.041
 wrist-0.040
Token Mike
Token ID4995
Feature activation+4.66e-02

Pos logit contributions
 possession+0.026
 favourite+0.026
 favorite+0.023
 purse+0.022
 wrist+0.022
Neg logit contributions
hon-0.030
 notice-0.026
 cal-0.026
 hon-0.026
 rep-0.025
Token showed
Token ID3751
Feature activation-1.12e-01

Pos logit contributions
hon+0.087
 rep+0.080
 louder+0.079
 thunder+0.078
 boom+0.078
Neg logit contributions
 possession-0.070
 favourite-0.070
 favorite-0.065
 purse-0.059
 wrist-0.057
Token his
Token ID465
Feature activation-1.29e-01

Pos logit contributions
 possession+0.235
 favourite+0.229
 favorite+0.214
 purse+0.205
 wrist+0.195
Neg logit contributions
hon-0.159
 notice-0.135
 rep-0.132
 cal-0.128
 hon-0.127
Token toy
Token ID13373
Feature activation-2.19e-01

Pos logit contributions
 possession+0.196
 favourite+0.174
attered+0.162
 favorite+0.154
 purse+0.152
Neg logit contributions
hon-0.240
 hon-0.221
 cal-0.218
 rep-0.217
 notice-0.214
Token car
Token ID1097
Feature activation-1.16e-01

Pos logit contributions
 possession+0.400
 favourite+0.372
 wrist+0.346
attered+0.343
 favourites+0.340
Neg logit contributions
 hon-0.300
hon-0.298
 sne-0.268
 slit-0.264
 boom-0.253
Token to
Token ID284
Feature activation+2.56e-02

Pos logit contributions
 possession+0.216
 favourite+0.206
 favorite+0.186
 purse+0.181
 wrist+0.177
Neg logit contributions
hon-0.189
 hon-0.168
 cal-0.161
 notice-0.160
 rep-0.159
Token everyone
Token ID2506
Feature activation+3.19e-02

Pos logit contributions
hon+0.038
 cal+0.030
 rep+0.030
 notice+0.030
 announcements+0.030
Neg logit contributions
 possession-0.053
 favourite-0.051
 favorite-0.048
 purse-0.046
 wrist-0.045
Token who
Token ID508
Feature activation-8.40e-02

Pos logit contributions
hon+0.053
 notice+0.044
 rep+0.044
 cal+0.043
 announcements+0.043
Neg logit contributions
 possession-0.060
 favourite-0.059
 favorite-0.054
 purse-0.051
 wrist-0.050
Token walked
Token ID6807
Feature activation+7.16e-02

Pos logit contributions
 possession+0.155
 favourite+0.149
 favorite+0.137
 purse+0.132
 wrist+0.127
Neg logit contributions
hon-0.140
 notice-0.120
 hon-0.119
 rep-0.118
 cal-0.118
Token Sally
Token ID25737
Feature activation-3.52e-02

Pos logit contributions
hon+0.034
 notice+0.028
 rep+0.028
 hon+0.027
 cal+0.027
Neg logit contributions
 possession-0.059
 favourite-0.057
 favorite-0.053
 purse-0.052
 wrist-0.050
Token and
Token ID290
Feature activation-5.10e-02

Pos logit contributions
 possession+0.074
 favourite+0.069
 favorite+0.063
 purse+0.062
attered+0.061
Neg logit contributions
hon-0.049
 notice-0.043
 overcome-0.043
 rep-0.042
 hon-0.042
Token showed
Token ID3751
Feature activation-1.24e-01

Pos logit contributions
 possession+0.125
 favourite+0.121
 favorite+0.114
 purse+0.111
 wrist+0.108
Neg logit contributions
hon-0.054
 notice-0.042
 rep-0.041
 hon-0.041
 cal-0.041
Token her
Token ID607
Feature activation-1.47e-01

Pos logit contributions
 possession+0.263
 favourite+0.255
 favorite+0.234
 wrist+0.233
attered+0.226
Neg logit contributions
hon-0.164
 cal-0.142
 notice-0.141
 rep-0.135
 louder-0.134
Token his
Token ID465
Feature activation-1.33e-01

Pos logit contributions
 possession+0.356
 favourite+0.343
attered+0.337
 wrist+0.317
 favourites+0.314
Neg logit contributions
hon-0.119
 cal-0.111
 notice-0.106
 hon-0.103
 hear-0.101
Token toy
Token ID13373
Feature activation-2.16e-01

Pos logit contributions
 possession+0.206
ase+0.206
attered+0.196
umes+0.191
 wrist+0.187
Neg logit contributions
 sne-0.209
 hon-0.205
 rep-0.195
 mad-0.192
hon-0.190
Token pistol
Token ID16790
Feature activation-1.32e-01

Pos logit contributions
 possession+0.393
 favourite+0.383
 wrist+0.378
artments+0.366
 favorites+0.364
Neg logit contributions
 hon-0.268
hon-0.268
 sne-0.259
 louder-0.246
 slit-0.235
Token.
Token ID13
Feature activation-3.21e-02

Pos logit contributions
 possession+0.332
 favourite+0.321
 favorite+0.292
 purse+0.292
 favorites+0.289
Neg logit contributions
hon-0.116
 hon-0.098
 louder-0.093
 rep-0.093
 cal-0.089
Token Sally
Token ID25737
Feature activation-1.91e-02

Pos logit contributions
 possession+0.074
 favourite+0.069
 favorite+0.064
 wrist+0.061
 purse+0.061
Neg logit contributions
hon-0.038
 rep-0.034
 notice-0.033
 cal-0.031
 hon-0.031
Token's
Token ID338
Feature activation-7.47e-02

Pos logit contributions
 possession+0.038
 favourite+0.036
 favorite+0.033
 purse+0.032
 wrist+0.031
Neg logit contributions
hon-0.030
 notice-0.025
 hon-0.025
 rep-0.025
 cal-0.025
Token face
Token ID1986
Feature activation-4.11e-02

Pos logit contributions
 possession+0.124
umes+0.116
ase+0.113
artments+0.108
attered+0.107
Neg logit contributions
 sne-0.115
 hon-0.105
 mad-0.105
 louder-0.102
 loud-0.101
Token
Token ID198
Feature activation+1.57e-02

Pos logit contributions
hon+0.037
 rep+0.032
 cal+0.032
 notice+0.032
 hon+0.032
Neg logit contributions
 possession-0.032
 favourite-0.031
 favorite-0.029
 purse-0.027
 wrist-0.025
TokenL
Token ID43
Feature activation+7.10e-02

Pos logit contributions
hon+0.025
 rep+0.022
 notice+0.022
 cal+0.021
 announcements+0.021
Neg logit contributions
 possession-0.029
 favourite-0.028
 favorite-0.026
 purse-0.025
 wrist-0.025
Tokenily
Token ID813
Feature activation-7.66e-03

Pos logit contributions
hon+0.108
 notice+0.089
 rep+0.088
 cal+0.087
 hon+0.086
Neg logit contributions
 possession-0.143
 favourite-0.140
 favorite-0.129
 purse-0.124
 wrist-0.120
Token handed
Token ID10158
Feature activation-1.11e-01

Pos logit contributions
 possession+0.017
 favourite+0.016
 favorite+0.015
 purse+0.015
 wrist+0.014
Neg logit contributions
hon-0.010
 notice-0.008
 rep-0.008
 hon-0.008
 cal-0.008
Token her
Token ID607
Feature activation-1.44e-01

Pos logit contributions
 possession+0.287
 favourite+0.279
 wrist+0.259
 favorite+0.256
attered+0.249
Neg logit contributions
hon-0.100
 louder-0.075
 hon-0.074
 notice-0.071
 cal-0.071
Token purse
Token ID27517
Feature activation-2.13e-01

Pos logit contributions
attered+0.237
 possession+0.217
resses+0.203
uggets+0.201
 favourite+0.196
Neg logit contributions
 the-0.202
 come-0.199
 mad-0.197
 hear-0.196
 notice-0.194
Token to
Token ID284
Feature activation-5.44e-03

Pos logit contributions
 possession+0.479
 favourites+0.471
 favourite+0.464
 favorites+0.464
attered+0.426
Neg logit contributions
 louder-0.179
hon-0.175
 hon-0.172
 cal-0.149
 come-0.148
Token Tim
Token ID5045
Feature activation-1.15e-02

Pos logit contributions
 possession+0.010
 favourite+0.010
 favorite+0.009
 purse+0.009
 wrist+0.009
Neg logit contributions
hon-0.009
 announcements-0.007
 notice-0.007
 cal-0.007
 overcome-0.007
Tokenmy
Token ID1820
Feature activation-5.99e-02

Pos logit contributions
 possession+0.024
 favourite+0.024
 favorite+0.022
 purse+0.021
 wrist+0.020
Neg logit contributions
hon-0.016
 notice-0.013
 rep-0.013
 cal-0.013
 hon-0.013
Token,
Token ID11
Feature activation-4.60e-02

Pos logit contributions
 possession+0.140
 favourite+0.135
 favorite+0.125
 purse+0.122
attered+0.120
Neg logit contributions
hon-0.068
 rep-0.055
 notice-0.055
 cal-0.054
 hon-0.054
Token but
Token ID475
Feature activation-2.98e-02

Pos logit contributions
 possession+0.091
 favourite+0.087
 favorite+0.080
 purse+0.078
 wrist+0.075
Neg logit contributions
hon-0.071
 notice-0.061
 rep-0.060
 hon-0.060
 cal-0.059
Token Everyday
Token ID48154
Feature activation-4.04e-02

Pos logit contributions
 possession+0.126
 favourite+0.119
 favorite+0.109
 brand+0.106
 possessions+0.105
Neg logit contributions
hon-0.097
 notice-0.089
 cal-0.085
 rep-0.085
 oblig-0.081
Token,
Token ID11
Feature activation-3.74e-02

Pos logit contributions
 favourite+0.069
 possession+0.069
 favorite+0.063
 purse+0.062
 wrist+0.056
Neg logit contributions
hon-0.076
 hon-0.064
 notice-0.063
 overcome-0.063
 cal-0.063
Token she
Token ID673
Feature activation-1.57e-02

Pos logit contributions
 possession+0.068
 favourite+0.066
 favorite+0.061
 purse+0.059
 wrist+0.056
Neg logit contributions
hon-0.064
 hon-0.054
 notice-0.054
 cal-0.054
 rep-0.054
Token showed
Token ID3751
Feature activation-1.26e-01

Pos logit contributions
 possession+0.029
 favourite+0.028
 favorite+0.025
 purse+0.025
 wrist+0.024
Neg logit contributions
hon-0.026
 notice-0.022
 hon-0.022
 rep-0.022
 cal-0.022
Token her
Token ID607
Feature activation-1.59e-01

Pos logit contributions
 possession+0.303
attered+0.297
belt+0.286
robe+0.285
 favourite+0.282
Neg logit contributions
hon-0.107
 cal-0.092
 hear-0.091
 louder-0.091
 overcome-0.086
Token purse
Token ID27517
Feature activation-2.12e-01

Pos logit contributions
attered+0.305
resses+0.256
 possession+0.249
artments+0.249
belt+0.245
Neg logit contributions
 the-0.177
 sne-0.176
 rep-0.174
,"-0.169
 cal-0.164
Token to
Token ID284
Feature activation-1.46e-04

Pos logit contributions
 possession+0.461
 favorites+0.433
 favourite+0.432
 favourites+0.428
attered+0.425
Neg logit contributions
 come-0.168
 overcome-0.162
 louder-0.160
 hon-0.150
 cal-0.146
Token her
Token ID607
Feature activation-1.12e-01

Pos logit contributions
 possession+0.000
attered+0.000
 favourite+0.000
ometer+0.000
 favorite+0.000
Neg logit contributions
 hear-0.000
 notice-0.000
hon-0.000
 rep-0.000
 come-0.000
Token friends
Token ID2460
Feature activation+1.94e-03

Pos logit contributions
attered+0.223
 possession+0.222
shirt+0.194
artments+0.193
robe+0.190
Neg logit contributions
 rep-0.126
 sne-0.121
 overcome-0.119
 cal-0.119
 hear-0.111
Token.
Token ID13
Feature activation-4.64e-02

Pos logit contributions
hon+0.003
 notice+0.002
 rep+0.002
 hon+0.002
 cal+0.002
Neg logit contributions
 possession-0.004
 favourite-0.004
 favorite-0.004
 purse-0.004
 wrist-0.004
Token She
Token ID1375
Feature activation-6.41e-02

Pos logit contributions
 possession+0.100
 favourite+0.088
 purse+0.083
 possessions+0.082
 wallet+0.081
Neg logit contributions
hon-0.064
 rep-0.057
 notice-0.056
 hear-0.052
 oblig-0.052
Token
Token ID198
Feature activation-1.02e-04

Pos logit contributions
 favourite+0.083
 favorite+0.080
 possession+0.077
 brand+0.064
 purse+0.064
Neg logit contributions
hon-0.100
 oblig-0.092
Jim-0.092
 notice-0.091
 rep-0.086
TokenL
Token ID43
Feature activation+4.78e-02

Pos logit contributions
 possession+0.000
 favourite+0.000
 favorite+0.000
 purse+0.000
 wrist+0.000
Neg logit contributions
hon-0.000
 cal-0.000
 notice-0.000
 rep-0.000
 hon-0.000
Tokenily
Token ID813
Feature activation-2.74e-02

Pos logit contributions
hon+0.088
 notice+0.079
 hon+0.079
 rep+0.079
 announcements+0.078
Neg logit contributions
 possession-0.078
 favourite-0.071
 favorite-0.065
 purse-0.065
 wrist-0.061
Token showed
Token ID3751
Feature activation-1.47e-01

Pos logit contributions
 favourite+0.040
 favorite+0.037
 possession+0.036
 purse+0.034
 wrist+0.033
Neg logit contributions
hon-0.055
 announcements-0.048
 boom-0.048
 explode-0.047
 oblig-0.047
Token the
Token ID262
Feature activation-8.02e-02

Pos logit contributions
 possession+0.298
 favourite+0.285
 favorite+0.260
 purse+0.256
 wrist+0.254
Neg logit contributions
hon-0.211
 cal-0.180
 notice-0.179
 louder-0.176
 hon-0.175
Token toy
Token ID13373
Feature activation-2.09e-01

Pos logit contributions
 possession+0.122
 favourite+0.117
 favorite+0.106
 purse+0.103
 wrist+0.096
Neg logit contributions
hon-0.160
 notice-0.141
 rep-0.138
 cal-0.138
 hon-0.137
Token to
Token ID284
Feature activation-1.21e-02

Pos logit contributions
 favourite+0.397
 possession+0.397
 favourites+0.381
 favorites+0.373
artments+0.360
Neg logit contributions
hon-0.265
 hon-0.259
 louder-0.248
 hear-0.232
 boom-0.228
Token her
Token ID607
Feature activation-1.25e-01

Pos logit contributions
 possession+0.022
 favourite+0.021
 favorite+0.020
 purse+0.019
 wrist+0.018
Neg logit contributions
hon-0.021
 notice-0.018
 rep-0.017
 cal-0.017
 hon-0.017
Token friend
Token ID1545
Feature activation-7.47e-02

Pos logit contributions
 possession+0.223
attered+0.206
 favourite+0.204
artments+0.183
shirt+0.182
Neg logit contributions
hon-0.183
 rep-0.177
 hon-0.175
 notice-0.171
 overcome-0.170
Token,
Token ID11
Feature activation-4.36e-02

Pos logit contributions
 favourite+0.146
 possession+0.143
 favorite+0.137
 purse+0.133
 wallet+0.124
Neg logit contributions
hon-0.118
 announcements-0.096
 notice-0.095
RO-0.093
 hon-0.092
Token Tim
Token ID5045
Feature activation+3.29e-02

Pos logit contributions
 possession+0.077
 favourite+0.075
 favorite+0.070
 purse+0.068
 wrist+0.064
Neg logit contributions
hon-0.075
 notice-0.063
 announcements-0.063
 oblig-0.062
 cal-0.062
Token Tim
Token ID5045
Feature activation+4.27e-02

Pos logit contributions
 possession+0.040
 favourite+0.039
 favorite+0.037
 purse+0.035
 wallet+0.032
Neg logit contributions
hon-0.031
 cal-0.026
 announcements-0.026
 oblig-0.025
 notice-0.025
Token wanted
Token ID2227
Feature activation-7.03e-02

Pos logit contributions
hon+0.080
 oblig+0.073
 announcements+0.073
 cal+0.071
 rep+0.071
Neg logit contributions
 possession-0.066
 favourite-0.064
 favorite-0.062
 purse-0.058
 wallet-0.056
Token to
Token ID284
Feature activation+2.10e-02

Pos logit contributions
 possession+0.145
 favourite+0.138
attered+0.129
 wrist+0.127
 purse+0.125
Neg logit contributions
hon-0.097
 hon-0.089
 rep-0.083
 thunder-0.083
 overcome-0.083
Token show
Token ID905
Feature activation-6.07e-02

Pos logit contributions
hon+0.033
 notice+0.027
 rep+0.027
 cal+0.027
 hon+0.027
Neg logit contributions
 possession-0.041
 favourite-0.040
 favorite-0.037
 purse-0.036
 wrist-0.034
Token his
Token ID465
Feature activation-1.19e-01

Pos logit contributions
 possession+0.142
 favourite+0.138
 favorite+0.128
attered+0.126
 purse+0.125
Neg logit contributions
hon-0.068
 hon-0.056
 notice-0.056
 louder-0.054
 cal-0.054
Token toy
Token ID13373
Feature activation-2.08e-01

Pos logit contributions
 possession+0.195
attered+0.176
ase+0.174
artments+0.169
ocket+0.169
Neg logit contributions
 hon-0.189
hon-0.182
 rep-0.171
 sne-0.169
 thunder-0.165
Token to
Token ID284
Feature activation+5.44e-03

Pos logit contributions
 possession+0.370
 favourite+0.339
 wrist+0.319
 favourites+0.311
attered+0.308
Neg logit contributions
hon-0.337
 hon-0.327
 louder-0.296
 boom-0.292
 sne-0.282
Token his
Token ID465
Feature activation-9.14e-02

Pos logit contributions
hon+0.006
 notice+0.005
 hon+0.005
 rep+0.005
 overcome+0.005
Neg logit contributions
 possession-0.013
 favourite-0.013
 favorite-0.012
 purse-0.011
attered-0.011
Token friends
Token ID2460
Feature activation+2.77e-03

Pos logit contributions
 possession+0.176
attered+0.162
shirt+0.153
artments+0.152
 favourite+0.151
Neg logit contributions
 hon-0.119
hon-0.117
 rep-0.112
 sne-0.109
 cal-0.106
Token.
Token ID13
Feature activation-3.25e-02

Pos logit contributions
hon+0.004
 notice+0.003
 rep+0.003
 hon+0.003
 cal+0.003
Neg logit contributions
 possession-0.006
 favourite-0.006
 favorite-0.006
 purse-0.005
 wrist-0.005
Token
Token ID198
Feature activation+2.18e-02

Pos logit contributions
 possession+0.070
 favourite+0.065
 purse+0.060
 favorite+0.059
 wrist+0.058
Neg logit contributions
hon-0.046
 rep-0.038
 hon-0.038
 notice-0.037
 overcome-0.036
Token just
Token ID655
Feature activation+2.66e-02

Pos logit contributions
 favourite+0.122
 favorite+0.116
 possession+0.116
 purse+0.098
 wallet+0.097
Neg logit contributions
hon-0.136
 cal-0.118
 oblig-0.116
Run-0.116
 notice-0.115
Token buried
Token ID11694
Feature activation-5.80e-02

Pos logit contributions
hon+0.037
 notice+0.032
 hon+0.032
 rep+0.032
 cal+0.031
Neg logit contributions
 possession-0.054
 favourite-0.053
 favorite-0.048
 purse-0.048
 wrist-0.047
Token his
Token ID465
Feature activation-8.64e-02

Pos logit contributions
 possession+0.125
 favourite+0.120
 purse+0.111
 wrist+0.110
 favorite+0.109
Neg logit contributions
hon-0.072
 hon-0.062
 louder-0.061
 notice-0.061
 cal-0.061
Token most
Token ID749
Feature activation-2.14e-02

Pos logit contributions
 possession+0.120
 favourite+0.103
attered+0.097
 wrist+0.094
 purse+0.093
Neg logit contributions
hon-0.158
 hon-0.150
 sne-0.149
 rep-0.147
 notice-0.145
Token prized
Token ID37768
Feature activation-8.18e-02

Pos logit contributions
 possession+0.035
 favourite+0.033
 favorite+0.030
 purse+0.030
 wrist+0.029
Neg logit contributions
hon-0.038
 cal-0.034
 notice-0.034
 hon-0.034
 overcome-0.033
Token possession
Token ID7797
Feature activation-2.08e-01

Pos logit contributions
 favourite+0.075
attered+0.071
 wrist+0.065
 brand+0.063
umes+0.062
Neg logit contributions
hon-0.175
 hon-0.162
 notice-0.152
 sne-0.150
 cal-0.150
Token a
Token ID257
Feature activation+1.78e-02

Pos logit contributions
 possession+0.526
 favourite+0.525
attered+0.495
 purse+0.493
 favorite+0.491
Neg logit contributions
hon-0.117
 hon-0.098
 rep-0.096
 overcome-0.086
 notice-0.086
Token few
Token ID1178
Feature activation-4.00e-02

Pos logit contributions
hon+0.032
 hon+0.029
 notice+0.029
 rep+0.029
 cal+0.028
Neg logit contributions
 possession-0.029
 favourite-0.027
 favorite-0.024
attered-0.024
 purse-0.024
Token inches
Token ID8331
Feature activation+9.16e-02

Pos logit contributions
 possession+0.071
 favourite+0.070
 favorite+0.063
 purse+0.062
 wrist+0.062
Neg logit contributions
hon-0.063
 notice-0.056
 hon-0.055
 cal-0.055
 rep-0.054
Token underground
Token ID11447
Feature activation-6.00e-02

Pos logit contributions
hon+0.116
 notice+0.098
 hon+0.097
 rep+0.094
 cal+0.093
Neg logit contributions
 possession-0.199
 favourite-0.194
 favorite-0.179
 purse-0.176
 wrist-0.173
Token.
Token ID13
Feature activation-2.26e-02

Pos logit contributions
 possession+0.128
 favourite+0.123
 favorite+0.115
 purse+0.110
 wrist+0.106
Neg logit contributions
hon-0.085
 notice-0.070
 rep-0.069
 cal-0.068
 hon-0.068
Token the
Token ID262
Feature activation+9.18e-03

Pos logit contributions
hon+0.112
 rep+0.095
 announcements+0.095
 notice+0.094
 cal+0.093
Neg logit contributions
 possession-0.135
 favourite-0.124
 purse-0.118
 favorite-0.116
 wrist-0.111
Token little
Token ID1310
Feature activation+2.32e-02

Pos logit contributions
hon+0.017
 notice+0.015
 oblig+0.014
 rep+0.014
 cal+0.014
Neg logit contributions
 possession-0.016
 favourite-0.015
 favorite-0.014
 purse-0.014
 wallet-0.013
Token girl
Token ID2576
Feature activation-1.14e-02

Pos logit contributions
hon+0.045
 oblig+0.041
 overcome+0.041
 notice+0.040
 announcements+0.040
Neg logit contributions
 possession-0.038
 favourite-0.034
 purse-0.033
 favorite-0.033
 wallet-0.029
Token find
Token ID1064
Feature activation-1.27e-01

Pos logit contributions
 possession+0.024
 favourite+0.022
 favorite+0.021
 purse+0.020
attered+0.020
Neg logit contributions
hon-0.016
 notice-0.014
 overcome-0.014
 cal-0.013
 rep-0.013
Token her
Token ID607
Feature activation-1.21e-01

Pos logit contributions
 possession+0.285
 favourite+0.284
 favorite+0.266
attered+0.264
 wrist+0.262
Neg logit contributions
hon-0.133
 cal-0.125
 notice-0.118
 louder-0.116
 overcome-0.110
Token toy
Token ID13373
Feature activation-2.08e-01

Pos logit contributions
attered+0.164
ase+0.157
 possession+0.147
umes+0.144
shirt+0.140
Neg logit contributions
 sne-0.191
 mad-0.188
 rep-0.187
 fall-0.185
 time-0.184
Token.
Token ID13
Feature activation-2.81e-02

Pos logit contributions
 possession+0.482
 favourite+0.482
 favorites+0.448
 favourites+0.448
attered+0.438
Neg logit contributions
hon-0.169
 hon-0.156
 overcome-0.144
 louder-0.142
 rep-0.137
Token After
Token ID2293
Feature activation-1.70e-02

Pos logit contributions
 possession+0.047
 favourite+0.044
 favorite+0.041
 purse+0.038
 wrist+0.036
Neg logit contributions
hon-0.052
 cal-0.046
 notice-0.046
 rep-0.045
 hon-0.045
Token searching
Token ID10342
Feature activation-4.19e-03

Pos logit contributions
 possession+0.031
 favourite+0.030
 favorite+0.028
 purse+0.027
 wrist+0.025
Neg logit contributions
hon-0.029
 notice-0.025
 cal-0.024
 hon-0.024
 rep-0.024
Token for
Token ID329
Feature activation-9.52e-03

Pos logit contributions
 possession+0.008
 favourite+0.008
 wrist+0.008
 favorite+0.007
attered+0.007
Neg logit contributions
hon-0.006
 notice-0.006
 cal-0.005
 louder-0.005
 overcome-0.005
Token a
Token ID257
Feature activation+3.16e-02

Pos logit contributions
 possession+0.023
 favourite+0.023
attered+0.022
 favorite+0.021
 wrist+0.021
Neg logit contributions
 notice-0.008
hon-0.008
 cal-0.008
 louder-0.007
 overcome-0.007
Token.
Token ID13
Feature activation-3.80e-02

Pos logit contributions
 possession+0.034
 favourite+0.032
 favorite+0.030
 purse+0.029
 wrist+0.028
Neg logit contributions
hon-0.026
 notice-0.022
 rep-0.022
 hon-0.021
 cal-0.021
Token Tom
Token ID4186
Feature activation+7.76e-02

Pos logit contributions
 possession+0.088
 favourite+0.085
 favorite+0.080
 purse+0.078
 wrist+0.075
Neg logit contributions
hon-0.046
 notice-0.037
 rep-0.036
 hon-0.036
 cal-0.035
Token shows
Token ID2523
Feature activation-1.06e-01

Pos logit contributions
hon+0.134
 notice+0.116
 rep+0.115
 cal+0.112
 hon+0.112
Neg logit contributions
 possession-0.137
 favourite-0.133
 favorite-0.123
 purse-0.117
 wrist-0.112
Token Mia
Token ID32189
Feature activation-2.17e-02

Pos logit contributions
 possession+0.229
 favourite+0.222
 favorite+0.211
 purse+0.205
 wrist+0.193
Neg logit contributions
hon-0.144
 rep-0.118
 notice-0.116
 overcome-0.114
 cal-0.113
Token his
Token ID465
Feature activation-1.42e-01

Pos logit contributions
 possession+0.047
 favourite+0.045
 favorite+0.042
 purse+0.041
 wrist+0.039
Neg logit contributions
hon-0.030
 notice-0.025
 hon-0.024
 rep-0.024
 cal-0.024
Token model
Token ID2746
Feature activation-2.07e-01

Pos logit contributions
 possession+0.192
 favourite+0.168
attered+0.150
 favorite+0.142
 wrist+0.141
Neg logit contributions
hon-0.288
 hon-0.268
 rep-0.265
 thunder-0.257
 notice-0.257
Token car
Token ID1097
Feature activation-1.20e-01

Pos logit contributions
 possession+0.345
 favourite+0.329
 favorite+0.283
 favourites+0.282
attered+0.277
Neg logit contributions
hon-0.355
 hon-0.331
 rep-0.311
 hear-0.308
 boom-0.307
Token.
Token ID13
Feature activation-4.23e-02

Pos logit contributions
 possession+0.254
 favourite+0.243
 favorite+0.222
 purse+0.217
 wrist+0.211
Neg logit contributions
hon-0.166
 hon-0.143
 rep-0.138
 notice-0.138
 cal-0.134
Token He
Token ID679
Feature activation-2.57e-02

Pos logit contributions
 possession+0.086
 favourite+0.082
 favorite+0.076
 purse+0.074
 wrist+0.071
Neg logit contributions
hon-0.064
 notice-0.054
 rep-0.053
 hon-0.053
 cal-0.052
Token says
Token ID1139
Feature activation-1.06e-02

Pos logit contributions
 possession+0.055
 favourite+0.052
 favorite+0.048
 purse+0.047
 wrist+0.046
Neg logit contributions
hon-0.036
 notice-0.030
 hon-0.030
 rep-0.030
 cal-0.029
Token,
Token ID11
Feature activation-5.52e-02

Pos logit contributions
 favourite+0.018
 possession+0.018
 favorite+0.018
 purse+0.017
 wallet+0.016
Neg logit contributions
hon-0.017
 notice-0.015
 overcome-0.015
 cal-0.015
Run-0.015
Tokenily
Token ID813
Feature activation-7.21e-03

Pos logit contributions
hon+0.131
 notice+0.122
 announcements+0.122
 cal+0.122
 hon+0.120
Neg logit contributions
 possession-0.128
 favourite-0.114
 favorite-0.105
 purse-0.104
robe-0.100
Token showed
Token ID3751
Feature activation-1.29e-01

Pos logit contributions
 favourite+0.013
 possession+0.013
 favorite+0.012
 purse+0.011
 wrist+0.011
Neg logit contributions
hon-0.012
 notice-0.010
 boom-0.010
 oblig-0.010
 rep-0.010
Token Sam
Token ID3409
Feature activation-2.37e-02

Pos logit contributions
 possession+0.316
 favourite+0.308
 favorite+0.291
 purse+0.282
 wrist+0.269
Neg logit contributions
hon-0.136
 notice-0.109
 rep-0.107
 cal-0.103
 hon-0.102
Token her
Token ID607
Feature activation-1.61e-01

Pos logit contributions
 possession+0.047
 favourite+0.044
 favorite+0.040
 purse+0.040
attered+0.039
Neg logit contributions
hon-0.035
 cal-0.031
 hon-0.030
 notice-0.030
 overcome-0.030
Token favorite
Token ID4004
Feature activation-1.74e-01

Pos logit contributions
 possession+0.245
 favourite+0.226
attered+0.218
 favorite+0.196
 purse+0.195
Neg logit contributions
hon-0.287
 hon-0.269
 rep-0.264
 cal-0.261
 notice-0.259
Token toy
Token ID13373
Feature activation-2.07e-01

Pos logit contributions
attered+0.305
 possession+0.264
umes+0.264
belt+0.257
artments+0.255
Neg logit contributions
 hon-0.267
 roar-0.253
 sne-0.250
 thunder-0.244
 laugh-0.243
Token,
Token ID11
Feature activation-5.27e-02

Pos logit contributions
 possession+0.501
 favourite+0.468
attered+0.452
 favourites+0.447
 favorites+0.444
Neg logit contributions
 hon-0.177
hon-0.168
 sne-0.144
 rep-0.139
 louder-0.136
Token a
Token ID257
Feature activation+2.26e-02

Pos logit contributions
 possession+0.098
 favourite+0.093
 favorite+0.085
 purse+0.083
attered+0.080
Neg logit contributions
hon-0.085
 hon-0.074
 rep-0.073
 notice-0.073
 cal-0.072
Token magnet
Token ID19972
Feature activation-6.03e-02

Pos logit contributions
hon+0.040
 hon+0.038
 rep+0.037
 louder+0.036
 notice+0.036
Neg logit contributions
 possession-0.036
 favourite-0.033
attered-0.031
 favorite-0.029
 favorites-0.029
Token.
Token ID13
Feature activation-2.96e-02

Pos logit contributions
 possession+0.148
 favourite+0.144
 favorite+0.131
 favorites+0.130
 favourites+0.129
Neg logit contributions
hon-0.058
 hon-0.051
 rep-0.045
 sne-0.042
 slit-0.041
Token "
Token ID366
Feature activation-1.04e-01

Pos logit contributions
 possession+0.062
 favourite+0.058
 favorite+0.054
 purse+0.052
attered+0.050
Neg logit contributions
hon-0.044
 rep-0.037
 notice-0.037
 hon-0.036
 louder-0.036
Token It
Token ID632
Feature activation-9.98e-02

Pos logit contributions
 possession+0.088
 favourite+0.084
 favorite+0.077
 purse+0.075
 wrist+0.072
Neg logit contributions
hon-0.082
 notice-0.071
 rep-0.070
 hon-0.070
 cal-0.069
Token was
Token ID373
Feature activation-2.57e-02

Pos logit contributions
 possession+0.230
 favourite+0.214
 wrist+0.212
 purse+0.209
attered+0.204
Neg logit contributions
 hon-0.114
hon-0.105
 roared-0.103
 slit-0.102
 ne-0.100
Token his
Token ID465
Feature activation-6.27e-02

Pos logit contributions
 possession+0.060
 wrist+0.054
 favourite+0.054
attered+0.053
 purse+0.051
Neg logit contributions
 hon-0.030
 louder-0.027
 rep-0.027
hon-0.027
 sne-0.026
Token most
Token ID749
Feature activation-1.11e-02

Pos logit contributions
attered+0.089
 possession+0.089
shirt+0.078
rolley+0.076
ase+0.074
Neg logit contributions
 hon-0.105
 rep-0.105
 sne-0.100
hon-0.099
 roar-0.098
Token prized
Token ID37768
Feature activation-7.69e-02

Pos logit contributions
 possession+0.020
robe+0.019
attered+0.019
artments+0.019
 favourite+0.018
Neg logit contributions
hon-0.015
 overcome-0.014
 cal-0.014
 bra-0.014
 hon-0.013
Token possession
Token ID7797
Feature activation-2.06e-01

Pos logit contributions
 favourite+0.052
attered+0.042
 favourites+0.042
 wrist+0.040
robe+0.039
Neg logit contributions
hon-0.178
 hon-0.162
,"-0.159
 cal-0.156
 notice-0.154
Token,
Token ID11
Feature activation-2.72e-02

Pos logit contributions
 favourite+0.530
 possession+0.517
attered+0.509
 favorites+0.500
 favorite+0.491
Neg logit contributions
 hon-0.094
hon-0.094
 rep-0.074
,"-0.071
 sne-0.066
Token and
Token ID290
Feature activation-8.85e-03

Pos logit contributions
 possession+0.059
 favourite+0.057
 purse+0.052
attered+0.052
 favorite+0.052
Neg logit contributions
hon-0.034
 hon-0.030
 rep-0.028
 notice-0.028
 thunder-0.027
Token he
Token ID339
Feature activation+2.93e-02

Pos logit contributions
 possession+0.021
 favourite+0.020
attered+0.019
 purse+0.019
 wrist+0.018
Neg logit contributions
hon-0.008
 hon-0.008
 rep-0.007
 notice-0.007
 overcome-0.007
Token never
Token ID1239
Feature activation+7.10e-02

Pos logit contributions
hon+0.044
 hon+0.042
 overcome+0.040
 sne+0.039
 roared+0.038
Neg logit contributions
 possession-0.056
 favourite-0.051
 purse-0.050
 wrist-0.047
 brand-0.046
Token let
Token ID1309
Feature activation+8.77e-02

Pos logit contributions
hon+0.137
Jim+0.117
 announcements+0.115
 boom+0.115
Run+0.115
Neg logit contributions
 possession-0.113
 favourite-0.102
 favorite-0.100
 purse-0.093
 wallet-0.089
Token so
Token ID523
Feature activation+3.29e-04

Pos logit contributions
 possession+0.061
 favourite+0.060
 favorite+0.055
 purse+0.052
 wrist+0.049
Neg logit contributions
hon-0.063
 notice-0.054
 rep-0.054
 cal-0.053
 hon-0.052
Token excited
Token ID6568
Feature activation+7.26e-03

Pos logit contributions
hon+0.001
 cal+0.001
 rep+0.001
 oblig+0.001
 notice+0.001
Neg logit contributions
 favourite-0.001
 possession-0.001
 favorite-0.000
 purse-0.000
attered-0.000
Token to
Token ID284
Feature activation+4.18e-02

Pos logit contributions
hon+0.016
 cal+0.014
 oblig+0.014
 notice+0.014
 announcements+0.014
Neg logit contributions
 possession-0.010
 favourite-0.010
 favorite-0.009
 purse-0.008
 wallet-0.007
Token show
Token ID905
Feature activation-5.61e-02

Pos logit contributions
hon+0.053
 cal+0.044
 rep+0.042
 louder+0.041
 slit+0.040
Neg logit contributions
 possession-0.092
 favourite-0.091
 favorite-0.085
 purse-0.081
 wrist-0.081
Token his
Token ID465
Feature activation-1.15e-01

Pos logit contributions
 possession+0.118
 favourite+0.114
 favorite+0.107
 purse+0.103
 wrist+0.098
Neg logit contributions
hon-0.081
 notice-0.067
 rep-0.067
 cal-0.065
 overcome-0.064
Token toy
Token ID13373
Feature activation-2.06e-01

Pos logit contributions
 possession+0.200
 favourite+0.176
attered+0.165
 wrist+0.164
 purse+0.164
Neg logit contributions
hon-0.192
 hon-0.183
 thunder-0.173
 boom-0.173
 notice-0.172
Token trains
Token ID13404
Feature activation-6.60e-02

Pos logit contributions
 possession+0.396
 favourite+0.371
 wrist+0.342
 purse+0.337
 favorite+0.328
Neg logit contributions
hon-0.324
 hon-0.296
 boom-0.282
 louder-0.280
 hear-0.272
Token to
Token ID284
Feature activation+2.74e-02

Pos logit contributions
 possession+0.112
 favourite+0.108
 favorite+0.101
 purse+0.095
 wrist+0.090
Neg logit contributions
hon-0.119
 notice-0.101
 cal-0.101
 rep-0.101
 oblig-0.099
Token everyone
Token ID2506
Feature activation+3.07e-02

Pos logit contributions
hon+0.039
 notice+0.032
 rep+0.032
 cal+0.032
 hon+0.031
Neg logit contributions
 possession-0.058
 favourite-0.056
 favorite-0.052
 purse-0.050
 wrist-0.048
Token.
Token ID13
Feature activation-2.10e-02

Pos logit contributions
hon+0.047
 notice+0.040
 cal+0.039
 rep+0.039
 announcements+0.039
Neg logit contributions
 possession-0.061
 favourite-0.059
 favorite-0.055
 purse-0.052
 wrist-0.050
Token But
Token ID887
Feature activation+3.18e-03

Pos logit contributions
 possession+0.050
 favourite+0.043
 purse+0.043
ocket+0.043
 wrist+0.041
Neg logit contributions
hon-0.024
 hon-0.022
 rep-0.020
 notice-0.020
 louder-0.019
Token nice
Token ID3621
Feature activation-1.96e-02

Pos logit contributions
 favourite+0.042
 possession+0.041
 favorite+0.040
 purse+0.036
 wrist+0.035
Neg logit contributions
hon-0.041
 notice-0.035
 rep-0.034
 slit-0.034
 cal-0.034
Token.
Token ID13
Feature activation-2.20e-02

Pos logit contributions
 possession+0.041
 favourite+0.039
 favorite+0.037
 purse+0.036
 wrist+0.034
Neg logit contributions
hon-0.029
 notice-0.024
 rep-0.024
 cal-0.023
 oblig-0.023
Token He
Token ID679
Feature activation-9.34e-03

Pos logit contributions
 possession+0.037
 favourite+0.037
 favorite+0.034
 purse+0.032
 wrist+0.030
Neg logit contributions
hon-0.039
 notice-0.034
 overcome-0.034
 rep-0.034
 cal-0.033
Token offers
Token ID4394
Feature activation-8.05e-02

Pos logit contributions
 favourite+0.020
 possession+0.020
 favorite+0.019
 purse+0.018
 favorites+0.017
Neg logit contributions
hon-0.012
 notice-0.010
 rep-0.010
 oblig-0.010
 overcome-0.009
Token his
Token ID465
Feature activation-1.11e-01

Pos logit contributions
 possession+0.177
 favourite+0.171
 favorite+0.160
 purse+0.155
 wrist+0.150
Neg logit contributions
hon-0.106
 notice-0.088
 rep-0.086
 hon-0.085
 cal-0.085
Token toy
Token ID13373
Feature activation-2.05e-01

Pos logit contributions
 possession+0.180
 favourite+0.162
attered+0.150
 purse+0.141
 wrist+0.140
Neg logit contributions
hon-0.202
 hon-0.190
 rep-0.177
 boom-0.177
 notice-0.176
Token train
Token ID4512
Feature activation-1.05e-01

Pos logit contributions
 possession+0.399
 favourite+0.368
 wrist+0.344
 favourites+0.336
attered+0.326
Neg logit contributions
hon-0.312
 hon-0.299
 louder-0.279
 boom-0.272
 hear-0.258
Token to
Token ID284
Feature activation+1.76e-02

Pos logit contributions
 possession+0.207
 favourite+0.199
 favorite+0.183
 purse+0.178
 wrist+0.171
Neg logit contributions
hon-0.162
 notice-0.137
 rep-0.135
 hon-0.135
 cal-0.134
Token Lily
Token ID20037
Feature activation-2.80e-02

Pos logit contributions
hon+0.029
 cal+0.024
 rep+0.023
 announcements+0.023
 overcome+0.023
Neg logit contributions
 possession-0.032
 favourite-0.031
 favorite-0.030
 purse-0.028
 wrist-0.027
Token and
Token ID290
Feature activation-2.72e-02

Pos logit contributions
 possession+0.061
 favourite+0.059
 favorite+0.056
 purse+0.054
 wrist+0.052
Neg logit contributions
hon-0.037
 notice-0.031
 rep-0.030
 hon-0.030
 cal-0.030
Token Sam
Token ID3409
Feature activation+5.49e-02

Pos logit contributions
 possession+0.058
 favourite+0.058
 favorite+0.056
 purse+0.053
 wrist+0.050
Neg logit contributions
hon-0.037
 announcements-0.029
 notice-0.028
rr-0.028
 boom-0.027
Token
Token ID198
Feature activation+3.81e-02

Pos logit contributions
 possession+0.024
 favourite+0.023
 favorite+0.021
 purse+0.020
attered+0.020
Neg logit contributions
hon-0.017
 rep-0.014
 notice-0.014
 cal-0.013
 hon-0.013
Token
Token ID198
Feature activation+3.32e-02

Pos logit contributions
hon+0.057
 notice+0.048
 hon+0.047
 rep+0.047
 overcome+0.046
Neg logit contributions
 possession-0.078
 favourite-0.075
 favorite-0.070
 purse-0.068
attered-0.065
TokenShe
Token ID3347
Feature activation-4.07e-02

Pos logit contributions
hon+0.051
 notice+0.044
 rep+0.043
 hon+0.043
 cal+0.043
Neg logit contributions
 possession-0.065
 favourite-0.063
 favorite-0.058
 purse-0.056
 wrist-0.054
Token showed
Token ID3751
Feature activation-1.05e-01

Pos logit contributions
 possession+0.077
 favourite+0.077
 favorite+0.072
 purse+0.068
 wrist+0.066
Neg logit contributions
hon-0.062
 notice-0.053
 rep-0.052
 announcements-0.051
 cal-0.051
Token her
Token ID607
Feature activation-1.44e-01

Pos logit contributions
 possession+0.222
 favourite+0.213
 favorite+0.195
 purse+0.193
attered+0.192
Neg logit contributions
hon-0.141
 louder-0.117
 hon-0.117
 notice-0.116
 cal-0.116
Token model
Token ID2746
Feature activation-2.05e-01

Pos logit contributions
 possession+0.229
attered+0.216
 favourite+0.207
shirt+0.192
artments+0.190
Neg logit contributions
hon-0.233
 hon-0.230
 rep-0.218
 boom-0.215
 thunder-0.214
Token to
Token ID284
Feature activation+3.29e-03

Pos logit contributions
 possession+0.363
 favourite+0.347
 favourites+0.308
attered+0.305
 favorite+0.304
Neg logit contributions
hon-0.336
 hon-0.305
 louder-0.290
 boom-0.288
 hear-0.287
Token her
Token ID607
Feature activation-1.04e-01

Pos logit contributions
hon+0.005
 notice+0.005
 rep+0.004
 hon+0.004
 cal+0.004
Neg logit contributions
 possession-0.006
 favourite-0.006
 favorite-0.006
 purse-0.005
 wrist-0.005
Token mom
Token ID1995
Feature activation-3.51e-02

Pos logit contributions
 possession+0.179
 favourite+0.162
attered+0.155
shirt+0.146
 purse+0.144
Neg logit contributions
hon-0.165
 hon-0.157
 rep-0.154
 notice-0.153
 cal-0.152
Token.
Token ID13
Feature activation-2.19e-02

Pos logit contributions
 possession+0.065
 favourite+0.063
 favorite+0.059
 purse+0.057
 wrist+0.055
Neg logit contributions
hon-0.058
 notice-0.049
 rep-0.048
 hon-0.048
 cal-0.048
Token "
Token ID366
Feature activation-1.05e-01

Pos logit contributions
 possession+0.041
 favourite+0.037
 possessions+0.033
 favorite+0.032
attered+0.032
Neg logit contributions
hon-0.037
 rep-0.035
 notice-0.034
 hear-0.033
 thunder-0.033
Token Tim
Token ID5045
Feature activation+5.17e-02

Pos logit contributions
 possession+0.033
 favourite+0.031
 favorite+0.029
 purse+0.029
 brand+0.027
Neg logit contributions
hon-0.031
 oblig-0.026
 notice-0.025
 announcements-0.025
 cal-0.025
Tokenmy
Token ID1820
Feature activation+5.89e-03

Pos logit contributions
hon+0.117
 announcements+0.104
Run+0.104
RO+0.104
 oblig+0.102
Neg logit contributions
 possession-0.071
 favorite-0.062
 favourite-0.061
 purse-0.056
 wallet-0.052
Token gave
Token ID2921
Feature activation-6.15e-02

Pos logit contributions
hon+0.010
 announcements+0.009
 boom+0.009
rr+0.009
RO+0.009
Neg logit contributions
 possession-0.010
 favourite-0.010
 favorite-0.009
 purse-0.009
 wallet-0.008
Token her
Token ID607
Feature activation-1.25e-01

Pos logit contributions
 possession+0.131
 favourite+0.127
 favorite+0.117
 purse+0.114
 wrist+0.112
Neg logit contributions
hon-0.083
 notice-0.071
 cal-0.069
 rep-0.068
 hon-0.068
Token his
Token ID465
Feature activation-1.14e-01

Pos logit contributions
 possession+0.231
 favourite+0.219
 wrist+0.196
 favorite+0.194
 purse+0.192
Neg logit contributions
hon-0.198
 notice-0.176
 cal-0.174
 hon-0.172
 louder-0.170
Token toy
Token ID13373
Feature activation-2.05e-01

Pos logit contributions
 possession+0.176
 favourite+0.157
 wrist+0.143
attered+0.141
 purse+0.140
Neg logit contributions
hon-0.211
 hon-0.195
 notice-0.194
 rep-0.192
 cal-0.189
Token makeup
Token ID16029
Feature activation-1.11e-01

Pos logit contributions
 possession+0.354
 favourite+0.330
 wrist+0.302
 purse+0.287
 favourites+0.284
Neg logit contributions
hon-0.337
 hon-0.306
 louder-0.301
 boom-0.299
 notice-0.290
Token set
Token ID900
Feature activation+5.92e-02

Pos logit contributions
 possession+0.238
 favourite+0.226
 favorite+0.204
 purse+0.201
 wrist+0.198
Neg logit contributions
hon-0.141
 notice-0.120
 rep-0.120
 hon-0.119
 cal-0.118
Token to
Token ID284
Feature activation+4.38e-02

Pos logit contributions
hon+0.108
 announcements+0.093
 rep+0.093
 notice+0.093
RO+0.092
Neg logit contributions
 possession-0.104
 favourite-0.098
 favorite-0.091
 purse-0.088
 wrist-0.082
Token play
Token ID711
Feature activation-8.31e-03

Pos logit contributions
hon+0.084
Run+0.070
 announcements+0.068
RO+0.067
Jim+0.066
Neg logit contributions
 possession-0.071
 favourite-0.070
 favorite-0.066
 brand-0.063
 purse-0.062
Token with
Token ID351
Feature activation-5.65e-02

Pos logit contributions
 possession+0.015
 favourite+0.014
 favorite+0.013
 purse+0.013
attered+0.012
Neg logit contributions
hon-0.014
 notice-0.012
 louder-0.012
 hon-0.012
 rep-0.012
Token So
Token ID1406
Feature activation+5.81e-02

Pos logit contributions
 possession+0.039
 favourite+0.035
 wrist+0.032
 purse+0.032
 favorite+0.032
Neg logit contributions
hon-0.021
 notice-0.019
 rep-0.018
 louder-0.018
 cal-0.017
Token,
Token ID11
Feature activation-1.05e-02

Pos logit contributions
hon+0.094
 announcements+0.073
 hon+0.073
 oblig+0.073
 cal+0.072
Neg logit contributions
 possession-0.117
 favourite-0.117
 favorite-0.110
 purse-0.106
 wrist-0.097
Token Lily
Token ID20037
Feature activation+2.20e-02

Pos logit contributions
 possession+0.022
 favourite+0.021
 favorite+0.020
 purse+0.019
 wrist+0.019
Neg logit contributions
hon-0.015
 notice-0.012
 rep-0.012
 hon-0.012
 cal-0.012
Token sold
Token ID2702
Feature activation-6.84e-02

Pos logit contributions
hon+0.034
 notice+0.029
 rep+0.029
 cal+0.028
 hon+0.028
Neg logit contributions
 possession-0.043
 favourite-0.041
 favorite-0.038
 purse-0.037
 wrist-0.036
Token her
Token ID607
Feature activation-1.21e-01

Pos logit contributions
 possession+0.155
 favourite+0.143
attered+0.141
robe+0.137
 wrist+0.134
Neg logit contributions
hon-0.071
 cal-0.068
 louder-0.067
 notice-0.067
 hon-0.066
Token toy
Token ID13373
Feature activation-2.04e-01

Pos logit contributions
attered+0.178
 possession+0.158
ase+0.154
umes+0.148
rolley+0.147
Neg logit contributions
 time-0.179
 hon-0.175
 sne-0.174
 rep-0.171
 mad-0.170
Token to
Token ID284
Feature activation+1.15e-02

Pos logit contributions
 possession+0.389
 favourite+0.370
 wrist+0.352
artments+0.348
attered+0.344
Neg logit contributions
hon-0.240
 hon-0.237
,"-0.201
 sne-0.188
 rep-0.185
Token the
Token ID262
Feature activation-6.68e-03

Pos logit contributions
hon+0.015
 notice+0.014
 hon+0.013
 rep+0.013
 cal+0.012
Neg logit contributions
 possession-0.025
 favourite-0.024
 favorite-0.022
attered-0.022
 purse-0.021
Token woman
Token ID2415
Feature activation-4.94e-02

Pos logit contributions
 possession+0.012
 favourite+0.011
attered+0.010
 favorite+0.009
robe+0.009
Neg logit contributions
hon-0.011
 notice-0.010
 hon-0.010
 rep-0.010
 louder-0.010
Token.
Token ID13
Feature activation-3.58e-02

Pos logit contributions
 possession+0.102
 favourite+0.097
 favorite+0.090
 purse+0.087
 wrist+0.084
Neg logit contributions
hon-0.070
 notice-0.060
 rep-0.059
 hon-0.058
 cal-0.058
Token
Token ID198
Feature activation+2.32e-02

Pos logit contributions
 possession+0.076
 favourite+0.070
 favorite+0.063
 possessions+0.062
 purse+0.062
Neg logit contributions
hon-0.050
 notice-0.044
 rep-0.043
 cal-0.042
 overcome-0.041
Token and
Token ID290
Feature activation-3.94e-02

Pos logit contributions
 possession+0.007
 favourite+0.007
 favorite+0.006
 purse+0.006
 wrist+0.006
Neg logit contributions
hon-0.005
 notice-0.004
 cal-0.004
 hon-0.004
 rep-0.004
Token gave
Token ID2921
Feature activation-5.36e-02

Pos logit contributions
 possession+0.081
 favourite+0.079
 favorite+0.074
 purse+0.071
 wrist+0.067
Neg logit contributions
hon-0.058
 notice-0.048
 rep-0.046
 announcements-0.045
 hon-0.045
Token Tim
Token ID5045
Feature activation-1.95e-02

Pos logit contributions
 possession+0.122
 favourite+0.118
 favorite+0.110
 purse+0.107
 wrist+0.105
Neg logit contributions
hon-0.066
 notice-0.054
 rep-0.053
 hon-0.053
 cal-0.053
Tokenmy
Token ID1820
Feature activation-6.77e-02

Pos logit contributions
 possession+0.040
 favourite+0.039
 favorite+0.036
 purse+0.035
 wrist+0.034
Neg logit contributions
hon-0.028
 notice-0.024
 cal-0.023
 rep-0.023
 hon-0.023
Token his
Token ID465
Feature activation-1.17e-01

Pos logit contributions
 possession+0.151
 favourite+0.144
 wrist+0.135
 purse+0.132
attered+0.132
Neg logit contributions
hon-0.075
 cal-0.072
 louder-0.064
 notice-0.064
 overcome-0.064
Token toy
Token ID13373
Feature activation-2.04e-01

Pos logit contributions
 possession+0.222
 favourite+0.203
attered+0.198
 wrist+0.196
 purse+0.186
Neg logit contributions
hon-0.159
 sne-0.152
 notice-0.151
 cal-0.151
 louder-0.149
Token back
Token ID736
Feature activation-8.72e-02

Pos logit contributions
 possession+0.397
 favourite+0.360
 wrist+0.355
artments+0.340
 purse+0.335
Neg logit contributions
 louder-0.259
hon-0.259
 sne-0.247
 hon-0.246
 boom-0.241
Token.
Token ID13
Feature activation-2.85e-02

Pos logit contributions
 possession+0.196
 favourite+0.191
 favorite+0.176
 purse+0.173
 wrist+0.170
Neg logit contributions
hon-0.100
 notice-0.086
 hon-0.083
 rep-0.083
 cal-0.081
Token
Token ID220
Feature activation-3.83e-03

Pos logit contributions
 possession+0.068
 favourite+0.064
 favorite+0.060
 purse+0.059
 wrist+0.058
Neg logit contributions
hon-0.031
 rep-0.027
 hon-0.026
 notice-0.024
 cal-0.024
Token
Token ID198
Feature activation+2.89e-02

Pos logit contributions
 possession+0.008
 favourite+0.007
 favorite+0.007
 purse+0.007
 wrist+0.006
Neg logit contributions
hon-0.006
 notice-0.005
 rep-0.005
 hon-0.005
 overcome-0.005
Token
Token ID198
Feature activation+2.46e-02

Pos logit contributions
hon+0.044
 notice+0.037
 rep+0.036
 hon+0.036
 overcome+0.036
Neg logit contributions
 possession-0.059
 favourite-0.056
 favorite-0.052
 purse-0.051
 wrist-0.049
Token to
Token ID284
Feature activation+3.94e-02

Pos logit contributions
 possession+0.039
 favourite+0.038
 favorite+0.035
 purse+0.034
 wrist+0.032
Neg logit contributions
hon-0.031
 notice-0.027
 rep-0.026
 cal-0.026
 hon-0.026
Token show
Token ID905
Feature activation-5.22e-02

Pos logit contributions
hon+0.060
 cal+0.050
 announcements+0.048
 rep+0.048
 louder+0.047
Neg logit contributions
 possession-0.078
 favourite-0.076
 favorite-0.071
 purse-0.067
 wrist-0.067
Token his
Token ID465
Feature activation-1.14e-01

Pos logit contributions
 possession+0.102
 favourite+0.095
 favorite+0.089
 purse+0.087
 wrist+0.082
Neg logit contributions
hon-0.087
 notice-0.072
 rep-0.070
 cal-0.070
 slit-0.069
Token friend
Token ID1545
Feature activation-8.75e-02

Pos logit contributions
 possession+0.196
 favourite+0.181
 purse+0.163
attered+0.162
 favorite+0.161
Neg logit contributions
hon-0.199
 hon-0.179
 rep-0.176
 cal-0.174
 notice-0.174
Token his
Token ID465
Feature activation-1.17e-01

Pos logit contributions
 possession+0.184
 favourite+0.176
 favorite+0.166
 purse+0.160
 wallet+0.150
Neg logit contributions
hon-0.130
 notice-0.107
 rep-0.105
 announcements-0.104
 oblig-0.102
Token toy
Token ID13373
Feature activation-2.04e-01

Pos logit contributions
 possession+0.197
 favourite+0.179
 purse+0.163
attered+0.162
 favorite+0.159
Neg logit contributions
hon-0.207
 hon-0.186
 rep-0.186
 notice-0.182
 cal-0.181
Token car
Token ID1097
Feature activation-1.04e-01

Pos logit contributions
 possession+0.378
 favourite+0.357
 favorite+0.321
 purse+0.319
 wrist+0.314
Neg logit contributions
hon-0.326
 hon-0.291
 rep-0.280
 louder-0.275
 overcome-0.272
Token.
Token ID13
Feature activation-3.03e-02

Pos logit contributions
 possession+0.212
 favourite+0.205
 favorite+0.193
 purse+0.185
 wrist+0.178
Neg logit contributions
hon-0.155
 notice-0.130
 cal-0.127
 announcements-0.125
 rep-0.125
Token His
Token ID2399
Feature activation-7.94e-02

Pos logit contributions
 possession+0.060
 favourite+0.056
 favorite+0.051
 purse+0.051
 wrist+0.049
Neg logit contributions
hon-0.047
 rep-0.041
 hon-0.041
 notice-0.039
 cal-0.038
Token friend
Token ID1545
Feature activation-5.33e-02

Pos logit contributions
 possession+0.149
 favourite+0.130
attered+0.123
 purse+0.122
 wrist+0.119
Neg logit contributions
hon-0.124
 hon-0.114
 rep-0.110
 louder-0.110
 overcome-0.109
Token liked
Token ID8288
Feature activation-9.86e-02

Pos logit contributions
 favourite+0.092
 possession+0.087
 favorite+0.087
 purse+0.077
 wallet+0.074
Neg logit contributions
hon-0.096
 announcements-0.081
 boom-0.080
 notice-0.079
 explode-0.078
Token Suddenly
Token ID24975
Feature activation+2.75e-02

Pos logit contributions
 possession+0.019
 favourite+0.017
 favorite+0.016
 purse+0.016
 wrist+0.015
Neg logit contributions
hon-0.013
 hon-0.011
 rep-0.011
 notice-0.011
 cal-0.011
Token,
Token ID11
Feature activation+1.38e-02

Pos logit contributions
hon+0.048
 oblig+0.043
 notice+0.042
 announcements+0.041
rr+0.041
Neg logit contributions
 favourite-0.044
 possession-0.042
 favorite-0.042
 purse-0.041
 wallet-0.038
Token he
Token ID339
Feature activation+5.01e-02

Pos logit contributions
hon+0.022
rr+0.018
 oblig+0.018
 notice+0.018
 rep+0.017
Neg logit contributions
 possession-0.026
 favourite-0.026
 favorite-0.025
 purse-0.024
 wallet-0.022
Token started
Token ID2067
Feature activation-2.79e-02

Pos logit contributions
hon+0.071
 rep+0.059
 oblig+0.058
 notice+0.058
 cal+0.057
Neg logit contributions
 possession-0.101
 favourite-0.101
 favorite-0.095
 purse-0.090
 wrist-0.086
Token to
Token ID284
Feature activation+6.97e-02

Pos logit contributions
 possession+0.041
 favourite+0.039
 favorite+0.036
 purse+0.034
 wrist+0.031
Neg logit contributions
hon-0.057
 notice-0.050
 oblig-0.049
 rep-0.049
 cal-0.049
Token sne
Token ID10505
Feature activation+1.51e-01

Pos logit contributions
hon+0.120
rr+0.104
Jim+0.103
ye+0.099
 oblig+0.097
Neg logit contributions
 favourite-0.110
 favorite-0.108
 purse-0.104
 microscope-0.101
 possession-0.101
Tokene
Token ID68
Feature activation-3.69e-02

Pos logit contributions
 rep+0.237
hon+0.224
 announcements+0.212
 hon+0.203
 louder+0.203
Neg logit contributions
 possession-0.277
 favourite-0.239
 purse-0.231
 favorite-0.224
ase-0.222
Tokenze
Token ID2736
Feature activation+2.34e-02

Pos logit contributions
 favourite+0.063
 possession+0.061
 favorite+0.060
 purse+0.057
 wrist+0.054
Neg logit contributions
hon-0.061
 oblig-0.057
 rep-0.056
 notice-0.056
 cal-0.052
Token.
Token ID13
Feature activation-1.33e-02

Pos logit contributions
hon+0.045
 oblig+0.043
 rep+0.041
 notice+0.039
 overcome+0.039
Neg logit contributions
 possession-0.032
 favourite-0.031
 favorite-0.030
robe-0.029
 purse-0.028
Token "
Token ID366
Feature activation-9.19e-02

Pos logit contributions
 possession+0.026
 favourite+0.025
 favorite+0.023
 purse+0.022
 wrist+0.021
Neg logit contributions
hon-0.021
 notice-0.018
 hon-0.018
 rep-0.018
 cal-0.017
TokenA
Token ID32
Feature activation+4.59e-02

Pos logit contributions
 possession+0.163
 favourite+0.158
 favorite+0.144
 purse+0.143
 wrist+0.137
Neg logit contributions
hon-0.147
 rep-0.132
 oblig-0.128
 cal-0.127
 overcome-0.127
Token made
Token ID925
Feature activation+3.91e-02

Pos logit contributions
 possession+0.139
 favourite+0.136
 favorite+0.127
 purse+0.122
 wrist+0.117
Neg logit contributions
hon-0.096
 notice-0.080
 rep-0.079
 cal-0.078
 oblig-0.077
Token a
Token ID257
Feature activation+3.97e-02

Pos logit contributions
hon+0.072
 rep+0.067
 oblig+0.067
 notice+0.065
 overcome+0.063
Neg logit contributions
 favourite-0.060
 favorite-0.058
 possession-0.056
 purse-0.049
 brand-0.049
Token loud
Token ID7812
Feature activation+1.50e-01

Pos logit contributions
hon+0.055
 rep+0.044
 oblig+0.043
 notice+0.040
 overcome+0.040
Neg logit contributions
 favourite-0.083
 possession-0.081
 favorite-0.080
 purse-0.076
 brand-0.073
Token and
Token ID290
Feature activation-7.94e-04

Pos logit contributions
hon+0.208
 overcome+0.201
Jim+0.195
 oblig+0.190
 rep+0.188
Neg logit contributions
 possession-0.258
 purse-0.240
 favourite-0.235
 wrist-0.235
 favorite-0.233
Token messy
Token ID24097
Feature activation+4.85e-02

Pos logit contributions
 favourite+0.001
 favorite+0.001
 possession+0.001
 brand+0.001
 purse+0.001
Neg logit contributions
hon-0.001
rr-0.001
 oblig-0.001
 overcome-0.001
 rep-0.001
Token noise
Token ID7838
Feature activation+1.35e-01

Pos logit contributions
hon+0.096
 overcome+0.083
 cal+0.082
 rep+0.081
 oblig+0.081
Neg logit contributions
 possession-0.080
 purse-0.071
 favourite-0.070
 favorite-0.067
 wrist-0.066
Token.
Token ID13
Feature activation+8.93e-03

Pos logit contributions
hon+0.235
 oblig+0.211
 rep+0.203
 overcome+0.201
rr+0.194
Neg logit contributions
 possession-0.219
 favourite-0.213
 favorite-0.205
 purse-0.186
 brand-0.178
Token
Token ID198
Feature activation+5.58e-02

Pos logit contributions
hon+0.021
 notice+0.019
 hon+0.019
 cal+0.019
 oblig+0.019
Neg logit contributions
 possession-0.009
 favourite-0.009
 favorite-0.008
 purse-0.007
 wrist-0.007
Token
Token ID198
Feature activation+4.91e-02

Pos logit contributions
hon+0.104
 rep+0.092
 notice+0.091
 cal+0.091
 hon+0.091
Neg logit contributions
 possession-0.086
 favourite-0.083
 favorite-0.075
 purse-0.071
 wrist-0.068
Token"
Token ID1
Feature activation-1.08e-01

Pos logit contributions
hon+0.077
 rep+0.071
 oblig+0.069
 cal+0.068
 hon+0.067
Neg logit contributions
 possession-0.085
 favourite-0.079
 purse-0.075
 favorite-0.071
 wrist-0.070
TokenHey
Token ID10814
Feature activation+1.25e-01

Pos logit contributions
 favourite+0.168
 possession+0.166
 favorite+0.156
 purse+0.155
 wrist+0.145
Neg logit contributions
hon-0.172
 overcome-0.162
 oblig-0.160
 cal-0.154
 rep-0.153
Token.
Token ID13
Feature activation+7.40e-03

Pos logit contributions
 possession+0.044
 favourite+0.044
 favorite+0.042
 purse+0.040
 wrist+0.037
Neg logit contributions
hon-0.046
 oblig-0.042
 overcome-0.041
Jim-0.041
 rep-0.040
Token The
Token ID383
Feature activation+1.39e-02

Pos logit contributions
hon+0.014
 notice+0.013
 cal+0.012
 oblig+0.012
 overcome+0.012
Neg logit contributions
 possession-0.011
 favourite-0.011
 favorite-0.010
 purse-0.010
 wrist-0.009
Token rocket
Token ID10701
Feature activation+1.25e-02

Pos logit contributions
hon+0.028
 notice+0.024
 rep+0.024
 oblig+0.023
 cal+0.023
Neg logit contributions
 possession-0.022
 favourite-0.021
 favorite-0.019
 purse-0.018
 wrist-0.017
Token makes
Token ID1838
Feature activation+5.04e-02

Pos logit contributions
hon+0.020
 rep+0.018
 oblig+0.018
Jim+0.017
 notice+0.017
Neg logit contributions
 favourite-0.022
 possession-0.022
 favorite-0.021
 purse-0.019
 wrist-0.019
Token another
Token ID1194
Feature activation+2.74e-02

Pos logit contributions
hon+0.089
 rep+0.086
 oblig+0.086
 notice+0.080
Run+0.078
Neg logit contributions
 favourite-0.081
 favorite-0.079
 possession-0.074
 brand-0.064
 purse-0.061
Token loud
Token ID7812
Feature activation+1.52e-01

Pos logit contributions
hon+0.045
Jim+0.037
 oblig+0.037
 overcome+0.036
 rep+0.036
Neg logit contributions
 possession-0.052
 favourite-0.051
 favorite-0.048
 brand-0.045
 wrist-0.045
Token sound
Token ID2128
Feature activation+1.16e-01

Pos logit contributions
Jud+0.224
Jim+0.222
 overcome+0.211
hon+0.210
 oblig+0.201
Neg logit contributions
 possession-0.264
 favorite-0.243
 favourite-0.239
 wrist-0.236
 brand-0.232
Token and
Token ID290
Feature activation+1.02e-02

Pos logit contributions
hon+0.220
 oblig+0.210
 rep+0.206
Jud+0.203
Jim+0.200
Neg logit contributions
 possession-0.146
 favourite-0.143
 favorite-0.141
 brand-0.122
 where-0.122
Token lifts
Token ID27103
Feature activation+8.14e-02

Pos logit contributions
hon+0.015
 oblig+0.014
Jim+0.013
rr+0.013
Jud+0.013
Neg logit contributions
 favourite-0.019
 favorite-0.019
 possession-0.018
 brand-0.017
 purse-0.016
Token off
Token ID572
Feature activation+3.13e-02

Pos logit contributions
hon+0.153
 oblig+0.144
 rep+0.143
 overcome+0.132
 achieve+0.131
Neg logit contributions
 possession-0.130
 favourite-0.124
 favorite-0.124
 purse-0.106
 item-0.098
Token.
Token ID13
Feature activation+6.18e-03

Pos logit contributions
hon+0.055
 oblig+0.050
 overcome+0.050
 rep+0.048
rr+0.047
Neg logit contributions
 possession-0.051
 favourite-0.048
 favorite-0.047
 purse-0.045
 item-0.040
Token the
Token ID262
Feature activation+4.50e-02

Pos logit contributions
hon+0.011
rr+0.009
 oblig+0.009
 announcements+0.008
 cal+0.008
Neg logit contributions
 favourite-0.010
 possession-0.010
 favorite-0.009
 purse-0.008
 wallet-0.008
Token mill
Token ID3939
Feature activation+3.17e-02

Pos logit contributions
hon+0.084
 notice+0.073
 rep+0.072
 hon+0.072
 cal+0.071
Neg logit contributions
 possession-0.075
 favourite-0.072
 favorite-0.066
 purse-0.063
 wrist-0.060
Tokener
Token ID263
Feature activation+4.14e-03

Pos logit contributions
hon+0.058
 notice+0.052
rr+0.051
 oblig+0.050
 boom+0.048
Neg logit contributions
 possession-0.046
 favourite-0.046
 purse-0.042
 favorite-0.041
 wallet-0.041
Token heard
Token ID2982
Feature activation+6.77e-02

Pos logit contributions
hon+0.007
 notice+0.006
 cal+0.006
 oblig+0.006
 announcements+0.006
Neg logit contributions
 possession-0.007
 favourite-0.007
 favorite-0.006
 purse-0.006
attered-0.006
Token loud
Token ID7812
Feature activation+1.45e-01

Pos logit contributions
hon+0.124
 oblig+0.108
 notice+0.106
 rep+0.103
 overcome+0.100
Neg logit contributions
 favourite-0.107
 possession-0.105
 favorite-0.098
 brand-0.092
 purse-0.089
Token noises
Token ID26782
Feature activation+1.34e-01

Pos logit contributions
hon+0.277
 oblig+0.256
 overcome+0.251
 notice+0.246
Jim+0.245
Neg logit contributions
 possession-0.209
 favourite-0.202
 favorite-0.186
 brand-0.175
 purse-0.173
Token outside
Token ID2354
Feature activation+2.25e-02

Pos logit contributions
hon+0.263
 oblig+0.239
Hon+0.224
 overcome+0.221
rr+0.221
Neg logit contributions
 possession-0.164
 favourite-0.163
 favorite-0.144
 brand-0.143
 purse-0.140
Token.
Token ID13
Feature activation+3.00e-03

Pos logit contributions
hon+0.043
 oblig+0.037
 cal+0.035
RO+0.034
Hon+0.034
Neg logit contributions
 possession-0.037
 favourite-0.034
 favorite-0.031
 purse-0.030
 attic-0.029
Token He
Token ID679
Feature activation+6.32e-03

Pos logit contributions
hon+0.006
 notice+0.006
 rep+0.005
 hon+0.005
 cal+0.005
Neg logit contributions
 possession-0.004
 favourite-0.004
 favorite-0.004
 purse-0.003
 wrist-0.003
Token knew
Token ID2993
Feature activation-8.60e-02

Pos logit contributions
hon+0.012
 rep+0.010
 oblig+0.010
 notice+0.010
 boom+0.010
Neg logit contributions
 favourite-0.010
 possession-0.010
 favorite-0.009
 purse-0.008
 brand-0.008
Token it
Token ID340
Feature activation-8.25e-02

Pos logit contributions
 possession+0.155
 favourite+0.148
 favorite+0.136
 purse+0.129
 wallet+0.120
Neg logit contributions
hon-0.155
 notice-0.130
 oblig-0.126
 announcements-0.124
 boom-0.123
Token who
Token ID508
Feature activation-8.59e-02

Pos logit contributions
hon+0.045
 overcome+0.041
 cal+0.040
 notice+0.040
 hon+0.039
Neg logit contributions
 possession-0.062
 favourite-0.060
attered-0.056
 purse-0.055
 favorite-0.054
Token can
Token ID460
Feature activation+1.71e-02

Pos logit contributions
 possession+0.175
 favourite+0.169
 favorite+0.155
 purse+0.155
 wrist+0.151
Neg logit contributions
hon-0.122
 notice-0.105
 overcome-0.102
 rep-0.102
 hon-0.101
Token help
Token ID1037
Feature activation+9.19e-02

Pos logit contributions
hon+0.025
 announcements+0.021
 cal+0.021
 thunder+0.021
 louder+0.021
Neg logit contributions
 favourite-0.033
 possession-0.033
 favorite-0.031
 purse-0.029
 wrist-0.029
Token you
Token ID345
Feature activation+9.82e-02

Pos logit contributions
hon+0.145
 rep+0.122
 cal+0.120
 hon+0.120
 announcements+0.118
Neg logit contributions
 possession-0.183
 favourite-0.174
 favorite-0.164
 purse-0.154
 wrist-0.148
Token when
Token ID618
Feature activation+3.85e-02

Pos logit contributions
hon+0.164
 announcements+0.135
 hon+0.134
 cal+0.134
 rep+0.134
Neg logit contributions
 possession-0.184
 favourite-0.179
 favorite-0.167
 purse-0.156
 wrist-0.153
Token you
Token ID345
Feature activation+1.33e-01

Pos logit contributions
hon+0.055
 cal+0.045
 notice+0.044
 hon+0.044
 oblig+0.043
Neg logit contributions
 possession-0.081
 favourite-0.079
 favorite-0.074
 purse-0.070
 wrist-0.067
Token need
Token ID761
Feature activation-3.15e-02

Pos logit contributions
hon+0.210
 announcements+0.184
 louder+0.177
 thunder+0.172
 hon+0.172
Neg logit contributions
 favourite-0.244
 possession-0.238
 favorite-0.228
 favorites-0.210
 purse-0.210
Token it
Token ID340
Feature activation-6.48e-02

Pos logit contributions
 possession+0.063
 favourite+0.061
 favorite+0.056
 purse+0.055
attered+0.053
Neg logit contributions
hon-0.047
 notice-0.041
 rep-0.041
 hon-0.040
 cal-0.039
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
 possession+0.126
 favourite+0.125
 favorite+0.119
 purse+0.106
 brand+0.104
Neg logit contributions
hon-0.106
 announcements-0.089
 hon-0.088
 notice-0.086
RO-0.085
Token<|endoftext|>
Token ID50256
Feature activation-1.89e-02

Pos logit contributions
 possession+0.024
 favourite+0.024
 favorite+0.022
 purse+0.022
attered+0.021
Neg logit contributions
hon-0.013
 cal-0.011
 rep-0.011
 overcome-0.010
 notice-0.010
TokenOnce
Token ID7454
Feature activation-2.16e-02

Pos logit contributions
 possession+0.030
 favourite+0.029
 favorite+0.026
 purse+0.025
 wrist+0.024
Neg logit contributions
hon-0.036
 notice-0.031
 announcements-0.031
 louder-0.031
 hon-0.031
Token sad
Token ID6507
Feature activation-3.99e-02

Pos logit contributions
 possession+0.059
 favourite+0.056
 favorite+0.051
 purse+0.051
 wrist+0.049
Neg logit contributions
hon-0.038
 hon-0.033
 cal-0.033
 notice-0.033
 louder-0.033
Token and
Token ID290
Feature activation-3.44e-02

Pos logit contributions
 possession+0.073
 favourite+0.070
 favorite+0.066
 purse+0.062
 wrist+0.058
Neg logit contributions
hon-0.069
 rep-0.057
 hon-0.057
 oblig-0.057
 cal-0.057
Token went
Token ID1816
Feature activation+6.48e-02

Pos logit contributions
 possession+0.065
 favourite+0.064
 favorite+0.063
 purse+0.059
 wallet+0.055
Neg logit contributions
hon-0.055
rr-0.045
 oblig-0.045
 notice-0.043
 overcome-0.042
Token away
Token ID1497
Feature activation-5.00e-02

Pos logit contributions
hon+0.109
 notice+0.103
 hon+0.102
 louder+0.099
 cal+0.099
Neg logit contributions
 possession-0.114
 favourite-0.110
 favorite-0.098
 wrist-0.095
 purse-0.094
Token.
Token ID13
Feature activation-3.37e-02

Pos logit contributions
 possession+0.095
 favourite+0.089
 favorite+0.084
 purse+0.080
 wrist+0.075
Neg logit contributions
hon-0.085
 announcements-0.067
 oblig-0.067
 notice-0.066
Jim-0.065
Token
Token ID198
Feature activation+2.67e-02

Pos logit contributions
 possession+0.069
 favourite+0.064
 purse+0.060
 favorite+0.059
 wrist+0.057
Neg logit contributions
hon-0.050
 notice-0.043
 rep-0.042
 overcome-0.042
 cal-0.041
Token
Token ID198
Feature activation+2.26e-02

Pos logit contributions
hon+0.043
 notice+0.037
 rep+0.037
 hon+0.036
 cal+0.036
Neg logit contributions
 possession-0.050
 favourite-0.048
 favorite-0.044
 purse-0.043
 wrist-0.041
TokenLater
Token ID18602
Feature activation-3.72e-02

Pos logit contributions
hon+0.034
 notice+0.028
 rep+0.028
 cal+0.028
 hon+0.028
Neg logit contributions
 possession-0.046
 favourite-0.044
 favorite-0.041
 purse-0.039
 wrist-0.038
Token,
Token ID11
Feature activation-1.92e-02

Pos logit contributions
 possession+0.053
 favourite+0.051
 favorite+0.047
 purse+0.047
 wallet+0.042
Neg logit contributions
hon-0.078
 announcements-0.068
 overcome-0.066
 notice-0.065
 hon-0.065
Token Fred
Token ID8559
Feature activation+6.01e-02

Pos logit contributions
 favourite+0.038
 possession+0.036
 favorite+0.035
 purse+0.031
 favourites+0.030
Neg logit contributions
hon-0.031
 cal-0.025
 announcements-0.025
 hon-0.025
 notice-0.025
Token heard
Token ID2982
Feature activation+3.53e-02

Pos logit contributions
hon+0.122
 boom+0.110
 louder+0.109
 oblig+0.109
 announcements+0.108
Neg logit contributions
 favourite-0.077
 possession-0.074
 favorite-0.074
 purse-0.067
 wallet-0.063
Token very
Token ID845
Feature activation-3.60e-02

Pos logit contributions
 favourite+0.002
 favorite+0.002
 brand+0.002
 possession+0.001
attered+0.001
Neg logit contributions
hon-0.002
 oblig-0.002
Jim-0.002
 inconvenience-0.002
Josh-0.002
Token dark
Token ID3223
Feature activation+2.67e-02

Pos logit contributions
 favourite+0.058
 favorite+0.055
 possession+0.054
 brand+0.049
attered+0.043
Neg logit contributions
hon-0.073
 oblig-0.062
rr-0.060
Jim-0.059
 rep-0.058
Token.
Token ID13
Feature activation+1.14e-03

Pos logit contributions
hon+0.053
 oblig+0.047
Jim+0.044
 overcome+0.044
 notice+0.044
Neg logit contributions
 possession-0.042
 favourite-0.041
 favorite-0.038
 brand-0.034
 purse-0.033
Token The
Token ID383
Feature activation+2.20e-03

Pos logit contributions
hon+0.003
 notice+0.002
 hon+0.002
 cal+0.002
 rep+0.002
Neg logit contributions
 favourite-0.001
 possession-0.001
 favorite-0.001
 purse-0.001
 wrist-0.001
Token little
Token ID1310
Feature activation+3.45e-02

Pos logit contributions
hon+0.004
 notice+0.004
 oblig+0.004
 rep+0.003
 overcome+0.003
Neg logit contributions
 favourite-0.004
 possession-0.004
 favorite-0.003
 purse-0.003
 wrist-0.003
Token bird
Token ID6512
Feature activation+1.86e-02

Pos logit contributions
hon+0.066
 oblig+0.058
 notice+0.058
 overcome+0.057
 rep+0.056
Neg logit contributions
 possession-0.058
 favourite-0.056
 favorite-0.053
 purse-0.051
 wrist-0.046
Token was
Token ID373
Feature activation-1.69e-02

Pos logit contributions
hon+0.034
 rep+0.030
 oblig+0.029
 announcements+0.029
 notice+0.028
Neg logit contributions
 favourite-0.031
 possession-0.030
 favorite-0.028
 purse-0.024
attered-0.023
Token so
Token ID523
Feature activation+1.20e-02

Pos logit contributions
 favourite+0.028
 possession+0.028
 favorite+0.026
 purse+0.024
 brand+0.023
Neg logit contributions
hon-0.032
 rep-0.026
 oblig-0.026
 notice-0.026
Run-0.025
Token high
Token ID1029
Feature activation+7.04e-02

Pos logit contributions
hon+0.022
 oblig+0.018
 rep+0.018
 hon+0.018
 announcements+0.018
Neg logit contributions
 favourite-0.020
 possession-0.020
 favorite-0.019
 brand-0.017
 purse-0.016
Token,
Token ID11
Feature activation-1.13e-02

Pos logit contributions
hon+0.160
 oblig+0.146
rr+0.141
 announcements+0.140
 notice+0.140
Neg logit contributions
 favourite-0.092
 possession-0.092
 favorite-0.084
 brand-0.071
 purse-0.069
Token it
Token ID340
Feature activation-2.94e-02

Pos logit contributions
 possession+0.019
 favourite+0.019
 favorite+0.017
 purse+0.016
 brand+0.015
Neg logit contributions
hon-0.021
 oblig-0.018
rr-0.017
 notice-0.017
 rep-0.017
Token,
Token ID11
Feature activation-2.31e-02

Pos logit contributions
 possession+0.050
 favourite+0.048
 purse+0.044
 favorite+0.043
 wrist+0.043
Neg logit contributions
hon-0.052
 notice-0.044
RO-0.044
 announcements-0.044
 oblig-0.043
Token and
Token ID290
Feature activation-1.75e-03

Pos logit contributions
 possession+0.040
 favourite+0.038
 favorite+0.035
 purse+0.034
 wrist+0.032
Neg logit contributions
hon-0.042
 notice-0.036
 oblig-0.035
 rep-0.035
 announcements-0.034
Token he
Token ID339
Feature activation+4.17e-02

Pos logit contributions
 possession+0.004
 favourite+0.003
 favorite+0.003
 purse+0.003
 wrist+0.003
Neg logit contributions
hon-0.003
 notice-0.002
 oblig-0.002
 rep-0.002
 announcements-0.002
Token was
Token ID373
Feature activation-7.86e-03

Pos logit contributions
hon+0.068
 notice+0.059
 rep+0.057
 cal+0.056
 announcements+0.055
Neg logit contributions
 possession-0.078
 favourite-0.075
 favorite-0.070
 purse-0.067
 wrist-0.064
Token trying
Token ID2111
Feature activation-1.34e-02

Pos logit contributions
 possession+0.013
 favourite+0.012
 favorite+0.011
 purse+0.011
 brand+0.010
Neg logit contributions
hon-0.015
 notice-0.013
 rep-0.012
 announcements-0.012
Run-0.012
Token to
Token ID284
Feature activation+3.34e-02

Pos logit contributions
 possession+0.024
 favourite+0.023
 purse+0.020
 favorite+0.020
 wrist+0.020
Neg logit contributions
hon-0.022
 notice-0.020
 louder-0.020
 overcome-0.020
 cal-0.020
Token collect
Token ID2824
Feature activation-5.42e-02

Pos logit contributions
hon+0.059
 announcements+0.051
 louder+0.047
 rep+0.047
 boom+0.046
Neg logit contributions
 possession-0.056
 favourite-0.053
 wrist-0.050
 purse-0.049
 favorite-0.049
Token wood
Token ID4898
Feature activation-2.62e-02

Pos logit contributions
 possession+0.098
 favourite+0.094
 favorite+0.086
 purse+0.083
 wrist+0.077
Neg logit contributions
hon-0.093
 notice-0.081
 rep-0.080
 hon-0.079
 oblig-0.077
Token for
Token ID329
Feature activation-7.19e-03

Pos logit contributions
 possession+0.050
 favourite+0.048
 favorite+0.044
 purse+0.042
 wrist+0.040
Neg logit contributions
hon-0.043
 notice-0.037
 rep-0.036
 hon-0.035
 cal-0.035
Token his
Token ID465
Feature activation-5.91e-02

Pos logit contributions
 possession+0.015
 favourite+0.014
 favorite+0.013
 purse+0.013
 brand+0.012
Neg logit contributions
hon-0.011
 notice-0.009
 rep-0.009
 cal-0.009
 hon-0.008
Token job
Token ID1693
Feature activation+9.48e-04

Pos logit contributions
 possession+0.095
 favourite+0.091
 favorite+0.083
 purse+0.079
 wrist+0.075
Neg logit contributions
hon-0.113
 notice-0.099
 rep-0.098
 hon-0.097
 cal-0.097
Token's
Token ID338
Feature activation-3.38e-02

Pos logit contributions
 possession+0.021
 favourite+0.020
 favorite+0.019
 purse+0.018
 wrist+0.017
Neg logit contributions
hon-0.015
 notice-0.013
 rep-0.012
 hon-0.012
 cal-0.012
Token hiding
Token ID11816
Feature activation+1.15e-03

Pos logit contributions
 possession+0.059
 favourite+0.056
 favorite+0.051
 purse+0.050
 wrist+0.048
Neg logit contributions
hon-0.058
 notice-0.051
 rep-0.050
 hon-0.050
 cal-0.050
Token spot
Token ID4136
Feature activation-6.95e-02

Pos logit contributions
hon+0.002
 notice+0.002
 rep+0.002
 hon+0.002
 cal+0.002
Neg logit contributions
 possession-0.002
 favourite-0.002
 favorite-0.002
 purse-0.002
 wrist-0.002
Token.
Token ID13
Feature activation-2.59e-03

Pos logit contributions
 possession+0.147
 favourite+0.142
 favorite+0.132
 purse+0.128
 wrist+0.123
Neg logit contributions
hon-0.097
 notice-0.081
 rep-0.079
 hon-0.079
 cal-0.078
Token<|endoftext|>
Token ID50256
Feature activation-1.36e-02

Pos logit contributions
 possession+0.004
 favourite+0.004
 favorite+0.004
 purse+0.004
 wrist+0.003
Neg logit contributions
hon-0.005
 notice-0.004
 rep-0.004
 hon-0.004
 cal-0.004
TokenJohn
Token ID7554
Feature activation+3.71e-02

Pos logit contributions
 possession+0.020
 favourite+0.019
 favorite+0.017
 purse+0.016
robe+0.016
Neg logit contributions
hon-0.027
 announcements-0.024
 louder-0.024
 notice-0.024
 hon-0.024
Token heard
Token ID2982
Feature activation+1.35e-02

Pos logit contributions
hon+0.069
 louder+0.062
 announcements+0.062
 rep+0.061
 notice+0.060
Neg logit contributions
 possession-0.059
 favourite-0.057
 favorite-0.053
 purse-0.050
 favorites-0.047
Token a
Token ID257
Feature activation+1.26e-02

Pos logit contributions
hon+0.025
 notice+0.023
 oblig+0.023
 overcome+0.022
 slit+0.022
Neg logit contributions
 favourite-0.020
 possession-0.020
 favorite-0.019
 brand-0.017
 purse-0.017
Token noise
Token ID7838
Feature activation+1.02e-01

Pos logit contributions
hon+0.017
 notice+0.013
 overcome+0.013
 oblig+0.013
 rep+0.012
Neg logit contributions
 favourite-0.026
 possession-0.026
 favorite-0.024
 purse-0.024
 brand-0.024
Token.
Token ID13
Feature activation-6.11e-02

Pos logit contributions
hon+0.190
 overcome+0.167
 oblig+0.165
 slit+0.164
 notice+0.162
Neg logit contributions
 possession-0.148
 favourite-0.148
 favorite-0.136
 brand-0.126
 purse-0.125
Token He
Token ID679
Feature activation-2.88e-02

Pos logit contributions
 possession+0.095
 favourite+0.090
 favorite+0.082
 purse+0.078
 wrist+0.075
Neg logit contributions
hon-0.119
 notice-0.104
 cal-0.103
 overcome-0.101
 rep-0.101
Token the
Token ID262
Feature activation+4.75e-02

Pos logit contributions
 possession+0.059
 favourite+0.059
 favorite+0.055
 brand+0.053
 purse+0.050
Neg logit contributions
hon-0.060
rr-0.051
 oblig-0.051
 notice-0.050
 overcome-0.047
Token sky
Token ID6766
Feature activation+5.50e-02

Pos logit contributions
hon+0.083
 oblig+0.071
qu+0.067
rr+0.066
Jim+0.065
Neg logit contributions
 favourite-0.084
 favorite-0.082
 possession-0.079
 attic-0.075
 purse-0.073
Token's
Token ID338
Feature activation-1.54e-02

Pos logit contributions
hon+0.110
 oblig+0.100
 notice+0.096
rr+0.096
 rep+0.094
Neg logit contributions
 possession-0.080
 favourite-0.078
 favorite-0.073
 brand-0.064
 purse-0.064
Token voice
Token ID3809
Feature activation+5.07e-02

Pos logit contributions
 favourite+0.030
 possession+0.030
 favorite+0.029
 purse+0.026
 brand+0.025
Neg logit contributions
hon-0.025
 oblig-0.021
 notice-0.020
Jim-0.020
 cal-0.019
Token.
Token ID13
Feature activation-1.35e-02

Pos logit contributions
hon+0.094
Jim+0.087
 oblig+0.086
 rep+0.083
Jud+0.081
Neg logit contributions
 favourite-0.078
 possession-0.077
 favorite-0.075
 purse-0.066
attered-0.065
Token
Token ID198
Feature activation+3.38e-02

Pos logit contributions
 possession+0.021
 favourite+0.020
 favorite+0.019
 purse+0.017
 wrist+0.017
Neg logit contributions
hon-0.026
 notice-0.023
 rep-0.023
 cal-0.023
 hon-0.022
Token
Token ID198
Feature activation+2.77e-02

Pos logit contributions
hon+0.061
 rep+0.053
 cal+0.053
 notice+0.053
 louder+0.052
Neg logit contributions
 possession-0.056
 favourite-0.055
 favorite-0.050
 purse-0.046
 wrist-0.045
TokenThe
Token ID464
Feature activation-1.39e-02

Pos logit contributions
hon+0.044
 rep+0.038
 notice+0.037
 cal+0.037
 oblig+0.037
Neg logit contributions
 possession-0.052
 favourite-0.051
 favorite-0.047
 purse-0.045
 wrist-0.043
Token wise
Token ID10787
Feature activation+5.11e-02

Pos logit contributions
 favourite+0.023
 favorite+0.022
 possession+0.022
 purse+0.021
 wallet+0.020
Neg logit contributions
hon-0.025
 oblig-0.020
qu-0.020
 notice-0.020
rr-0.020
Token man
Token ID582
Feature activation+1.92e-02

Pos logit contributions
hon+0.107
RO+0.095
 notice+0.095
 overcome+0.093
qu+0.093
Neg logit contributions
 possession-0.070
 favourite-0.060
 favorite-0.059
 purse-0.058
 wallet-0.056
Token went
Token ID1816
Feature activation+5.13e-02

Pos logit contributions
hon+0.036
 oblig+0.033
 notice+0.032
 rep+0.032
 announcements+0.032
Neg logit contributions
 favourite-0.026
 favorite-0.026
 possession-0.025
 purse-0.023
 wallet-0.022
Token shadow
Token ID9082
Feature activation-4.31e-02

Pos logit contributions
hon+0.041
 notice+0.036
 hon+0.036
 louder+0.036
 thunder+0.036
Neg logit contributions
 possession-0.047
 favourite-0.044
 favorite-0.040
 purse-0.040
 wrist-0.038
Token moved
Token ID3888
Feature activation+3.23e-02

Pos logit contributions
 possession+0.082
 favourite+0.079
 favorite+0.073
 purse+0.070
 wrist+0.067
Neg logit contributions
hon-0.069
 notice-0.059
 rep-0.059
 cal-0.058
 hon-0.058
Token too
Token ID1165
Feature activation+5.17e-02

Pos logit contributions
hon+0.059
 oblig+0.055
 rep+0.052
 notice+0.050
 announcements+0.050
Neg logit contributions
 possession-0.054
 favourite-0.052
 favorite-0.050
 purse-0.044
attered-0.043
Token!
Token ID0
Feature activation-2.10e-02

Pos logit contributions
hon+0.093
 oblig+0.090
 announcements+0.086
 rep+0.083
RO+0.080
Neg logit contributions
 possession-0.083
 favourite-0.074
 favorite-0.073
 purse-0.067
 wallet-0.061
Token Max
Token ID5436
Feature activation+4.22e-02

Pos logit contributions
 possession+0.044
 favourite+0.042
 favorite+0.039
 purse+0.038
 wrist+0.037
Neg logit contributions
hon-0.030
 notice-0.025
 rep-0.025
 hon-0.025
 cal-0.025
Token thought
Token ID1807
Feature activation-7.40e-02

Pos logit contributions
hon+0.068
 rep+0.059
 oblig+0.058
 notice+0.057
 cal+0.057
Neg logit contributions
 possession-0.078
 favourite-0.077
 favorite-0.072
 purse-0.068
 wrist-0.065
Token it
Token ID340
Feature activation-9.96e-02

Pos logit contributions
 possession+0.141
 favourite+0.136
 favorite+0.127
 purse+0.120
 wrist+0.114
Neg logit contributions
hon-0.120
 notice-0.102
 rep-0.102
 cal-0.100
 hon-0.099
Token was
Token ID373
Feature activation-6.01e-02

Pos logit contributions
 possession+0.179
 favourite+0.171
 favorite+0.157
 purse+0.152
 wrist+0.145
Neg logit contributions
hon-0.171
 notice-0.148
 rep-0.146
 hon-0.146
 cal-0.145
Token funny
Token ID8258
Feature activation-1.62e-03

Pos logit contributions
 favourite+0.106
 possession+0.105
 favorite+0.104
 brand+0.089
 purse+0.086
Neg logit contributions
hon-0.107
 oblig-0.092
 notice-0.089
 rep-0.087
 announcements-0.085
Token.
Token ID13
Feature activation-3.07e-02

Pos logit contributions
 possession+0.003
 favourite+0.003
 favorite+0.003
 purse+0.003
 wrist+0.003
Neg logit contributions
hon-0.003
 notice-0.002
 rep-0.002
 oblig-0.002
 cal-0.002
Token He
Token ID679
Feature activation-2.21e-02

Pos logit contributions
 possession+0.060
 favourite+0.056
 favorite+0.051
 purse+0.051
 wrist+0.049
Neg logit contributions
hon-0.049
 notice-0.042
 hon-0.042
 rep-0.041
 cal-0.041
Token frustrated
Token ID14718
Feature activation-2.16e-02

Pos logit contributions
 possession+0.024
 favourite+0.023
 favorite+0.022
 purse+0.021
 wrist+0.020
Neg logit contributions
hon-0.016
 notice-0.013
 rep-0.013
 hon-0.013
 cal-0.013
Token,
Token ID11
Feature activation-2.97e-02

Pos logit contributions
 possession+0.038
 favourite+0.037
 favorite+0.034
 purse+0.031
 brand+0.030
Neg logit contributions
hon-0.039
 oblig-0.033
RO-0.033
 announcements-0.032
 notice-0.032
Token when
Token ID618
Feature activation+3.59e-02

Pos logit contributions
 possession+0.051
 favourite+0.050
 favorite+0.046
 purse+0.043
 wrist+0.041
Neg logit contributions
hon-0.054
 oblig-0.045
 rep-0.044
 cal-0.044
 notice-0.044
Token he
Token ID339
Feature activation+5.72e-02

Pos logit contributions
hon+0.059
 cal+0.046
rr+0.046
 notice+0.045
 announcements+0.045
Neg logit contributions
 possession-0.071
 favourite-0.071
 favorite-0.064
 purse-0.058
 brand-0.057
Token spotted
Token ID13489
Feature activation-4.85e-02

Pos logit contributions
hon+0.095
 boom+0.077
 hon+0.077
 announcements+0.076
 rep+0.076
Neg logit contributions
 possession-0.106
 favourite-0.105
 favorite-0.097
 purse-0.093
 wallet-0.088
Token something
Token ID1223
Feature activation-9.85e-03

Pos logit contributions
 possession+0.099
 favourite+0.094
 favorite+0.088
 purse+0.086
 wrist+0.085
Neg logit contributions
hon-0.069
 rep-0.060
 notice-0.059
 hon-0.059
 cal-0.059
Token in
Token ID287
Feature activation+1.15e-02

Pos logit contributions
 possession+0.019
 favourite+0.017
 wrist+0.016
 favorite+0.016
 purse+0.016
Neg logit contributions
hon-0.015
 rep-0.014
 louder-0.014
 hon-0.014
 notice-0.013
Token the
Token ID262
Feature activation+3.63e-02

Pos logit contributions
hon+0.014
 notice+0.011
 rep+0.011
 hon+0.011
 cal+0.011
Neg logit contributions
 possession-0.027
 favourite-0.026
 favorite-0.024
 purse-0.024
 wrist-0.023
Token bushes
Token ID37413
Feature activation-2.99e-03

Pos logit contributions
hon+0.057
 hon+0.057
 cal+0.056
 notice+0.056
 thunder+0.055
Neg logit contributions
 possession-0.062
 favourite-0.060
 favorite-0.054
 favourites-0.051
 favorites-0.051
Token!
Token ID0
Feature activation-1.39e-02

Pos logit contributions
 possession+0.006
 favourite+0.006
 favorite+0.006
 purse+0.006
 wrist+0.005
Neg logit contributions
hon-0.004
 notice-0.003
 rep-0.003
 hon-0.003
 cal-0.003
Token It
Token ID632
Feature activation-8.04e-02

Pos logit contributions
 possession+0.030
 favourite+0.026
 wrist+0.026
 favorite+0.026
 purse+0.026
Neg logit contributions
hon-0.018
 rep-0.017
 thunder-0.015
Run-0.015
 hon-0.015
Token wet
Token ID9583
Feature activation+6.08e-02

Pos logit contributions
hon+0.058
 notice+0.050
 hon+0.049
 rep+0.049
 cal+0.049
Neg logit contributions
 possession-0.066
 favourite-0.063
 favorite-0.057
 purse-0.056
 wrist-0.054
Token floor
Token ID4314
Feature activation-1.34e-03

Pos logit contributions
hon+0.091
 notice+0.077
 hon+0.076
 rep+0.076
 cal+0.075
Neg logit contributions
 possession-0.122
 favourite-0.118
 favorite-0.109
 purse-0.105
 wrist-0.101
Token.
Token ID13
Feature activation+6.98e-03

Pos logit contributions
 possession+0.002
 favourite+0.002
 favorite+0.002
 purse+0.002
 wrist+0.002
Neg logit contributions
hon-0.002
 oblig-0.002
RO-0.002
 rep-0.002
 announcements-0.002
Token He
Token ID679
Feature activation+9.64e-03

Pos logit contributions
hon+0.011
 notice+0.009
 rep+0.009
 hon+0.009
 cal+0.009
Neg logit contributions
 possession-0.014
 favourite-0.013
 purse-0.012
 favorite-0.012
 wrist-0.012
Token fell
Token ID3214
Feature activation+5.19e-02

Pos logit contributions
hon+0.014
 rep+0.012
 oblig+0.011
 notice+0.011
 cal+0.011
Neg logit contributions
 possession-0.020
 favourite-0.019
 favorite-0.019
 purse-0.017
attered-0.017
Token and
Token ID290
Feature activation-2.10e-02

Pos logit contributions
hon+0.096
 oblig+0.084
 rep+0.083
 notice+0.083
 cal+0.082
Neg logit contributions
 possession-0.085
 favourite-0.081
 favorite-0.076
 purse-0.072
attered-0.068
Token hurt
Token ID5938
Feature activation+6.26e-02

Pos logit contributions
 possession+0.042
 favourite+0.041
 favorite+0.040
attered+0.037
 purse+0.037
Neg logit contributions
hon-0.029
 oblig-0.026
 rep-0.025
rr-0.024
 announcements-0.024
Token his
Token ID465
Feature activation-4.22e-02

Pos logit contributions
hon+0.106
 oblig+0.093
 rep+0.091
 notice+0.087
 cal+0.087
Neg logit contributions
 possession-0.113
 favourite-0.108
 favorite-0.103
 purse-0.097
 wrist-0.091
Token knee
Token ID10329
Feature activation-1.46e-02

Pos logit contributions
 possession+0.064
 favourite+0.060
 favorite+0.054
 purse+0.052
 wrist+0.049
Neg logit contributions
hon-0.084
 notice-0.074
 hon-0.074
 rep-0.074
 cal-0.073
Token.
Token ID13
Feature activation+6.77e-03

Pos logit contributions
 possession+0.024
 favourite+0.024
 favorite+0.023
 purse+0.022
attered+0.021
Neg logit contributions
hon-0.026
 oblig-0.025
Jim-0.023
 rep-0.023
RO-0.022
Token He
Token ID679
Feature activation+8.15e-03

Pos logit contributions
hon+0.010
 notice+0.009
 rep+0.009
 hon+0.009
 cal+0.009
Neg logit contributions
 possession-0.013
 favourite-0.013
 favorite-0.012
 purse-0.012
 wrist-0.011
TokenOne
Token ID3198
Feature activation-6.08e-02

Pos logit contributions
 possession+0.031
 favourite+0.031
 favorite+0.027
 purse+0.026
robe+0.026
Neg logit contributions
hon-0.040
 announcements-0.036
 notice-0.035
 hon-0.035
 louder-0.035
Token day
Token ID1110
Feature activation-2.30e-02

Pos logit contributions
 possession+0.092
 favourite+0.091
 favorite+0.083
 purse+0.073
 wrist+0.066
Neg logit contributions
hon-0.127
 announcements-0.112
 notice-0.110
 rep-0.109
 cal-0.109
Token,
Token ID11
Feature activation-5.84e-02

Pos logit contributions
 favourite+0.044
 possession+0.041
 favorite+0.040
 purse+0.038
 wallet+0.034
Neg logit contributions
hon-0.038
 cal-0.034
 announcements-0.033
 hon-0.032
 explode-0.031
Token a
Token ID257
Feature activation+1.83e-02

Pos logit contributions
 possession+0.129
 favourite+0.122
 favorite+0.114
 purse+0.112
 wrist+0.111
Neg logit contributions
hon-0.076
 notice-0.063
 rep-0.062
 hon-0.061
 louder-0.058
Token brave
Token ID14802
Feature activation+7.94e-02

Pos logit contributions
hon+0.032
 notice+0.027
 overcome+0.026
 rep+0.026
 announcements+0.026
Neg logit contributions
 possession-0.033
 favourite-0.032
 favorite-0.030
 purse-0.029
 wallet-0.027
Token pirate
Token ID25868
Feature activation+2.65e-03

Pos logit contributions
hon+0.152
 overcome+0.146
 notice+0.136
 collapse+0.134
 announcements+0.134
Neg logit contributions
 possession-0.125
 favourite-0.117
 favorite-0.113
 purse-0.110
 wallet-0.100
Token went
Token ID1816
Feature activation+3.44e-02

Pos logit contributions
hon+0.005
 cal+0.005
 louder+0.005
 announcements+0.005
 notice+0.005
Neg logit contributions
 possession-0.004
 favourite-0.004
 favorite-0.004
 purse-0.003
 wallet-0.003
Token on
Token ID319
Feature activation-4.00e-02

Pos logit contributions
hon+0.075
 notice+0.068
 cal+0.067
 announcements+0.067
 rep+0.067
Neg logit contributions
 possession-0.043
 favourite-0.042
 favorite-0.039
 purse-0.033
 brand-0.032
Token a
Token ID257
Feature activation+7.28e-03

Pos logit contributions
 possession+0.074
 favourite+0.072
 favorite+0.067
 purse+0.062
 brand+0.059
Neg logit contributions
hon-0.068
 notice-0.057
 cal-0.057
 oblig-0.056
 louder-0.055
Token journey
Token ID7002
Feature activation+4.61e-02

Pos logit contributions
hon+0.013
 rep+0.011
 cal+0.011
 notice+0.011
 oblig+0.011
Neg logit contributions
 possession-0.013
 favourite-0.013
 favorite-0.012
 purse-0.011
 brand-0.010
Token.
Token ID13
Feature activation-5.07e-02

Pos logit contributions
hon+0.085
 cal+0.076
 announcements+0.074
 rep+0.072
 slit+0.072
Neg logit contributions
 possession-0.080
 favourite-0.073
 favorite-0.068
 purse-0.060
 wrist-0.058
Token they
Token ID484
Feature activation+6.62e-02

Pos logit contributions
 possession+0.030
 favourite+0.029
 purse+0.027
 favorite+0.027
 wrist+0.026
Neg logit contributions
hon-0.014
 hon-0.012
 rep-0.012
 notice-0.012
 louder-0.011
Token both
Token ID1111
Feature activation-6.67e-03

Pos logit contributions
hon+0.094
 notice+0.082
 hon+0.079
 rep+0.078
 overcome+0.078
Neg logit contributions
 possession-0.139
 favourite-0.132
 favorite-0.121
 purse-0.121
 wrist-0.117
Token loved
Token ID6151
Feature activation-5.55e-02

Pos logit contributions
 possession+0.009
 favourite+0.009
 favorite+0.008
 purse+0.007
attered+0.006
Neg logit contributions
hon-0.015
 rep-0.013
 cal-0.013
 louder-0.013
 announcements-0.013
Token animals
Token ID4695
Feature activation+2.68e-02

Pos logit contributions
 possession+0.090
 favourite+0.086
 favorite+0.080
 purse+0.073
 wrist+0.069
Neg logit contributions
hon-0.108
 notice-0.094
 cal-0.093
 oblig-0.093
 rep-0.092
Token.
Token ID13
Feature activation-1.60e-02

Pos logit contributions
hon+0.040
 notice+0.033
 rep+0.033
 oblig+0.032
 cal+0.032
Neg logit contributions
 possession-0.055
 favourite-0.053
 favorite-0.051
 purse-0.048
 wrist-0.045
Token One
Token ID1881
Feature activation-3.36e-02

Pos logit contributions
 possession+0.035
 favourite+0.031
 purse+0.030
 wrist+0.029
 favorite+0.029
Neg logit contributions
hon-0.022
 rep-0.018
 notice-0.018
 hon-0.018
 thunder-0.017
Token day
Token ID1110
Feature activation+6.38e-03

Pos logit contributions
 possession+0.060
 favourite+0.057
 favorite+0.052
 purse+0.051
 wrist+0.049
Neg logit contributions
hon-0.058
 notice-0.050
 hon-0.050
 rep-0.050
 cal-0.049
Token,
Token ID11
Feature activation-1.49e-02

Pos logit contributions
hon+0.007
 notice+0.006
 rep+0.006
 cal+0.006
 hon+0.006
Neg logit contributions
 possession-0.015
 favourite-0.015
 favorite-0.014
 purse-0.013
 wrist-0.013
Token there
Token ID612
Feature activation-2.41e-02

Pos logit contributions
 possession+0.035
 favourite+0.034
 favorite+0.032
 purse+0.031
 wrist+0.030
Neg logit contributions
hon-0.017
 notice-0.014
 rep-0.014
 cal-0.014
 hon-0.013
Token was
Token ID373
Feature activation-1.01e-02

Pos logit contributions
 possession+0.050
 favourite+0.046
 purse+0.043
 wrist+0.042
 favorite+0.042
Neg logit contributions
hon-0.036
 notice-0.031
 overcome-0.031
 hon-0.030
 hear-0.030
Token an
Token ID281
Feature activation+4.17e-02

Pos logit contributions
 possession+0.020
 favourite+0.020
 favorite+0.018
 purse+0.017
 wrist+0.017
Neg logit contributions
hon-0.015
 notice-0.013
 rep-0.013
 cal-0.013
 hon-0.013
Token a
Token ID257
Feature activation+5.44e-02

Pos logit contributions
 favourite+0.038
 possession+0.036
 favorite+0.036
 purse+0.034
 wallet+0.032
Neg logit contributions
hon-0.040
 overcome-0.033
 announcements-0.033
 cal-0.033
 notice-0.033
Tokenpron
Token ID31186
Feature activation-3.31e-02

Pos logit contributions
hon+0.110
 notice+0.097
 rep+0.096
 cal+0.096
 hon+0.095
Neg logit contributions
 possession-0.080
 favourite-0.077
 favorite-0.070
 purse-0.067
 wrist-0.063
Token.
Token ID13
Feature activation-1.77e-02

Pos logit contributions
 possession+0.067
 favourite+0.065
 favorite+0.061
 purse+0.059
 wrist+0.057
Neg logit contributions
hon-0.049
 notice-0.041
 cal-0.041
 rep-0.040
 overcome-0.040
Token
Token ID198
Feature activation+3.94e-02

Pos logit contributions
 possession+0.027
 favourite+0.026
 favorite+0.024
 purse+0.023
 wrist+0.022
Neg logit contributions
hon-0.035
 notice-0.031
 rep-0.030
 hon-0.030
 cal-0.030
Token
Token ID198
Feature activation+3.31e-02

Pos logit contributions
hon+0.069
 notice+0.060
 rep+0.060
 cal+0.060
 hon+0.059
Neg logit contributions
 possession-0.067
 favourite-0.064
 favorite-0.059
 purse-0.057
 wrist-0.054
Token"
Token ID1
Feature activation-1.21e-01

Pos logit contributions
hon+0.059
 cal+0.054
 slit+0.053
 rep+0.053
 hon+0.052
Neg logit contributions
 possession-0.050
 favourite-0.048
 purse-0.045
 wrist-0.044
 favorite-0.042
TokenI
Token ID40
Feature activation+3.60e-02

Pos logit contributions
 possession+0.201
 favourite+0.197
 favorite+0.182
 purse+0.172
 wrist+0.166
Neg logit contributions
hon-0.210
 notice-0.187
 cal-0.187
 rep-0.183
 overcome-0.182
Token do
Token ID466
Feature activation+3.53e-02

Pos logit contributions
hon+0.056
 louder+0.050
 thunder+0.049
 announcements+0.049
 cal+0.049
Neg logit contributions
 favourite-0.067
 possession-0.065
 favorite-0.064
 purse-0.057
 favorites-0.057
Token,
Token ID11
Feature activation-2.60e-03

Pos logit contributions
hon+0.058
 notice+0.050
 cal+0.050
 rep+0.048
 louder+0.047
Neg logit contributions
 possession-0.066
 favourite-0.065
 favorite-0.060
 purse-0.056
 wrist-0.055
Token I
Token ID314
Feature activation+4.28e-02

Pos logit contributions
 favourite+0.005
 possession+0.004
 favorite+0.004
 purse+0.004
 wrist+0.004
Neg logit contributions
hon-0.005
 notice-0.004
 overcome-0.004
 oblig-0.004
 announcements-0.004
Token do
Token ID466
Feature activation+4.21e-02

Pos logit contributions
hon+0.071
 announcements+0.063
 thunder+0.062
 louder+0.061
 cal+0.061
Neg logit contributions
 favourite-0.077
 possession-0.073
 favorite-0.073
 favorites-0.065
 favourites-0.065
Token was
Token ID373
Feature activation-5.34e-02

Pos logit contributions
 possession+0.004
 favourite+0.004
 favorite+0.004
 purse+0.004
 wrist+0.003
Neg logit contributions
hon-0.006
 hon-0.005
 notice-0.005
 rep-0.005
 cal-0.005
Token a
Token ID257
Feature activation+1.41e-02

Pos logit contributions
 possession+0.099
 favourite+0.092
 purse+0.083
 favorite+0.083
 wrist+0.081
Neg logit contributions
hon-0.089
 hon-0.078
 notice-0.076
 rep-0.076
 cal-0.075
Token very
Token ID845
Feature activation-3.98e-02

Pos logit contributions
hon+0.020
 hon+0.019
 notice+0.018
 sne+0.017
 rep+0.017
Neg logit contributions
 possession-0.028
 favourite-0.026
attered-0.024
 purse-0.024
 wrist-0.024
Token happy
Token ID3772
Feature activation-4.09e-02

Pos logit contributions
 possession+0.074
 favourite+0.070
 favorite+0.063
 purse+0.063
 wrist+0.061
Neg logit contributions
hon-0.065
 hon-0.056
 notice-0.056
 rep-0.055
 cal-0.054
Token seal
Token ID13810
Feature activation-7.39e-02

Pos logit contributions
 possession+0.076
 favourite+0.073
 favorite+0.067
 purse+0.065
 wrist+0.062
Neg logit contributions
hon-0.067
 notice-0.058
 hon-0.057
 rep-0.057
 cal-0.056
Token who
Token ID508
Feature activation-1.20e-01

Pos logit contributions
 possession+0.156
 favourite+0.151
 purse+0.141
 favorite+0.138
 wrist+0.137
Neg logit contributions
hon-0.096
 hon-0.082
 rep-0.076
 cal-0.075
 notice-0.074
Token loved
Token ID6151
Feature activation-8.13e-02

Pos logit contributions
 possession+0.186
 favourite+0.175
 purse+0.164
 wrist+0.156
 favorite+0.153
Neg logit contributions
hon-0.229
 hon-0.212
 notice-0.194
 cal-0.191
 overcome-0.191
Token to
Token ID284
Feature activation+5.05e-02

Pos logit contributions
 possession+0.140
 favourite+0.134
 favorite+0.121
 purse+0.121
 wrist+0.117
Neg logit contributions
hon-0.144
 hon-0.127
 rep-0.124
 notice-0.124
 cal-0.121
Token hop
Token ID1725
Feature activation+1.61e-02

Pos logit contributions
hon+0.081
 cal+0.071
 louder+0.070
 announcements+0.068
 rep+0.067
Neg logit contributions
 favourite-0.094
 possession-0.093
 favorite-0.088
 purse-0.081
 wrist-0.081
Token around
Token ID1088
Feature activation-7.19e-02

Pos logit contributions
hon+0.033
 notice+0.029
 hon+0.029
 rep+0.028
 cal+0.028
Neg logit contributions
 possession-0.024
 favourite-0.023
 favorite-0.020
 purse-0.020
 wrist-0.019
Token on
Token ID319
Feature activation-1.34e-02

Pos logit contributions
 possession+0.136
 favourite+0.133
 favorite+0.123
 purse+0.112
 wrist+0.109
Neg logit contributions
hon-0.118
 cal-0.100
 notice-0.100
 announcements-0.099
 rep-0.097
Token hug
Token ID16225
Feature activation-1.84e-02

Pos logit contributions
hon+0.053
 notice+0.044
 rep+0.042
 hon+0.042
 overcome+0.042
Neg logit contributions
 possession-0.083
 favourite-0.080
 favorite-0.074
 purse-0.073
 wrist-0.070
Token.
Token ID13
Feature activation-2.72e-02

Pos logit contributions
 possession+0.040
 favourite+0.039
 favorite+0.036
 purse+0.035
 wrist+0.034
Neg logit contributions
hon-0.024
 notice-0.020
 rep-0.020
 hon-0.019
 cal-0.019
Token She
Token ID1375
Feature activation-5.02e-02

Pos logit contributions
 possession+0.055
 favourite+0.051
 favorite+0.048
 purse+0.046
attered+0.045
Neg logit contributions
hon-0.042
 rep-0.037
 hon-0.035
 notice-0.034
 cal-0.034
Token said
Token ID531
Feature activation-2.36e-02

Pos logit contributions
 possession+0.101
 favourite+0.099
 favorite+0.093
 purse+0.088
 wrist+0.085
Neg logit contributions
hon-0.074
 notice-0.062
 rep-0.061
 hon-0.060
 cal-0.060
Token:
Token ID25
Feature activation-1.49e-01

Pos logit contributions
 favourite+0.045
 possession+0.045
 favorite+0.043
 purse+0.041
 brand+0.038
Neg logit contributions
hon-0.036
 notice-0.032
RO-0.030
 overcome-0.030
 announcements-0.030
Token "
Token ID366
Feature activation-1.38e-01

Pos logit contributions
 possession+0.184
 favourite+0.169
 favorite+0.149
 purse+0.141
 wrist+0.129
Neg logit contributions
hon-0.341
 rep-0.307
 notice-0.306
 hon-0.303
 cal-0.301
TokenIt
Token ID1026
Feature activation-5.30e-02

Pos logit contributions
 possession+0.205
 favourite+0.198
 favorite+0.176
 purse+0.168
 wrist+0.165
Neg logit contributions
hon-0.269
 cal-0.240
 notice-0.240
 hon-0.239
 overcome-0.238
Token's
Token ID338
Feature activation-6.15e-02

Pos logit contributions
 favourite+0.083
 possession+0.080
 favorite+0.078
robe+0.066
 purse+0.065
Neg logit contributions
hon-0.104
 notice-0.094
 oblig-0.089
 announcements-0.089
 rep-0.088
Token all
Token ID477
Feature activation-3.75e-02

Pos logit contributions
 favourite+0.135
 possession+0.131
 favorite+0.130
 brand+0.118
 purse+0.115
Neg logit contributions
hon-0.088
 oblig-0.067
 notice-0.067
 announcements-0.066
 slit-0.064
Token right
Token ID826
Feature activation+7.61e-02

Pos logit contributions
 possession+0.064
 favourite+0.062
 favorite+0.060
 brand+0.053
 purse+0.050
Neg logit contributions
hon-0.070
 notice-0.060
 oblig-0.059
 slit-0.059
 announcements-0.059
Token,
Token ID11
Feature activation-1.54e-02

Pos logit contributions
hon+0.120
 notice+0.100
 hon+0.098
 rep+0.097
 cal+0.097
Neg logit contributions
 possession-0.154
 favourite-0.147
 favorite-0.138
 purse-0.130
 wrist-0.124
Token mom
Token ID1995
Feature activation-1.03e-02

Pos logit contributions
 possession+0.103
 favourite+0.088
attered+0.083
 wrist+0.080
 favorite+0.079
Neg logit contributions
hon-0.111
 rep-0.104
 notice-0.101
 overcome-0.100
 cal-0.099
Tokenmy
Token ID1820
Feature activation-1.21e-02

Pos logit contributions
 favourite+0.019
 possession+0.018
 favorite+0.017
 purse+0.017
 wallet+0.016
Neg logit contributions
hon-0.017
 notice-0.014
 announcements-0.014
 boom-0.014
 cal-0.014
Token showed
Token ID3751
Feature activation-1.24e-01

Pos logit contributions
 favourite+0.022
 possession+0.022
 favorite+0.020
 purse+0.020
 wallet+0.018
Neg logit contributions
hon-0.020
 boom-0.017
 notice-0.017
 announcements-0.017
 louder-0.016
Token her
Token ID607
Feature activation-1.58e-01

Pos logit contributions
 possession+0.221
 favourite+0.212
 favorite+0.195
 purse+0.188
 wrist+0.178
Neg logit contributions
hon-0.214
 notice-0.186
 rep-0.183
 hon-0.182
 cal-0.181
Token a
Token ID257
Feature activation-4.40e-02

Pos logit contributions
 possession+0.319
 favourite+0.302
 favorite+0.279
attered+0.279
 wrist+0.273
Neg logit contributions
hon-0.214
 rep-0.188
 notice-0.186
 cal-0.186
 hon-0.181
Token pair
Token ID5166
Feature activation-1.38e-01

Pos logit contributions
 possession+0.077
 favourite+0.071
attered+0.068
 favorite+0.065
 wrist+0.064
Neg logit contributions
hon-0.070
 rep-0.065
 hon-0.065
 notice-0.064
 cal-0.063
Token of
Token ID286
Feature activation-5.74e-03

Pos logit contributions
 favourite+0.350
 possession+0.347
 favorite+0.333
 favorites+0.330
 favourites+0.319
Neg logit contributions
hon-0.117
 notice-0.095
 hear-0.090
 hon-0.086
 rep-0.085
Token sunglasses
Token ID36251
Feature activation-7.57e-02

Pos logit contributions
 possession+0.009
 favourite+0.008
 favorite+0.007
 purse+0.007
 wrist+0.007
Neg logit contributions
hon-0.011
 notice-0.010
 rep-0.010
 hon-0.010
 cal-0.010
Token.
Token ID13
Feature activation-3.54e-02

Pos logit contributions
 possession+0.156
 favourite+0.148
 favorite+0.137
 purse+0.131
 wrist+0.128
Neg logit contributions
hon-0.108
 rep-0.094
 notice-0.092
 hon-0.091
 overcome-0.088
Token They
Token ID1119
Feature activation+4.73e-02

Pos logit contributions
 possession+0.062
 favourite+0.057
 favorite+0.052
 purse+0.049
 wrist+0.048
Neg logit contributions
hon-0.063
 notice-0.056
 rep-0.056
 hon-0.054
 louder-0.053
Token were
Token ID547
Feature activation-1.19e-03

Pos logit contributions
hon+0.060
 notice+0.053
 rep+0.052
 hon+0.051
 overcome+0.048
Neg logit contributions
 possession-0.107
 favourite-0.098
 favorite-0.092
 purse-0.091
 wrist-0.089
Token L
Token ID406
Feature activation+4.26e-02

Pos logit contributions
 possession+0.099
 favourite+0.095
 favorite+0.088
 purse+0.086
 wrist+0.082
Neg logit contributions
hon-0.092
 notice-0.081
 hon-0.077
 announcements-0.077
 cal-0.077
Tokenulu
Token ID15712
Feature activation-5.33e-03

Pos logit contributions
hon+0.071
 notice+0.059
 rep+0.059
 cal+0.058
 hon+0.058
Neg logit contributions
 possession-0.080
 favourite-0.078
 favorite-0.072
 purse-0.068
 wrist-0.067
Token.
Token ID13
Feature activation-4.56e-02

Pos logit contributions
 possession+0.009
 favourite+0.008
 purse+0.008
 favorite+0.008
 wrist+0.007
Neg logit contributions
hon-0.010
 announcements-0.009
RO-0.009
 notice-0.008
Hon-0.008
Token
Token ID198
Feature activation+1.95e-02

Pos logit contributions
 possession+0.073
 favourite+0.067
 favorite+0.060
 purse+0.059
 wrist+0.056
Neg logit contributions
hon-0.089
 rep-0.080
 hon-0.079
 notice-0.077
 cal-0.077
Token
Token ID198
Feature activation+1.66e-02

Pos logit contributions
hon+0.033
 notice+0.029
 cal+0.028
 rep+0.028
 hon+0.028
Neg logit contributions
 possession-0.035
 favourite-0.034
 favorite-0.031
 purse-0.029
 wrist-0.028
Token"
Token ID1
Feature activation-1.30e-01

Pos logit contributions
hon+0.025
 notice+0.021
 rep+0.020
 cal+0.020
 hon+0.020
Neg logit contributions
 possession-0.034
 favourite-0.032
 favorite-0.030
 purse-0.029
 wrist-0.028
TokenMy
Token ID3666
Feature activation-9.35e-02

Pos logit contributions
 possession+0.206
 favourite+0.199
 favorite+0.180
 purse+0.173
 wrist+0.165
Neg logit contributions
hon-0.249
 notice-0.220
 cal-0.216
 hon-0.215
 rep-0.214
Token tail
Token ID7894
Feature activation-6.27e-02

Pos logit contributions
 possession+0.153
 favourite+0.128
attered+0.121
 purse+0.119
artments+0.114
Neg logit contributions
hon-0.161
 sne-0.151
 notice-0.147
 hear-0.147
 louder-0.147
Token is
Token ID318
Feature activation-3.58e-02

Pos logit contributions
 possession+0.114
 favourite+0.110
 favorite+0.103
 purse+0.098
 wrist+0.094
Neg logit contributions
hon-0.106
 notice-0.090
 rep-0.089
 oblig-0.088
 announcements-0.088
Token stuck
Token ID7819
Feature activation-5.45e-03

Pos logit contributions
 possession+0.065
 favourite+0.063
 favorite+0.058
 purse+0.055
 wrist+0.052
Neg logit contributions
hon-0.062
 notice-0.053
 rep-0.052
 hon-0.051
 cal-0.051
Token!"
Token ID2474
Feature activation+6.14e-02

Pos logit contributions
 possession+0.010
 favourite+0.009
 favorite+0.009
 purse+0.008
attered+0.008
Neg logit contributions
hon-0.009
 announcements-0.008
 oblig-0.008
 cal-0.008
 notice-0.008