TOP ACTIVATIONS
MAX = 0.768

Power Point slide PNG larger image larg
one a babys itter between 2002 and 2003 . Jim
2010 boys beware Reviewer : j wt 0001 -
, I think Reviewer : B iz r Pix
iff Tra x Reviewer : V the Happy L
was about homosexuality Reviewer : k imp unk rock
things like Sm ile if you masturb ate
bad idea . Reviewer : Mike M anners -
house , gay ish dance trou pe , and foam parties
er magnet ? Reviewer : hey _ ler oy
was eaten by a crocod ile that was never caught .
2 , 370 pound crocod ile . Two years ago ,
i Spe lling was a trou per and stuck through her
Song - B obs To ilet - A J Po opy
that they saw a crocod ile kill a water buffalo this
s right in - between , at 32 %. A
it 's the largest crocod ile ever to be taken alive
are Here .... Reviewer : SAS K ATCH EW
one element of a tri pty ch called Echo that Indigenous
45 366 . Topics : community - and -

MIN ACTIVATIONS
MIN = -0.772

Un ilateral de Ind epend encia ) could be re ph
uman and Saur on kill Bor om ir and capture Merry
t even been on the disabled list since his previous Tommy
really great less - f requently used options to consider .
K aff ir lime leaves impart intense fruit iness without the
all the right things goal keepers should ," Y all op
G ess berg witz West chester 1 hour ago Pretty simple
Gutenberg ( www . g utenberg . org ). Any file
should stay in the mountain shack , and please rest and
16 , 1981 Birth place : Long Beach ,
At G f inity 3 r ai N had
who , unlike his brother Bor om ir , resists the
ik ov and And rey Bor isen ko is scheduled to
s agent , Scott Bor as . With the slot
small distance to the mountain shack , and by the time
total mass that the v ort ons carry needs to match
publication in the Ast roph ysical Journal ( ar X iv
format , enabling a single binary package to work perfectly and
Get Mass ( ambient D ensity ). // This is because
Far rah W ether s Mysteries , comic book short stories

INTERVAL 0.383 - 0.768
CONTAINS 0.295%

Bal rog . Gand alf faces the Bal rog , and
come . She finds a sword , hops on her dragon
gamble ' While Lord Hes elt ine , a
ache and a bit of Paul Newman about him '. Photograph
ists have been present in Greece from the 1900

INTERVAL -0.002 - 0.383
CONTAINS 50.520%

communities that bear the extraction costs . L NG
lan ak ila i ā Kal an ial i
which you can 't really pick out with the camera in
but he might also have one caveat . Yes , his
appreciated that they were able to keep things fresh with The

INTERVAL -0.387 - -0.002
CONTAINS 48.876%

the broader context of a highly competitive industry , many of
below to become an In Daily supporter . Powered by Press
void V ort on Sim :: Pop ulate D ensity
He began training the turtles in the art of nin j
One Jill ste in supporter told us three whole buses of

INTERVAL -0.772 - -0.387
CONTAINS 0.308%

one of my favorite fl ours to work with , although
String Al ignment ] :: Center $ s Format . Line
from Kaiser Family Foundation , promoted prominently in the media ,
June 26 . Thanks , Wii UM aster Race
Officials said May ra Martinez was brought to the jail
Token
Token ID198
Feature activation+1.12e-01

Pos logit contributions
between+0.390
 Gaw+0.361
 undertaking+0.328
pty+0.311
abus+0.306
Neg logit contributions
united-0.477
CTV-0.439
 additive-0.368
 iod-0.361
SHARE-0.330
Token
Token ID198
Feature activation+1.15e-01

Pos logit contributions
between+0.084
 Gaw+0.078
 undertaking+0.071
pty+0.067
abus+0.066
Neg logit contributions
united-0.103
CTV-0.094
 additive-0.079
 iod-0.077
SHARE-0.071
TokenPower
Token ID13434
Feature activation+3.83e-01

Pos logit contributions
between+0.085
 Gaw+0.082
 undertaking+0.074
pty+0.070
wagen+0.069
Neg logit contributions
united-0.104
CTV-0.096
 additive-0.079
 iod-0.076
SHARE-0.073
TokenPoint
Token ID12727
Feature activation-9.69e-03

Pos logit contributions
between+0.360
 Gaw+0.341
 undertaking+0.317
pty+0.304
devices+0.304
Neg logit contributions
united-0.274
CTV-0.247
 iod-0.194
 additive-0.193
SHARE-0.168
Token slide
Token ID10649
Feature activation+5.24e-01

Pos logit contributions
united+0.010
CTV+0.009
 additive+0.008
 iod+0.008
 Bravo+0.007
Neg logit contributions
between-0.006
 Gaw-0.006
 undertaking-0.005
pty-0.005
abus-0.005
Token PNG
Token ID36182
Feature activation+7.68e-01

Pos logit contributions
between+0.195
 Gaw+0.169
 undertaking+0.134
pty+0.116
abus+0.111
Neg logit contributions
united-0.677
CTV-0.641
 additive-0.567
 iod-0.561
SHARE-0.530
Token larger
Token ID4025
Feature activation+3.20e-01

Pos logit contributions
between+0.550
 Gaw+0.501
 undertaking+0.457
pty+0.429
abus+0.425
Neg logit contributions
united-0.733
CTV-0.678
 additive-0.572
 iod-0.565
SHARE-0.514
Token image
Token ID2939
Feature activation+2.08e-01

Pos logit contributions
between+0.208
 Gaw+0.190
 undertaking+0.167
pty+0.158
abus+0.155
Neg logit contributions
united-0.328
CTV-0.304
 additive-0.260
 iod-0.257
SHARE-0.236
Token
Token ID198
Feature activation+1.50e-01

Pos logit contributions
between+0.152
 Gaw+0.139
 undertaking+0.125
pty+0.119
abus+0.117
Neg logit contributions
united-0.197
CTV-0.181
 additive-0.153
 iod-0.151
SHARE-0.137
Token
Token ID198
Feature activation+1.25e-01

Pos logit contributions
between+0.113
 Gaw+0.105
 undertaking+0.095
pty+0.090
abus+0.089
Neg logit contributions
united-0.137
CTV-0.126
 additive-0.105
 iod-0.103
SHARE-0.094
Tokenlarg
Token ID15521
Feature activation+3.60e-01

Pos logit contributions
between+0.083
 Gaw+0.082
 undertaking+0.072
pty+0.067
wagen+0.067
Neg logit contributions
united-0.123
CTV-0.114
 additive-0.093
 iod-0.091
SHARE-0.087
Token one
Token ID530
Feature activation+1.01e-01

Pos logit contributions
between+0.017
 Gaw+0.016
 undertaking+0.014
pty+0.013
abus+0.013
Neg logit contributions
united-0.024
CTV-0.023
 additive-0.019
 iod-0.019
SHARE-0.017
Token a
Token ID257
Feature activation+1.23e-01

Pos logit contributions
between+0.075
 Gaw+0.070
 undertaking+0.063
pty+0.060
abus+0.060
Neg logit contributions
united-0.093
CTV-0.086
 additive-0.072
 iod-0.071
 Bravo-0.065
Token babys
Token ID46711
Feature activation-2.22e-01

Pos logit contributions
between+0.100
 Gaw+0.092
 undertaking+0.084
pty+0.080
abus+0.079
Neg logit contributions
united-0.107
CTV-0.097
 additive-0.080
 iod-0.079
SHARE-0.071
Tokenitter
Token ID1967
Feature activation+7.76e-02

Pos logit contributions
united+0.178
CTV+0.161
 additive+0.131
 iod+0.128
SHARE+0.114
Neg logit contributions
between-0.193
 Gaw-0.182
 undertaking-0.167
pty-0.159
abus-0.157
Token
Token ID960
Feature activation+1.99e-01

Pos logit contributions
between+0.062
 Gaw+0.057
 undertaking+0.052
pty+0.049
abus+0.048
Neg logit contributions
united-0.068
CTV-0.062
 additive-0.052
 iod-0.051
SHARE-0.046
Tokenbetween
Token ID23395
Feature activation+7.61e-01

Pos logit contributions
between+0.137
 Gaw+0.126
 undertaking+0.113
pty+0.107
abus+0.105
Neg logit contributions
united-0.196
CTV-0.181
 additive-0.153
 iod-0.151
SHARE-0.139
Token 2002
Token ID6244
Feature activation+2.37e-01

Pos logit contributions
between+0.524
 Gaw+0.479
 undertaking+0.428
pty+0.401
devices+0.393
Neg logit contributions
united-0.752
CTV-0.695
 additive-0.588
 iod-0.582
SHARE-0.534
Token and
Token ID290
Feature activation+2.12e-02

Pos logit contributions
between+0.188
 Gaw+0.174
 undertaking+0.158
pty+0.150
abus+0.148
Neg logit contributions
united-0.210
CTV-0.192
 additive-0.159
 iod-0.157
SHARE-0.141
Token 2003
Token ID5816
Feature activation+1.35e-01

Pos logit contributions
between+0.012
 Gaw+0.011
 undertaking+0.010
pty+0.009
abus+0.009
Neg logit contributions
united-0.023
CTV-0.021
 additive-0.019
 iod-0.018
SHARE-0.017
Token.
Token ID13
Feature activation-3.30e-03

Pos logit contributions
between+0.102
 Gaw+0.094
 undertaking+0.085
pty+0.081
abus+0.079
Neg logit contributions
united-0.123
CTV-0.113
 additive-0.095
 iod-0.094
SHARE-0.085
Token Jim
Token ID5395
Feature activation+2.44e-02

Pos logit contributions
united+0.003
CTV+0.003
 additive+0.002
 iod+0.002
SHARE+0.002
Neg logit contributions
between-0.003
 Gaw-0.002
 undertaking-0.002
pty-0.002
abus-0.002
Token 2010
Token ID3050
Feature activation+1.80e-01

Pos logit contributions
between+0.011
 Gaw+0.010
 undertaking+0.009
pty+0.008
abus+0.008
Neg logit contributions
united-0.019
CTV-0.018
 additive-0.016
 iod-0.015
SHARE-0.014
Tokenboys
Token ID13202
Feature activation-3.12e-01

Pos logit contributions
between+0.174
 Gaw+0.167
 undertaking+0.156
pty+0.148
wagen+0.145
Neg logit contributions
united-0.126
CTV-0.112
 additive-0.084
 iod-0.084
SHARE-0.074
Token beware
Token ID40600
Feature activation+1.91e-01

Pos logit contributions
united+0.349
CTV+0.324
 additive+0.282
 iod+0.279
 Bravo+0.258
Neg logit contributions
between-0.172
 Gaw-0.156
 undertaking-0.132
pty-0.127
devices-0.122
Token
Token ID198
Feature activation+6.46e-02

Pos logit contributions
between+0.142
 Gaw+0.131
 undertaking+0.118
pty+0.112
abus+0.110
Neg logit contributions
united-0.178
CTV-0.164
 additive-0.138
 iod-0.136
SHARE-0.124
Token
Token ID198
Feature activation+4.54e-02

Pos logit contributions
between+0.049
 Gaw+0.045
 undertaking+0.041
pty+0.039
abus+0.038
Neg logit contributions
united-0.059
CTV-0.054
 additive-0.046
 iod-0.045
SHARE-0.041
TokenReviewer
Token ID35407
Feature activation+7.41e-01

Pos logit contributions
between+0.012
 Gaw+0.010
 undertaking+0.007
pty+0.005
devices+0.004
Neg logit contributions
united-0.064
CTV-0.061
 additive-0.054
 iod-0.054
SHARE-0.051
Token:
Token ID25
Feature activation-2.85e-01

Pos logit contributions
between+0.766
 Gaw+0.717
 undertaking+0.668
pty+0.648
abus+0.639
Neg logit contributions
united-0.474
CTV-0.418
 additive-0.322
 iod-0.318
SHARE-0.263
Token j
Token ID474
Feature activation-1.94e-01

Pos logit contributions
united+0.257
CTV+0.236
 additive+0.197
 iod+0.195
 Bravo+0.176
Neg logit contributions
between-0.219
 Gaw-0.202
 undertaking-0.184
pty-0.175
abus-0.172
Tokenwt
Token ID46569
Feature activation+3.44e-02

Pos logit contributions
united+0.184
CTV+0.168
 additive+0.141
 iod+0.139
SHARE+0.127
Neg logit contributions
between-0.142
 Gaw-0.131
 undertaking-0.119
pty-0.112
abus-0.109
Token0001
Token ID18005
Feature activation-2.62e-02

Pos logit contributions
between+0.027
 Gaw+0.025
 undertaking+0.022
pty+0.021
abus+0.021
Neg logit contributions
united-0.031
CTV-0.028
 additive-0.024
 iod-0.023
SHARE-0.021
Token -
Token ID532
Feature activation-4.67e-02

Pos logit contributions
united+0.020
CTV+0.018
 additive+0.014
 iod+0.014
SHARE+0.013
Neg logit contributions
between-0.024
 Gaw-0.022
 undertaking-0.021
pty-0.020
abus-0.019
Token,
Token ID11
Feature activation-6.08e-02

Pos logit contributions
united+0.075
CTV+0.068
 additive+0.055
 iod+0.054
SHARE+0.048
Neg logit contributions
between-0.078
 Gaw-0.073
 undertaking-0.067
pty-0.064
abus-0.063
Token I
Token ID314
Feature activation-2.71e-02

Pos logit contributions
united+0.056
CTV+0.051
 additive+0.043
 iod+0.042
 Bravo+0.038
Neg logit contributions
between-0.046
 Gaw-0.042
 undertaking-0.038
pty-0.037
abus-0.036
Token think
Token ID892
Feature activation-6.27e-03

Pos logit contributions
united+0.022
CTV+0.020
 additive+0.017
 iod+0.016
SHARE+0.015
Neg logit contributions
between-0.023
 Gaw-0.021
 undertaking-0.019
pty-0.019
abus-0.018
Token
Token ID198
Feature activation+5.50e-02

Pos logit contributions
united+0.006
CTV+0.005
 additive+0.004
 iod+0.004
SHARE+0.004
Neg logit contributions
between-0.005
 Gaw-0.004
 undertaking-0.004
pty-0.004
abus-0.004
Token
Token ID198
Feature activation+4.40e-02

Pos logit contributions
between+0.041
 Gaw+0.038
 undertaking+0.034
pty+0.033
abus+0.032
Neg logit contributions
united-0.051
CTV-0.047
 additive-0.039
 iod-0.038
SHARE-0.035
TokenReviewer
Token ID35407
Feature activation+7.07e-01

Pos logit contributions
between+0.011
 Gaw+0.009
 undertaking+0.006
pty+0.004
abus+0.004
Neg logit contributions
united-0.063
CTV-0.059
 additive-0.053
 iod-0.053
SHARE-0.050
Token:
Token ID25
Feature activation-2.72e-01

Pos logit contributions
between+0.732
 Gaw+0.685
 undertaking+0.638
pty+0.619
abus+0.610
Neg logit contributions
united-0.452
CTV-0.399
 additive-0.307
 iod-0.303
SHARE-0.251
Token B
Token ID347
Feature activation-5.83e-02

Pos logit contributions
united+0.246
CTV+0.226
 additive+0.189
 iod+0.186
 Bravo+0.169
Neg logit contributions
between-0.208
 Gaw-0.192
 undertaking-0.174
pty-0.166
abus-0.163
Tokeniz
Token ID528
Feature activation+7.34e-02

Pos logit contributions
united+0.053
CTV+0.049
 additive+0.040
 iod+0.040
SHARE+0.036
Neg logit contributions
between-0.045
 Gaw-0.041
 undertaking-0.037
pty-0.036
abus-0.035
Tokenr
Token ID81
Feature activation-1.09e-01

Pos logit contributions
between+0.056
 Gaw+0.052
 undertaking+0.047
pty+0.045
abus+0.044
Neg logit contributions
united-0.067
CTV-0.061
 additive-0.051
 iod-0.050
SHARE-0.046
Token Pix
Token ID21642
Feature activation+1.07e-01

Pos logit contributions
united+0.097
CTV+0.088
 additive+0.073
 iod+0.072
SHARE+0.065
Neg logit contributions
between-0.085
 Gaw-0.079
 undertaking-0.072
pty-0.068
devices-0.067
Tokeniff
Token ID733
Feature activation+1.09e-03

Pos logit contributions
united+0.028
CTV+0.026
 additive+0.022
 iod+0.022
SHARE+0.020
Neg logit contributions
between-0.023
 Gaw-0.021
 undertaking-0.019
pty-0.018
abus-0.017
TokenTra
Token ID15721
Feature activation+6.03e-04

Pos logit contributions
between+0.001
 Gaw+0.001
 undertaking+0.001
pty+0.001
abus+0.001
Neg logit contributions
united-0.001
CTV-0.001
 additive-0.001
 iod-0.001
SHARE-0.001
Tokenx
Token ID87
Feature activation-2.40e-01

Pos logit contributions
between+0.001
 Gaw+0.001
 undertaking+0.001
pty+0.001
abus+0.000
Neg logit contributions
united-0.000
CTV-0.000
 additive-0.000
 iod-0.000
SHARE-0.000
Token
Token ID198
Feature activation-3.08e-02

Pos logit contributions
united+0.221
CTV+0.203
 additive+0.170
 iod+0.167
SHARE+0.152
Neg logit contributions
between-0.181
 Gaw-0.167
 undertaking-0.151
pty-0.144
abus-0.141
Token
Token ID198
Feature activation-1.27e-02

Pos logit contributions
united+0.028
CTV+0.026
 additive+0.022
 iod+0.021
SHARE+0.020
Neg logit contributions
between-0.023
 Gaw-0.021
 undertaking-0.019
pty-0.018
abus-0.018
TokenReviewer
Token ID35407
Feature activation+7.05e-01

Pos logit contributions
united+0.018
CTV+0.017
 additive+0.015
 iod+0.015
SHARE+0.014
Neg logit contributions
between-0.003
 Gaw-0.002
 undertaking-0.002
pty-0.001
abus-0.001
Token:
Token ID25
Feature activation-3.06e-01

Pos logit contributions
between+0.730
 Gaw+0.683
 undertaking+0.636
pty+0.617
abus+0.609
Neg logit contributions
united-0.449
CTV-0.397
 additive-0.304
 iod-0.301
SHARE-0.249
Token V
Token ID569
Feature activation-3.43e-02

Pos logit contributions
united+0.276
CTV+0.252
 additive+0.211
 iod+0.208
 Bravo+0.188
Neg logit contributions
between-0.235
 Gaw-0.217
 undertaking-0.197
pty-0.188
abus-0.185
Tokenthe
Token ID1169
Feature activation+8.31e-02

Pos logit contributions
united+0.031
CTV+0.029
 additive+0.024
 iod+0.023
SHARE+0.021
Neg logit contributions
between-0.026
 Gaw-0.024
 undertaking-0.022
pty-0.021
abus-0.021
TokenHappy
Token ID25082
Feature activation-1.93e-01

Pos logit contributions
between+0.063
 Gaw+0.059
 undertaking+0.053
pty+0.050
devices+0.050
Neg logit contributions
united-0.076
CTV-0.069
 additive-0.058
 iod-0.057
SHARE-0.052
TokenL
Token ID43
Feature activation-8.40e-02

Pos logit contributions
united+0.168
CTV+0.154
 additive+0.126
 iod+0.124
SHARE+0.113
Neg logit contributions
between-0.155
 Gaw-0.144
 undertaking-0.132
pty-0.125
abus-0.124
Token was
Token ID373
Feature activation-8.05e-02

Pos logit contributions
united+0.088
CTV+0.081
 additive+0.068
 iod+0.067
 Bravo+0.061
Neg logit contributions
between-0.070
 Gaw-0.065
 undertaking-0.058
pty-0.056
abus-0.055
Token about
Token ID546
Feature activation-6.58e-02

Pos logit contributions
united+0.075
CTV+0.069
 additive+0.058
 iod+0.057
SHARE+0.052
Neg logit contributions
between-0.060
 Gaw-0.055
 undertaking-0.050
pty-0.047
abus-0.046
Token homosexuality
Token ID19822
Feature activation+9.45e-02

Pos logit contributions
united+0.060
CTV+0.055
 additive+0.047
 iod+0.046
 Bravo+0.042
Neg logit contributions
between-0.049
 Gaw-0.046
 undertaking-0.041
pty-0.040
abus-0.039
Token
Token ID198
Feature activation+4.73e-02

Pos logit contributions
between+0.074
 Gaw+0.069
 undertaking+0.062
pty+0.060
abus+0.059
Neg logit contributions
united-0.084
CTV-0.077
 additive-0.064
 iod-0.063
SHARE-0.057
Token
Token ID198
Feature activation+4.53e-02

Pos logit contributions
between+0.035
 Gaw+0.033
 undertaking+0.030
pty+0.028
abus+0.028
Neg logit contributions
united-0.044
CTV-0.040
 additive-0.033
 iod-0.033
SHARE-0.030
TokenReviewer
Token ID35407
Feature activation+6.98e-01

Pos logit contributions
between+0.035
 Gaw+0.032
 undertaking+0.029
pty+0.028
abus+0.027
Neg logit contributions
united-0.041
CTV-0.038
 additive-0.031
 iod-0.031
SHARE-0.028
Token:
Token ID25
Feature activation-2.82e-01

Pos logit contributions
between+0.720
 Gaw+0.680
 undertaking+0.634
pty+0.611
abus+0.602
Neg logit contributions
united-0.448
CTV-0.394
 additive-0.298
 iod-0.296
SHARE-0.248
Token k
Token ID479
Feature activation+5.53e-02

Pos logit contributions
united+0.255
CTV+0.233
 additive+0.195
 iod+0.192
 Bravo+0.174
Neg logit contributions
between-0.218
 Gaw-0.201
 undertaking-0.182
pty-0.174
abus-0.171
Tokenimp
Token ID11011
Feature activation+2.38e-01

Pos logit contributions
between+0.040
 Gaw+0.037
 undertaking+0.034
pty+0.031
devices+0.031
Neg logit contributions
united-0.052
CTV-0.048
 additive-0.040
 iod-0.040
SHARE-0.036
Tokenunk
Token ID2954
Feature activation+3.19e-02

Pos logit contributions
between+0.180
 Gaw+0.167
 undertaking+0.151
pty+0.143
abus+0.140
Neg logit contributions
united-0.219
CTV-0.201
 additive-0.168
 iod-0.165
SHARE-0.150
Tokenrock
Token ID10823
Feature activation+1.73e-01

Pos logit contributions
between+0.027
 Gaw+0.025
 undertaking+0.023
pty+0.022
abus+0.021
Neg logit contributions
united-0.027
CTV-0.024
 additive-0.020
 iod-0.020
SHARE-0.017
Token things
Token ID1243
Feature activation+9.31e-02

Pos logit contributions
united+0.129
CTV+0.117
 additive+0.095
 iod+0.094
SHARE+0.083
Neg logit contributions
between-0.135
 Gaw-0.127
 undertaking-0.116
pty-0.111
abus-0.109
Token like
Token ID588
Feature activation-6.60e-02

Pos logit contributions
between+0.079
 Gaw+0.073
 undertaking+0.067
pty+0.064
abus+0.063
Neg logit contributions
united-0.077
CTV-0.070
 additive-0.057
 iod-0.056
SHARE-0.050
Token
Token ID564
Feature activation-1.34e-01

Pos logit contributions
united+0.052
CTV+0.047
 additive+0.038
 iod+0.037
SHARE+0.033
Neg logit contributions
between-0.058
 Gaw-0.055
 undertaking-0.050
pty-0.048
abus-0.047
Token
Token ID250
Feature activation-1.24e-01

Pos logit contributions
united+0.109
CTV+0.099
 additive+0.081
 iod+0.079
SHARE+0.071
Neg logit contributions
between-0.115
 Gaw-0.107
 undertaking-0.098
pty-0.094
abus-0.093
TokenSm
Token ID7556
Feature activation-3.73e-02

Pos logit contributions
united+0.107
CTV+0.098
 additive+0.080
 iod+0.079
SHARE+0.072
Neg logit contributions
between-0.099
 Gaw-0.093
 undertaking-0.084
pty-0.081
abus-0.079
Tokenile
Token ID576
Feature activation+6.94e-01

Pos logit contributions
united+0.036
CTV+0.034
 additive+0.028
 iod+0.028
SHARE+0.026
Neg logit contributions
between-0.026
 Gaw-0.024
 undertaking-0.022
pty-0.020
abus-0.020
Token if
Token ID611
Feature activation+1.20e-01

Pos logit contributions
between+0.572
 Gaw+0.534
 undertaking+0.485
pty+0.465
abus+0.457
Neg logit contributions
united-0.588
CTV-0.536
 additive-0.441
 iod-0.434
SHARE-0.389
Token you
Token ID345
Feature activation+1.27e-02

Pos logit contributions
between+0.089
 Gaw+0.082
 undertaking+0.074
pty+0.071
abus+0.070
Neg logit contributions
united-0.111
CTV-0.102
 additive-0.086
 iod-0.085
SHARE-0.077
Token masturb
Token ID22938
Feature activation+2.54e-01

Pos logit contributions
between+0.011
 Gaw+0.010
 undertaking+0.009
pty+0.009
abus+0.009
Neg logit contributions
united-0.010
CTV-0.010
 additive-0.008
 iod-0.008
SHARE-0.007
Tokenate
Token ID378
Feature activation+1.04e-01

Pos logit contributions
between+0.195
 Gaw+0.182
 undertaking+0.165
pty+0.157
devices+0.154
Neg logit contributions
united-0.228
CTV-0.208
 additive-0.175
 iod-0.172
SHARE-0.156
Token
Token ID447
Feature activation+1.08e-02

Pos logit contributions
between+0.083
 Gaw+0.077
 undertaking+0.070
pty+0.067
abus+0.066
Neg logit contributions
united-0.091
CTV-0.083
 additive-0.069
 iod-0.068
SHARE-0.061
Token bad
Token ID2089
Feature activation+1.22e-01

Pos logit contributions
between+0.028
 Gaw+0.026
 undertaking+0.023
pty+0.022
abus+0.022
Neg logit contributions
united-0.041
CTV-0.038
 additive-0.032
 iod-0.031
SHARE-0.029
Token idea
Token ID2126
Feature activation-8.61e-02

Pos logit contributions
between+0.098
 Gaw+0.091
 undertaking+0.084
pty+0.079
abus+0.078
Neg logit contributions
united-0.106
CTV-0.097
 additive-0.079
 iod-0.078
SHARE-0.071
Token.
Token ID13
Feature activation-6.54e-03

Pos logit contributions
united+0.079
CTV+0.072
 additive+0.060
 iod+0.059
SHARE+0.054
Neg logit contributions
between-0.065
 Gaw-0.061
 undertaking-0.055
pty-0.052
abus-0.051
Token
Token ID198
Feature activation+1.24e-02

Pos logit contributions
united+0.006
CTV+0.005
 additive+0.004
 iod+0.004
SHARE+0.004
Neg logit contributions
between-0.005
 Gaw-0.005
 undertaking-0.004
pty-0.004
abus-0.004
Token
Token ID198
Feature activation+1.43e-03

Pos logit contributions
between+0.009
 Gaw+0.009
 undertaking+0.008
pty+0.007
abus+0.007
Neg logit contributions
united-0.011
CTV-0.011
 additive-0.009
 iod-0.009
SHARE-0.008
TokenReviewer
Token ID35407
Feature activation+6.85e-01

Pos logit contributions
between+0.000
 Gaw+0.000
 undertaking+0.000
pty+0.000
abus+0.000
Neg logit contributions
united-0.002
CTV-0.002
 additive-0.002
 iod-0.002
SHARE-0.002
Token:
Token ID25
Feature activation-2.95e-01

Pos logit contributions
between+0.709
 Gaw+0.664
 undertaking+0.619
pty+0.599
abus+0.591
Neg logit contributions
united-0.438
CTV-0.386
 additive-0.296
 iod-0.292
SHARE-0.243
Token Mike
Token ID4995
Feature activation+1.49e-01

Pos logit contributions
united+0.268
CTV+0.245
 additive+0.205
 iod+0.202
 Bravo+0.183
Neg logit contributions
between-0.226
 Gaw-0.208
 undertaking-0.189
pty-0.181
abus-0.178
TokenM
Token ID44
Feature activation-6.24e-02

Pos logit contributions
between+0.114
 Gaw+0.105
 undertaking+0.096
pty+0.091
abus+0.089
Neg logit contributions
united-0.135
CTV-0.124
 additive-0.104
 iod-0.102
SHARE-0.093
Tokenanners
Token ID15672
Feature activation-2.68e-01

Pos logit contributions
united+0.048
CTV+0.043
 additive+0.035
 iod+0.034
SHARE+0.030
Neg logit contributions
between-0.056
 Gaw-0.053
 undertaking-0.049
pty-0.047
abus-0.046
Token -
Token ID532
Feature activation-3.95e-02

Pos logit contributions
united+0.216
CTV+0.195
 additive+0.158
 iod+0.155
SHARE+0.139
Neg logit contributions
between-0.232
 Gaw-0.217
 undertaking-0.200
pty-0.191
abus-0.189
Token house
Token ID2156
Feature activation-7.40e-03

Pos logit contributions
united+0.087
CTV+0.080
 additive+0.067
 iod+0.065
SHARE+0.059
Neg logit contributions
between-0.074
 Gaw-0.069
 undertaking-0.062
pty-0.060
abus-0.059
Token,
Token ID11
Feature activation-2.00e-02

Pos logit contributions
united+0.007
CTV+0.006
 additive+0.005
 iod+0.005
SHARE+0.005
Neg logit contributions
between-0.006
 Gaw-0.005
 undertaking-0.005
pty-0.004
abus-0.004
Token gay
Token ID5650
Feature activation+4.03e-03

Pos logit contributions
united+0.018
CTV+0.017
 additive+0.014
 iod+0.014
 Bravo+0.012
Neg logit contributions
between-0.015
 Gaw-0.014
 undertaking-0.013
pty-0.012
abus-0.012
Tokenish
Token ID680
Feature activation+8.43e-02

Pos logit contributions
between+0.003
 Gaw+0.003
 undertaking+0.003
pty+0.003
abus+0.003
Neg logit contributions
united-0.003
CTV-0.003
 additive-0.003
 iod-0.003
SHARE-0.002
Token dance
Token ID9280
Feature activation-2.10e-02

Pos logit contributions
between+0.067
 Gaw+0.062
 undertaking+0.056
pty+0.053
abus+0.053
Neg logit contributions
united-0.074
CTV-0.068
 additive-0.057
 iod-0.056
SHARE-0.050
Token trou
Token ID4057
Feature activation+6.80e-01

Pos logit contributions
united+0.019
CTV+0.017
 additive+0.014
 iod+0.014
SHARE+0.013
Neg logit contributions
between-0.017
 Gaw-0.015
 undertaking-0.014
pty-0.013
abus-0.013
Tokenpe
Token ID431
Feature activation+2.39e-01

Pos logit contributions
between+0.524
 Gaw+0.485
 undertaking+0.441
pty+0.417
abus+0.412
Neg logit contributions
united-0.614
CTV-0.561
 additive-0.468
 iod-0.460
SHARE-0.418
Token,
Token ID11
Feature activation-1.12e-02

Pos logit contributions
between+0.194
 Gaw+0.181
 undertaking+0.165
pty+0.157
abus+0.155
Neg logit contributions
united-0.205
CTV-0.187
 additive-0.154
 iod-0.152
SHARE-0.136
Token and
Token ID290
Feature activation-2.87e-02

Pos logit contributions
united+0.010
CTV+0.009
 additive+0.008
 iod+0.007
SHARE+0.007
Neg logit contributions
between-0.009
 Gaw-0.008
 undertaking-0.007
pty-0.007
abus-0.007
Token foam
Token ID19828
Feature activation+1.22e-01

Pos logit contributions
united+0.026
CTV+0.024
 additive+0.020
 iod+0.020
SHARE+0.018
Neg logit contributions
between-0.022
 Gaw-0.020
 undertaking-0.018
pty-0.018
abus-0.017
Token parties
Token ID4671
Feature activation+5.81e-02

Pos logit contributions
between+0.094
 Gaw+0.087
 undertaking+0.079
pty+0.075
abus+0.074
Neg logit contributions
united-0.110
CTV-0.101
 additive-0.084
 iod-0.083
SHARE-0.075
Tokener
Token ID263
Feature activation+1.15e-01

Pos logit contributions
between+0.223
 Gaw+0.204
 undertaking+0.183
pty+0.174
abus+0.171
Neg logit contributions
united-0.304
CTV-0.280
 additive-0.237
 iod-0.234
SHARE-0.214
Token magnet
Token ID19972
Feature activation-1.57e-01

Pos logit contributions
between+0.098
 Gaw+0.091
 undertaking+0.084
pty+0.080
abus+0.079
Neg logit contributions
united-0.094
CTV-0.085
 additive-0.069
 iod-0.068
SHARE-0.062
Token?
Token ID30
Feature activation-3.67e-02

Pos logit contributions
united+0.118
CTV+0.107
 additive+0.085
 iod+0.084
SHARE+0.073
Neg logit contributions
between-0.144
 Gaw-0.135
 undertaking-0.125
pty-0.120
abus-0.119
Token
Token ID198
Feature activation+3.25e-02

Pos logit contributions
united+0.034
CTV+0.031
 additive+0.026
 iod+0.026
SHARE+0.023
Neg logit contributions
between-0.027
 Gaw-0.025
 undertaking-0.023
pty-0.022
abus-0.021
Token
Token ID198
Feature activation+8.10e-03

Pos logit contributions
between+0.024
 Gaw+0.023
 undertaking+0.020
pty+0.019
abus+0.019
Neg logit contributions
united-0.030
CTV-0.028
 additive-0.023
 iod-0.023
SHARE-0.021
TokenReviewer
Token ID35407
Feature activation+6.78e-01

Pos logit contributions
between+0.002
 Gaw+0.002
 undertaking+0.001
pty+0.001
devices+0.001
Neg logit contributions
united-0.011
CTV-0.011
 additive-0.010
 iod-0.010
SHARE-0.009
Token:
Token ID25
Feature activation-3.03e-01

Pos logit contributions
between+0.702
 Gaw+0.657
 undertaking+0.612
pty+0.593
abus+0.585
Neg logit contributions
united-0.434
CTV-0.383
 additive-0.294
 iod-0.290
SHARE-0.241
Token hey
Token ID17207
Feature activation+4.32e-02

Pos logit contributions
united+0.275
CTV+0.252
 additive+0.211
 iod+0.208
 Bravo+0.188
Neg logit contributions
between-0.232
 Gaw-0.214
 undertaking-0.194
pty-0.185
abus-0.182
Token_
Token ID62
Feature activation+5.11e-02

Pos logit contributions
between+0.032
 Gaw+0.030
 undertaking+0.027
pty+0.026
devices+0.025
Neg logit contributions
united-0.040
CTV-0.037
 additive-0.031
 iod-0.030
SHARE-0.027
Tokenler
Token ID1754
Feature activation+8.47e-02

Pos logit contributions
between+0.037
 Gaw+0.035
 undertaking+0.032
pty+0.030
devices+0.029
Neg logit contributions
united-0.048
CTV-0.044
 additive-0.037
 iod-0.036
SHARE-0.033
Tokenoy
Token ID726
Feature activation+9.50e-02

Pos logit contributions
between+0.064
 Gaw+0.059
 undertaking+0.054
pty+0.051
abus+0.050
Neg logit contributions
united-0.078
CTV-0.071
 additive-0.060
 iod-0.059
SHARE-0.053
Token was
Token ID373
Feature activation-3.06e-02

Pos logit contributions
united+0.001
CTV+0.001
 additive+0.001
 iod+0.001
SHARE+0.001
Neg logit contributions
between-0.001
 Gaw-0.001
 undertaking-0.001
pty-0.001
abus-0.001
Token eaten
Token ID17065
Feature activation+1.79e-01

Pos logit contributions
united+0.027
CTV+0.024
 additive+0.020
 iod+0.020
SHARE+0.018
Neg logit contributions
between-0.024
 Gaw-0.023
 undertaking-0.020
pty-0.020
abus-0.020
Token by
Token ID416
Feature activation-2.28e-02

Pos logit contributions
between+0.150
 Gaw+0.140
 undertaking+0.128
pty+0.123
abus+0.121
Neg logit contributions
united-0.149
CTV-0.136
 additive-0.112
 iod-0.110
SHARE-0.098
Token a
Token ID257
Feature activation+8.86e-02

Pos logit contributions
united+0.022
CTV+0.020
 additive+0.017
 iod+0.017
SHARE+0.016
Neg logit contributions
between-0.016
 Gaw-0.015
 undertaking-0.013
pty-0.012
abus-0.012
Token crocod
Token ID37565
Feature activation+5.95e-01

Pos logit contributions
between+0.059
 Gaw+0.053
 undertaking+0.048
pty+0.045
abus+0.044
Neg logit contributions
united-0.090
CTV-0.083
 additive-0.071
 iod-0.070
SHARE-0.064
Tokenile
Token ID576
Feature activation+6.75e-01

Pos logit contributions
between+0.225
 Gaw+0.194
 undertaking+0.154
pty+0.133
devices+0.132
Neg logit contributions
united-0.769
CTV-0.720
 additive-0.642
 iod-0.632
SHARE-0.595
Token that
Token ID326
Feature activation+5.67e-02

Pos logit contributions
between+0.509
 Gaw+0.472
 undertaking+0.425
pty+0.406
abus+0.400
Neg logit contributions
united-0.618
CTV-0.568
 additive-0.477
 iod-0.468
SHARE-0.425
Token was
Token ID373
Feature activation-2.96e-04

Pos logit contributions
between+0.045
 Gaw+0.042
 undertaking+0.038
pty+0.036
abus+0.036
Neg logit contributions
united-0.050
CTV-0.045
 additive-0.038
 iod-0.037
SHARE-0.033
Token never
Token ID1239
Feature activation+5.27e-02

Pos logit contributions
united+0.000
CTV+0.000
 additive+0.000
 iod+0.000
SHARE+0.000
Neg logit contributions
between-0.000
 Gaw-0.000
 undertaking-0.000
pty-0.000
abus-0.000
Token caught
Token ID4978
Feature activation+1.19e-01

Pos logit contributions
between+0.038
 Gaw+0.035
 undertaking+0.031
pty+0.030
abus+0.029
Neg logit contributions
united-0.051
CTV-0.047
 additive-0.039
 iod-0.039
SHARE-0.035
Token.
Token ID13
Feature activation+7.96e-02

Pos logit contributions
between+0.092
 Gaw+0.085
 undertaking+0.077
pty+0.074
abus+0.072
Neg logit contributions
united-0.107
CTV-0.098
 additive-0.082
 iod-0.081
SHARE-0.073
Token 2
Token ID362
Feature activation-1.77e-01

Pos logit contributions
between+0.000
 Gaw+0.000
 undertaking+0.000
pty+0.000
abus+0.000
Neg logit contributions
united-0.000
CTV-0.000
 additive-0.000
 iod-0.000
SHARE-0.000
Token,
Token ID11
Feature activation+4.15e-02

Pos logit contributions
united+0.162
CTV+0.149
 additive+0.124
 iod+0.123
SHARE+0.111
Neg logit contributions
between-0.135
 Gaw-0.124
 undertaking-0.113
pty-0.107
abus-0.105
Token370
Token ID20167
Feature activation-8.50e-02

Pos logit contributions
between+0.031
 Gaw+0.029
 undertaking+0.026
pty+0.025
abus+0.025
Neg logit contributions
united-0.038
CTV-0.035
 additive-0.029
 iod-0.029
SHARE-0.026
Token pound
Token ID14896
Feature activation-1.22e-02

Pos logit contributions
united+0.078
CTV+0.071
 additive+0.060
 iod+0.059
SHARE+0.053
Neg logit contributions
between-0.065
 Gaw-0.060
 undertaking-0.054
pty-0.051
abus-0.051
Token crocod
Token ID37565
Feature activation+5.37e-01

Pos logit contributions
united+0.011
CTV+0.010
 additive+0.009
 iod+0.009
 Bravo+0.008
Neg logit contributions
between-0.009
 Gaw-0.008
 undertaking-0.007
pty-0.007
abus-0.007
Tokenile
Token ID576
Feature activation+6.68e-01

Pos logit contributions
between+0.209
 Gaw+0.182
 undertaking+0.144
devices+0.127
pty+0.124
Neg logit contributions
united-0.686
CTV-0.643
 additive-0.575
 iod-0.563
SHARE-0.530
Token.
Token ID13
Feature activation+7.16e-02

Pos logit contributions
between+0.517
 Gaw+0.480
 undertaking+0.434
pty+0.415
abus+0.409
Neg logit contributions
united-0.598
CTV-0.549
 additive-0.458
 iod-0.451
SHARE-0.408
Token Two
Token ID4930
Feature activation-5.18e-02

Pos logit contributions
between+0.056
 Gaw+0.051
 undertaking+0.047
pty+0.045
abus+0.044
Neg logit contributions
united-0.064
CTV-0.059
 additive-0.049
 iod-0.048
SHARE-0.044
Token years
Token ID812
Feature activation-3.18e-02

Pos logit contributions
united+0.048
CTV+0.044
 additive+0.037
 iod+0.036
SHARE+0.033
Neg logit contributions
between-0.039
 Gaw-0.036
 undertaking-0.032
pty-0.031
abus-0.031
Token ago
Token ID2084
Feature activation+5.37e-02

Pos logit contributions
united+0.034
CTV+0.032
 additive+0.027
 iod+0.027
SHARE+0.025
Neg logit contributions
between-0.019
 Gaw-0.018
 undertaking-0.015
pty-0.014
abus-0.014
Token,
Token ID11
Feature activation-2.07e-02

Pos logit contributions
between+0.045
 Gaw+0.042
 undertaking+0.038
pty+0.037
abus+0.036
Neg logit contributions
united-0.045
CTV-0.041
 additive-0.034
 iod-0.033
SHARE-0.030
Tokeni
Token ID72
Feature activation+1.45e-01

Pos logit contributions
united+0.202
CTV+0.186
 additive+0.158
 iod+0.155
SHARE+0.143
Neg logit contributions
between-0.137
 Gaw-0.126
 undertaking-0.112
pty-0.106
abus-0.104
Token Spe
Token ID2531
Feature activation-1.48e-01

Pos logit contributions
between+0.115
 Gaw+0.107
 undertaking+0.097
pty+0.093
abus+0.091
Neg logit contributions
united-0.127
CTV-0.116
 additive-0.096
 iod-0.095
SHARE-0.085
Tokenlling
Token ID2680
Feature activation+1.79e-03

Pos logit contributions
united+0.127
CTV+0.115
 additive+0.095
 iod+0.093
SHARE+0.083
Neg logit contributions
between-0.121
 Gaw-0.113
 undertaking-0.103
pty-0.098
abus-0.097
Token was
Token ID373
Feature activation-8.09e-03

Pos logit contributions
between+0.001
 Gaw+0.001
 undertaking+0.001
pty+0.001
abus+0.001
Neg logit contributions
united-0.002
CTV-0.001
 additive-0.001
 iod-0.001
SHARE-0.001
Token a
Token ID257
Feature activation+6.95e-02

Pos logit contributions
united+0.007
CTV+0.007
 additive+0.006
 iod+0.005
SHARE+0.005
Neg logit contributions
between-0.006
 Gaw-0.006
 undertaking-0.005
pty-0.005
abus-0.005
Token trou
Token ID4057
Feature activation+6.65e-01

Pos logit contributions
between+0.056
 Gaw+0.052
 undertaking+0.048
pty+0.046
abus+0.045
Neg logit contributions
united-0.060
CTV-0.055
 additive-0.045
 iod-0.044
SHARE-0.040
Tokenper
Token ID525
Feature activation-1.28e-01

Pos logit contributions
between+0.508
 Gaw+0.472
 undertaking+0.431
pty+0.406
abus+0.401
Neg logit contributions
united-0.603
CTV-0.550
 additive-0.460
 iod-0.452
SHARE-0.409
Token and
Token ID290
Feature activation-3.27e-02

Pos logit contributions
united+0.116
CTV+0.106
 additive+0.089
 iod+0.087
SHARE+0.079
Neg logit contributions
between-0.097
 Gaw-0.090
 undertaking-0.081
pty-0.078
abus-0.077
Token stuck
Token ID7819
Feature activation-7.05e-02

Pos logit contributions
united+0.029
CTV+0.027
 additive+0.022
 iod+0.022
SHARE+0.020
Neg logit contributions
between-0.026
 Gaw-0.024
 undertaking-0.022
pty-0.021
abus-0.020
Token through
Token ID832
Feature activation-1.20e-01

Pos logit contributions
united+0.059
CTV+0.053
 additive+0.044
 iod+0.043
 Bravo+0.039
Neg logit contributions
between-0.059
 Gaw-0.055
 undertaking-0.050
pty-0.048
abus-0.048
Token her
Token ID607
Feature activation-3.70e-01

Pos logit contributions
united+0.107
CTV+0.098
 additive+0.082
 iod+0.080
 Bravo+0.073
Neg logit contributions
between-0.094
 Gaw-0.087
 undertaking-0.079
pty-0.076
abus-0.075
Token Song
Token ID10940
Feature activation+1.94e-01

Pos logit contributions
between+0.016
 Gaw+0.015
 undertaking+0.013
pty+0.013
devices+0.012
Neg logit contributions
united-0.020
CTV-0.018
 additive-0.015
 iod-0.015
 Bravo-0.014
Token-
Token ID12
Feature activation+1.58e-01

Pos logit contributions
between+0.130
 Gaw+0.118
 undertaking+0.106
pty+0.100
devices+0.097
Neg logit contributions
united-0.195
CTV-0.180
 additive-0.153
 iod-0.151
 Bravo-0.140
TokenB
Token ID33
Feature activation-6.55e-02

Pos logit contributions
between+0.125
 Gaw+0.116
 undertaking+0.106
pty+0.101
abus+0.099
Neg logit contributions
united-0.139
CTV-0.127
 additive-0.104
 iod-0.103
SHARE-0.094
Tokenobs
Token ID8158
Feature activation+7.27e-02

Pos logit contributions
united+0.060
CTV+0.055
 additive+0.046
 iod+0.045
SHARE+0.041
Neg logit contributions
between-0.049
 Gaw-0.046
 undertaking-0.041
pty-0.039
abus-0.039
Token To
Token ID1675
Feature activation+1.93e-02

Pos logit contributions
between+0.056
 Gaw+0.052
 undertaking+0.047
pty+0.045
abus+0.044
Neg logit contributions
united-0.066
CTV-0.060
 additive-0.050
 iod-0.050
SHARE-0.045
Tokenilet
Token ID41550
Feature activation+6.58e-01

Pos logit contributions
between+0.015
 Gaw+0.013
 undertaking+0.012
pty+0.012
abus+0.011
Neg logit contributions
united-0.018
CTV-0.016
 additive-0.014
 iod-0.013
SHARE-0.012
Token-
Token ID12
Feature activation+1.56e-01

Pos logit contributions
between+0.509
 Gaw+0.468
 undertaking+0.432
pty+0.407
abus+0.402
Neg logit contributions
united-0.591
CTV-0.540
 additive-0.450
 iod-0.441
 Bravo-0.406
TokenA
Token ID32
Feature activation+1.75e-01

Pos logit contributions
between+0.124
 Gaw+0.116
 undertaking+0.106
pty+0.100
abus+0.099
Neg logit contributions
united-0.137
CTV-0.125
 additive-0.103
 iod-0.101
SHARE-0.092
TokenJ
Token ID41
Feature activation-1.80e-01

Pos logit contributions
between+0.135
 Gaw+0.125
 undertaking+0.114
pty+0.108
devices+0.106
Neg logit contributions
united-0.159
CTV-0.145
 additive-0.121
 iod-0.119
 Bravo-0.108
Token Po
Token ID7695
Feature activation+1.33e-01

Pos logit contributions
united+0.164
CTV+0.150
 additive+0.125
 iod+0.123
 Bravo+0.112
Neg logit contributions
between-0.138
 Gaw-0.127
 undertaking-0.116
pty-0.110
abus-0.108
Tokenopy
Token ID11081
Feature activation+2.56e-01

Pos logit contributions
between+0.096
 Gaw+0.088
 undertaking+0.080
pty+0.075
abus+0.074
Neg logit contributions
united-0.127
CTV-0.117
 additive-0.098
 iod-0.097
 Bravo-0.089
Token that
Token ID326
Feature activation+7.21e-02

Pos logit contributions
between+0.001
 Gaw+0.001
 undertaking+0.000
pty+0.000
abus+0.000
Neg logit contributions
united-0.001
CTV-0.001
 additive-0.001
 iod-0.001
 Bravo-0.001
Token they
Token ID484
Feature activation-1.17e-01

Pos logit contributions
between+0.052
 Gaw+0.048
 undertaking+0.043
pty+0.042
abus+0.041
Neg logit contributions
united-0.068
CTV-0.062
 additive-0.053
 iod-0.052
SHARE-0.047
Token saw
Token ID2497
Feature activation+1.01e-01

Pos logit contributions
united+0.104
CTV+0.095
 additive+0.079
 iod+0.078
SHARE+0.071
Neg logit contributions
between-0.092
 Gaw-0.085
 undertaking-0.077
pty-0.073
abus-0.072
Token a
Token ID257
Feature activation+9.88e-02

Pos logit contributions
between+0.071
 Gaw+0.066
 undertaking+0.059
pty+0.056
abus+0.055
Neg logit contributions
united-0.097
CTV-0.090
 additive-0.077
 iod-0.076
SHARE-0.069
Token crocod
Token ID37565
Feature activation+6.01e-01

Pos logit contributions
between+0.070
 Gaw+0.064
 undertaking+0.058
pty+0.055
abus+0.054
Neg logit contributions
united-0.095
CTV-0.088
 additive-0.074
 iod-0.073
 Bravo-0.067
Tokenile
Token ID576
Feature activation+6.47e-01

Pos logit contributions
between+0.232
 Gaw+0.200
 undertaking+0.157
devices+0.139
pty+0.138
Neg logit contributions
united-0.772
CTV-0.722
 additive-0.645
 iod-0.635
SHARE-0.596
Token kill
Token ID1494
Feature activation-5.69e-02

Pos logit contributions
between+0.483
 Gaw+0.448
 undertaking+0.403
pty+0.385
abus+0.379
Neg logit contributions
united-0.597
CTV-0.548
 additive-0.461
 iod-0.454
SHARE-0.412
Token a
Token ID257
Feature activation+8.19e-02

Pos logit contributions
united+0.055
CTV+0.050
 additive+0.043
 iod+0.042
SHARE+0.038
Neg logit contributions
between-0.040
 Gaw-0.037
 undertaking-0.033
pty-0.032
abus-0.031
Token water
Token ID1660
Feature activation+1.37e-01

Pos logit contributions
between+0.064
 Gaw+0.059
 undertaking+0.054
pty+0.052
abus+0.051
Neg logit contributions
united-0.073
CTV-0.066
 additive-0.055
 iod-0.054
SHARE-0.049
Token buffalo
Token ID45019
Feature activation+4.71e-02

Pos logit contributions
between+0.112
 Gaw+0.105
 undertaking+0.095
pty+0.091
abus+0.091
Neg logit contributions
united-0.117
CTV-0.106
 additive-0.088
 iod-0.086
SHARE-0.077
Token this
Token ID428
Feature activation+4.73e-03

Pos logit contributions
between+0.036
 Gaw+0.033
 undertaking+0.030
pty+0.029
abus+0.028
Neg logit contributions
united-0.043
CTV-0.039
 additive-0.033
 iod-0.032
SHARE-0.029
Token
Token ID247
Feature activation-3.89e-02

Pos logit contributions
united+0.050
CTV+0.045
 additive+0.037
 iod+0.037
SHARE+0.033
Neg logit contributions
between-0.049
 Gaw-0.045
 undertaking-0.042
pty-0.040
abus-0.039
Tokens
Token ID82
Feature activation+1.17e-02

Pos logit contributions
united+0.037
CTV+0.034
 additive+0.029
 iod+0.028
SHARE+0.026
Neg logit contributions
between-0.028
 Gaw-0.026
 undertaking-0.023
pty-0.022
abus-0.022
Token right
Token ID826
Feature activation-8.97e-02

Pos logit contributions
between+0.008
 Gaw+0.008
 undertaking+0.007
pty+0.006
abus+0.006
Neg logit contributions
united-0.011
CTV-0.010
 additive-0.009
 iod-0.009
 Bravo-0.008
Token in
Token ID287
Feature activation-1.91e-02

Pos logit contributions
united+0.080
CTV+0.073
 additive+0.061
 iod+0.060
SHARE+0.055
Neg logit contributions
between-0.070
 Gaw-0.065
 undertaking-0.059
pty-0.056
abus-0.055
Token-
Token ID12
Feature activation+2.88e-02

Pos logit contributions
united+0.019
CTV+0.018
 additive+0.015
 iod+0.015
SHARE+0.014
Neg logit contributions
between-0.013
 Gaw-0.012
 undertaking-0.010
pty-0.010
abus-0.010
Tokenbetween
Token ID23395
Feature activation+6.40e-01

Pos logit contributions
between+0.021
 Gaw+0.020
 undertaking+0.018
pty+0.017
abus+0.017
Neg logit contributions
united-0.027
CTV-0.025
 additive-0.021
 iod-0.020
SHARE-0.019
Token,
Token ID11
Feature activation-4.33e-02

Pos logit contributions
between+0.490
 Gaw+0.455
 undertaking+0.410
pty+0.395
abus+0.392
Neg logit contributions
united-0.578
CTV-0.529
 additive-0.445
 iod-0.435
 Bravo-0.397
Token at
Token ID379
Feature activation-6.51e-02

Pos logit contributions
united+0.041
CTV+0.037
 additive+0.032
 iod+0.031
 Bravo+0.029
Neg logit contributions
between-0.031
 Gaw-0.029
 undertaking-0.026
pty-0.025
abus-0.025
Token 32
Token ID3933
Feature activation-1.08e-01

Pos logit contributions
united+0.062
CTV+0.057
 additive+0.048
 iod+0.047
 Bravo+0.043
Neg logit contributions
between-0.046
 Gaw-0.043
 undertaking-0.038
pty-0.037
abus-0.037
Token%.
Token ID7225
Feature activation+5.89e-03

Pos logit contributions
united+0.090
CTV+0.082
 additive+0.067
 iod+0.066
SHARE+0.059
Neg logit contributions
between-0.091
 Gaw-0.085
 undertaking-0.077
pty-0.074
abus-0.073
Token A
Token ID317
Feature activation+1.07e-01

Pos logit contributions
between+0.005
 Gaw+0.004
 undertaking+0.004
pty+0.004
abus+0.004
Neg logit contributions
united-0.005
CTV-0.005
 additive-0.004
 iod-0.004
 Bravo-0.004
Token it
Token ID340
Feature activation-4.13e-02

Pos logit contributions
united+0.003
CTV+0.003
 additive+0.002
 iod+0.002
SHARE+0.002
Neg logit contributions
between-0.003
 Gaw-0.003
 undertaking-0.003
pty-0.003
abus-0.002
Token's
Token ID338
Feature activation-1.40e-01

Pos logit contributions
united+0.037
CTV+0.034
 additive+0.028
 iod+0.028
SHARE+0.025
Neg logit contributions
between-0.032
 Gaw-0.030
 undertaking-0.027
pty-0.026
abus-0.025
Token the
Token ID262
Feature activation+1.04e-02

Pos logit contributions
united+0.128
CTV+0.118
 additive+0.099
 iod+0.097
SHARE+0.088
Neg logit contributions
between-0.106
 Gaw-0.098
 undertaking-0.088
pty-0.085
abus-0.083
Token largest
Token ID4387
Feature activation+2.38e-01

Pos logit contributions
between+0.007
 Gaw+0.006
 undertaking+0.006
pty+0.005
abus+0.005
Neg logit contributions
united-0.010
CTV-0.009
 additive-0.008
 iod-0.008
 Bravo-0.007
Token crocod
Token ID37565
Feature activation+5.64e-01

Pos logit contributions
between+0.147
 Gaw+0.134
 undertaking+0.116
pty+0.111
abus+0.109
Neg logit contributions
united-0.249
CTV-0.231
 additive-0.201
 iod-0.197
 Bravo-0.182
Tokenile
Token ID576
Feature activation+6.39e-01

Pos logit contributions
between+0.216
 Gaw+0.187
 undertaking+0.148
pty+0.128
devices+0.126
Neg logit contributions
united-0.726
CTV-0.680
 additive-0.605
 iod-0.597
SHARE-0.561
Token ever
Token ID1683
Feature activation-7.58e-03

Pos logit contributions
between+0.480
 Gaw+0.445
 undertaking+0.398
pty+0.383
abus+0.379
Neg logit contributions
united-0.584
CTV-0.537
 additive-0.455
 iod-0.444
 Bravo-0.404
Token to
Token ID284
Feature activation+3.77e-02

Pos logit contributions
united+0.007
CTV+0.007
 additive+0.006
 iod+0.006
 Bravo+0.005
Neg logit contributions
between-0.005
 Gaw-0.005
 undertaking-0.004
pty-0.004
abus-0.004
Token be
Token ID307
Feature activation+8.30e-02

Pos logit contributions
between+0.029
 Gaw+0.027
 undertaking+0.024
pty+0.023
abus+0.023
Neg logit contributions
united-0.034
CTV-0.031
 additive-0.026
 iod-0.026
SHARE-0.023
Token taken
Token ID2077
Feature activation+5.16e-02

Pos logit contributions
between+0.059
 Gaw+0.054
 undertaking+0.048
pty+0.046
abus+0.045
Neg logit contributions
united-0.080
CTV-0.074
 additive-0.062
 iod-0.061
SHARE-0.056
Token alive
Token ID6776
Feature activation+3.10e-02

Pos logit contributions
between+0.045
 Gaw+0.042
 undertaking+0.039
pty+0.037
abus+0.037
Neg logit contributions
united-0.041
CTV-0.037
 additive-0.030
 iod-0.030
SHARE-0.026
Token are
Token ID389
Feature activation-1.17e-01

Pos logit contributions
united+0.124
CTV+0.113
 additive+0.093
 iod+0.091
SHARE+0.082
Neg logit contributions
between-0.121
 Gaw-0.113
 undertaking-0.103
pty-0.099
abus-0.097
Token Here
Token ID3423
Feature activation-2.55e-01

Pos logit contributions
united+0.080
CTV+0.071
 additive+0.055
 iod+0.054
SHARE+0.046
Neg logit contributions
between-0.117
 Gaw-0.110
 undertaking-0.102
pty-0.099
abus-0.097
Token....
Token ID1106
Feature activation-2.41e-03

Pos logit contributions
united+0.208
CTV+0.188
 additive+0.153
 iod+0.151
SHARE+0.134
Neg logit contributions
between-0.217
 Gaw-0.204
 undertaking-0.187
pty-0.180
abus-0.176
Token
Token ID198
Feature activation-1.04e-03

Pos logit contributions
united+0.002
CTV+0.002
 additive+0.002
 iod+0.002
SHARE+0.002
Neg logit contributions
between-0.002
 Gaw-0.002
 undertaking-0.002
pty-0.001
abus-0.001
Token
Token ID198
Feature activation-2.01e-02

Pos logit contributions
united+0.001
CTV+0.001
 additive+0.001
 iod+0.001
SHARE+0.001
Neg logit contributions
between-0.001
 Gaw-0.001
 undertaking-0.001
pty-0.001
abus-0.001
TokenReviewer
Token ID35407
Feature activation+6.30e-01

Pos logit contributions
united+0.029
CTV+0.027
 additive+0.024
 iod+0.024
SHARE+0.023
Neg logit contributions
between-0.005
 Gaw-0.004
 undertaking-0.003
pty-0.002
abus-0.002
Token:
Token ID25
Feature activation-3.28e-01

Pos logit contributions
between+0.652
 Gaw+0.611
 undertaking+0.569
pty+0.551
abus+0.544
Neg logit contributions
united-0.402
CTV-0.354
 additive-0.272
 iod-0.268
SHARE-0.222
Token SAS
Token ID35516
Feature activation+1.36e-01

Pos logit contributions
united+0.300
CTV+0.275
 additive+0.231
 iod+0.228
 Bravo+0.206
Neg logit contributions
between-0.249
 Gaw-0.229
 undertaking-0.208
pty-0.198
abus-0.195
TokenK
Token ID42
Feature activation-8.40e-02

Pos logit contributions
between+0.108
 Gaw+0.101
 undertaking+0.092
pty+0.087
abus+0.086
Neg logit contributions
united-0.119
CTV-0.109
 additive-0.090
 iod-0.089
SHARE-0.080
TokenATCH
Token ID11417
Feature activation-5.43e-02

Pos logit contributions
united+0.072
CTV+0.066
 additive+0.054
 iod+0.053
SHARE+0.048
Neg logit contributions
between-0.068
 Gaw-0.064
 undertaking-0.058
pty-0.055
devices-0.054
TokenEW
Token ID6217
Feature activation+1.38e-01

Pos logit contributions
united+0.047
CTV+0.043
 additive+0.035
 iod+0.035
SHARE+0.031
Neg logit contributions
between-0.044
 Gaw-0.041
 undertaking-0.037
pty-0.036
devices-0.035
Token one
Token ID530
Feature activation+3.71e-02

Pos logit contributions
between+0.044
 Gaw+0.041
 undertaking+0.037
pty+0.035
abus+0.035
Neg logit contributions
united-0.053
CTV-0.049
 additive-0.041
 iod-0.040
SHARE-0.037
Token element
Token ID5002
Feature activation+1.58e-01

Pos logit contributions
between+0.027
 Gaw+0.025
 undertaking+0.023
pty+0.022
abus+0.022
Neg logit contributions
united-0.035
CTV-0.032
 additive-0.027
 iod-0.026
SHARE-0.024
Token of
Token ID286
Feature activation+2.50e-02

Pos logit contributions
between+0.118
 Gaw+0.109
 undertaking+0.097
pty+0.093
abus+0.093
Neg logit contributions
united-0.147
CTV-0.135
 additive-0.113
 iod-0.111
 Bravo-0.101
Token a
Token ID257
Feature activation+7.55e-02

Pos logit contributions
between+0.019
 Gaw+0.017
 undertaking+0.015
pty+0.015
abus+0.015
Neg logit contributions
united-0.023
CTV-0.021
 additive-0.018
 iod-0.018
 Bravo-0.016
Token tri
Token ID1333
Feature activation+1.41e-01

Pos logit contributions
between+0.060
 Gaw+0.055
 undertaking+0.050
pty+0.048
abus+0.047
Neg logit contributions
united-0.067
CTV-0.061
 additive-0.051
 iod-0.050
SHARE-0.045
Tokenpty
Token ID5835
Feature activation+6.23e-01

Pos logit contributions
between+0.095
 Gaw+0.087
 undertaking+0.078
pty+0.072
abus+0.072
Neg logit contributions
united-0.141
CTV-0.130
 additive-0.111
 iod-0.109
SHARE-0.100
Tokench
Token ID354
Feature activation+4.51e-02

Pos logit contributions
between+0.400
 Gaw+0.365
 undertaking+0.321
abus+0.299
devices+0.299
Neg logit contributions
united-0.644
CTV-0.590
 additive-0.509
 iod-0.502
SHARE-0.462
Token called
Token ID1444
Feature activation-8.19e-02

Pos logit contributions
between+0.033
 Gaw+0.030
 undertaking+0.027
pty+0.026
abus+0.026
Neg logit contributions
united-0.042
CTV-0.039
 additive-0.033
 iod-0.032
SHARE-0.030
Token Echo
Token ID21455
Feature activation-1.19e-01

Pos logit contributions
united+0.077
CTV+0.070
 additive+0.059
 iod+0.058
SHARE+0.053
Neg logit contributions
between-0.060
 Gaw-0.055
 undertaking-0.050
pty-0.048
abus-0.047
Token that
Token ID326
Feature activation+7.85e-02

Pos logit contributions
united+0.111
CTV+0.102
 additive+0.085
 iod+0.083
 Bravo+0.077
Neg logit contributions
between-0.089
 Gaw-0.082
 undertaking-0.074
pty-0.070
abus-0.069
Token Indigenous
Token ID24033
Feature activation+1.22e-01

Pos logit contributions
between+0.057
 Gaw+0.053
 undertaking+0.047
pty+0.045
abus+0.044
Neg logit contributions
united-0.074
CTV-0.068
 additive-0.057
 iod-0.057
SHARE-0.052
Token45
Token ID2231
Feature activation+1.46e-02

Pos logit contributions
between+0.036
 Gaw+0.033
 undertaking+0.030
pty+0.029
abus+0.028
Neg logit contributions
united-0.043
CTV-0.039
 additive-0.033
 iod-0.032
SHARE-0.029
Token 366
Token ID44856
Feature activation+3.67e-02

Pos logit contributions
between+0.013
 Gaw+0.012
 undertaking+0.011
pty+0.011
abus+0.010
Neg logit contributions
united-0.012
CTV-0.011
 additive-0.009
 iod-0.008
 Bravo-0.008
Token.
Token ID13
Feature activation+2.51e-01

Pos logit contributions
between+0.029
 Gaw+0.027
 undertaking+0.024
pty+0.023
abus+0.023
Neg logit contributions
united-0.033
CTV-0.030
 additive-0.025
 iod-0.024
SHARE-0.022
Token
Token ID198
Feature activation+1.93e-01

Pos logit contributions
between+0.192
 Gaw+0.177
 undertaking+0.161
pty+0.153
abus+0.151
Neg logit contributions
united-0.229
CTV-0.210
 additive-0.175
 iod-0.173
SHARE-0.157
Token
Token ID198
Feature activation+1.79e-01

Pos logit contributions
between+0.144
 Gaw+0.133
 undertaking+0.120
pty+0.114
abus+0.112
Neg logit contributions
united-0.179
CTV-0.164
 additive-0.138
 iod-0.136
SHARE-0.124
TokenTopics
Token ID25902
Feature activation+6.18e-01

Pos logit contributions
between+0.077
 Gaw+0.069
 undertaking+0.057
pty+0.050
abus+0.049
Neg logit contributions
united-0.222
CTV-0.209
 additive-0.182
 iod-0.180
SHARE-0.171
Token:
Token ID25
Feature activation-1.32e-02

Pos logit contributions
between+0.636
 Gaw+0.595
 undertaking+0.556
pty+0.536
abus+0.530
Neg logit contributions
united-0.397
CTV-0.354
 additive-0.271
 iod-0.267
SHARE-0.224
Token community
Token ID2055
Feature activation-1.10e-01

Pos logit contributions
united+0.010
CTV+0.009
 additive+0.007
 iod+0.007
SHARE+0.006
Neg logit contributions
between-0.012
 Gaw-0.011
 undertaking-0.010
pty-0.010
abus-0.010
Token-
Token ID12
Feature activation+2.10e-01

Pos logit contributions
united+0.107
CTV+0.099
 additive+0.084
 iod+0.083
SHARE+0.076
Neg logit contributions
between-0.077
 Gaw-0.070
 undertaking-0.063
pty-0.059
abus-0.058
Tokenand
Token ID392
Feature activation+1.34e-01

Pos logit contributions
between+0.167
 Gaw+0.152
 undertaking+0.140
pty+0.133
devices+0.131
Neg logit contributions
united-0.183
CTV-0.171
 additive-0.142
 iod-0.139
SHARE-0.127
Token-
Token ID12
Feature activation+2.07e-01

Pos logit contributions
between+0.092
 Gaw+0.084
 undertaking+0.076
pty+0.071
abus+0.070
Neg logit contributions
united-0.132
CTV-0.122
 additive-0.103
 iod-0.102
SHARE-0.094
Token Un
Token ID791
Feature activation+1.19e-02

Pos logit contributions
united+0.209
CTV+0.190
 additive+0.157
 iod+0.154
SHARE+0.138
Neg logit contributions
between-0.202
 Gaw-0.188
 undertaking-0.172
pty-0.164
abus-0.162
Tokenilateral
Token ID14796
Feature activation-9.64e-02

Pos logit contributions
between+0.009
 Gaw+0.008
 undertaking+0.008
pty+0.007
abus+0.007
Neg logit contributions
united-0.011
CTV-0.010
 additive-0.008
 iod-0.008
SHARE-0.007
Token de
Token ID390
Feature activation-2.72e-01

Pos logit contributions
united+0.087
CTV+0.080
 additive+0.066
 iod+0.065
SHARE+0.059
Neg logit contributions
between-0.074
 Gaw-0.069
 undertaking-0.062
pty-0.059
abus-0.058
Token Ind
Token ID1423
Feature activation+5.05e-02

Pos logit contributions
united+0.213
CTV+0.193
 additive+0.155
 iod+0.152
SHARE+0.135
Neg logit contributions
between-0.242
 Gaw-0.227
 undertaking-0.208
pty-0.200
abus-0.197
Tokenepend
Token ID2690
Feature activation-1.61e-01

Pos logit contributions
between+0.045
 Gaw+0.042
 undertaking+0.039
pty+0.037
abus+0.037
Neg logit contributions
united-0.039
CTV-0.036
 additive-0.029
 iod-0.028
SHARE-0.025
Tokenencia
Token ID29634
Feature activation-7.72e-01

Pos logit contributions
united+0.054
CTV+0.041
 additive+0.019
 iod+0.018
SHARE+0.007
Neg logit contributions
between-0.216
 Gaw-0.207
 undertaking-0.196
pty-0.191
abus-0.189
Token)
Token ID8
Feature activation-7.70e-04

Pos logit contributions
united+0.645
CTV+0.586
 additive+0.481
 iod+0.473
SHARE+0.424
Neg logit contributions
between-0.646
 Gaw-0.602
 undertaking-0.550
pty-0.527
abus-0.519
Token could
Token ID714
Feature activation-8.80e-02

Pos logit contributions
united+0.001
CTV+0.001
 additive+0.001
 iod+0.001
SHARE+0.001
Neg logit contributions
between-0.001
 Gaw-0.001
 undertaking-0.000
pty-0.000
abus-0.000
Token be
Token ID307
Feature activation+9.94e-02

Pos logit contributions
united+0.086
CTV+0.080
 additive+0.068
 iod+0.067
SHARE+0.061
Neg logit contributions
between-0.061
 Gaw-0.056
 undertaking-0.050
pty-0.047
abus-0.046
Token re
Token ID302
Feature activation+1.48e-02

Pos logit contributions
between+0.081
 Gaw+0.075
 undertaking+0.068
pty+0.065
abus+0.064
Neg logit contributions
united-0.086
CTV-0.078
 additive-0.064
 iod-0.063
SHARE-0.057
Tokenph
Token ID746
Feature activation-1.87e-01

Pos logit contributions
between+0.011
 Gaw+0.010
 undertaking+0.009
pty+0.009
abus+0.009
Neg logit contributions
united-0.014
CTV-0.013
 additive-0.011
 iod-0.010
SHARE-0.009
Tokenuman
Token ID3778
Feature activation-2.95e-01

Pos logit contributions
united+0.187
CTV+0.167
 additive+0.136
 iod+0.133
 Bravo+0.118
Neg logit contributions
between-0.201
 Gaw-0.188
 undertaking-0.174
pty-0.165
devices-0.163
Token and
Token ID290
Feature activation-9.82e-02

Pos logit contributions
united+0.257
CTV+0.235
 additive+0.195
 iod+0.191
SHARE+0.172
Neg logit contributions
between-0.237
 Gaw-0.220
 undertaking-0.200
pty-0.191
abus-0.188
Token Saur
Token ID46197
Feature activation-7.24e-03

Pos logit contributions
united+0.090
CTV+0.082
 additive+0.069
 iod+0.068
 Bravo+0.062
Neg logit contributions
between-0.074
 Gaw-0.068
 undertaking-0.062
pty-0.059
abus-0.058
Tokenon
Token ID261
Feature activation-6.44e-02

Pos logit contributions
united+0.005
CTV+0.005
 additive+0.004
 iod+0.003
 Bravo+0.003
Neg logit contributions
between-0.007
 Gaw-0.007
 undertaking-0.006
pty-0.006
devices-0.006
Token kill
Token ID1494
Feature activation-1.51e-01

Pos logit contributions
united+0.056
CTV+0.051
 additive+0.043
 iod+0.042
SHARE+0.038
Neg logit contributions
between-0.051
 Gaw-0.048
 undertaking-0.043
pty-0.041
abus-0.041
Token Bor
Token ID12182
Feature activation-6.62e-01

Pos logit contributions
united+0.142
CTV+0.131
 additive+0.110
 iod+0.109
 Bravo+0.099
Neg logit contributions
between-0.110
 Gaw-0.101
 undertaking-0.091
pty-0.087
abus-0.086
Tokenom
Token ID296
Feature activation-4.05e-02

Pos logit contributions
united+0.627
CTV+0.575
 additive+0.483
 iod+0.477
 Bravo+0.435
Neg logit contributions
between-0.478
 Gaw-0.441
 undertaking-0.399
pty-0.380
devices-0.370
Tokenir
Token ID343
Feature activation-1.76e-01

Pos logit contributions
united+0.036
CTV+0.033
 additive+0.027
 iod+0.027
SHARE+0.024
Neg logit contributions
between-0.032
 Gaw-0.029
 undertaking-0.027
pty-0.025
abus-0.025
Token and
Token ID290
Feature activation-1.22e-01

Pos logit contributions
united+0.154
CTV+0.141
 additive+0.117
 iod+0.115
SHARE+0.104
Neg logit contributions
between-0.141
 Gaw-0.130
 undertaking-0.118
pty-0.114
abus-0.112
Token capture
Token ID8006
Feature activation+2.49e-01

Pos logit contributions
united+0.108
CTV+0.098
 additive+0.082
 iod+0.081
SHARE+0.073
Neg logit contributions
between-0.097
 Gaw-0.090
 undertaking-0.082
pty-0.078
abus-0.077
Token Merry
Token ID39001
Feature activation-2.65e-01

Pos logit contributions
between+0.190
 Gaw+0.174
 undertaking+0.159
pty+0.153
abus+0.151
Neg logit contributions
united-0.225
CTV-0.206
 additive-0.172
 iod-0.170
 Bravo-0.154
Tokent
Token ID83
Feature activation-8.03e-02

Pos logit contributions
united+0.041
CTV+0.037
 additive+0.031
 iod+0.030
SHARE+0.028
Neg logit contributions
between-0.034
 Gaw-0.032
 undertaking-0.029
pty-0.027
abus-0.027
Token even
Token ID772
Feature activation-2.20e-02

Pos logit contributions
united+0.071
CTV+0.065
 additive+0.054
 iod+0.053
SHARE+0.048
Neg logit contributions
between-0.063
 Gaw-0.059
 undertaking-0.053
pty-0.051
abus-0.051
Token been
Token ID587
Feature activation-8.91e-02

Pos logit contributions
united+0.019
CTV+0.017
 additive+0.014
 iod+0.014
SHARE+0.012
Neg logit contributions
between-0.018
 Gaw-0.017
 undertaking-0.015
pty-0.015
abus-0.015
Token on
Token ID319
Feature activation-2.27e-01

Pos logit contributions
united+0.074
CTV+0.067
 additive+0.056
 iod+0.055
SHARE+0.049
Neg logit contributions
between-0.075
 Gaw-0.070
 undertaking-0.063
pty-0.061
abus-0.060
Token the
Token ID262
Feature activation-3.65e-02

Pos logit contributions
united+0.218
CTV+0.201
 additive+0.170
 iod+0.168
 Bravo+0.153
Neg logit contributions
between-0.161
 Gaw-0.148
 undertaking-0.133
pty-0.126
abus-0.124
Token disabled
Token ID10058
Feature activation-6.52e-01

Pos logit contributions
united+0.029
CTV+0.026
 additive+0.021
 iod+0.021
SHARE+0.018
Neg logit contributions
between-0.032
 Gaw-0.030
 undertaking-0.028
pty-0.027
abus-0.026
Token list
Token ID1351
Feature activation+7.22e-02

Pos logit contributions
united+0.592
CTV+0.543
 additive+0.451
 iod+0.444
SHARE+0.404
Neg logit contributions
between-0.500
 Gaw-0.461
 undertaking-0.421
pty-0.399
abus-0.391
Token since
Token ID1201
Feature activation+8.93e-02

Pos logit contributions
between+0.048
 Gaw+0.044
 undertaking+0.039
pty+0.037
abus+0.036
Neg logit contributions
united-0.073
CTV-0.067
 additive-0.057
 iod-0.057
SHARE-0.052
Token his
Token ID465
Feature activation-5.34e-02

Pos logit contributions
between+0.066
 Gaw+0.061
 undertaking+0.054
pty+0.053
abus+0.052
Neg logit contributions
united-0.083
CTV-0.076
 additive-0.065
 iod-0.064
 Bravo-0.058
Token previous
Token ID2180
Feature activation+1.64e-01

Pos logit contributions
united+0.051
CTV+0.046
 additive+0.039
 iod+0.039
SHARE+0.035
Neg logit contributions
between-0.039
 Gaw-0.036
 undertaking-0.032
pty-0.031
abus-0.030
Token Tommy
Token ID19919
Feature activation-2.06e-02

Pos logit contributions
between+0.129
 Gaw+0.120
 undertaking+0.109
pty+0.104
abus+0.103
Neg logit contributions
united-0.144
CTV-0.132
 additive-0.110
 iod-0.108
SHARE-0.097
Token really
Token ID1107
Feature activation+1.04e-02

Pos logit contributions
between+0.052
 Gaw+0.048
 undertaking+0.043
pty+0.041
abus+0.041
Neg logit contributions
united-0.073
CTV-0.067
 additive-0.058
 iod-0.057
 Bravo-0.052
Token great
Token ID1049
Feature activation+1.93e-01

Pos logit contributions
between+0.008
 Gaw+0.007
 undertaking+0.006
pty+0.006
abus+0.006
Neg logit contributions
united-0.010
CTV-0.009
 additive-0.008
 iod-0.007
 Bravo-0.007
Token less
Token ID1342
Feature activation+5.67e-02

Pos logit contributions
between+0.150
 Gaw+0.139
 undertaking+0.126
pty+0.121
abus+0.119
Neg logit contributions
united-0.173
CTV-0.158
 additive-0.133
 iod-0.130
 Bravo-0.117
Token-
Token ID12
Feature activation+8.27e-02

Pos logit contributions
between+0.046
 Gaw+0.042
 undertaking+0.039
pty+0.037
abus+0.036
Neg logit contributions
united-0.049
CTV-0.045
 additive-0.038
 iod-0.037
SHARE-0.033
Tokenf
Token ID69
Feature activation+6.33e-02

Pos logit contributions
between+0.060
 Gaw+0.056
 undertaking+0.050
pty+0.048
abus+0.046
Neg logit contributions
united-0.078
CTV-0.072
 additive-0.060
 iod-0.060
SHARE-0.055
Tokenrequently
Token ID37971
Feature activation-6.45e-01

Pos logit contributions
between+0.049
 Gaw+0.046
 undertaking+0.041
pty+0.039
abus+0.039
Neg logit contributions
united-0.057
CTV-0.052
 additive-0.043
 iod-0.043
SHARE-0.038
Token used
Token ID973
Feature activation-1.86e-01

Pos logit contributions
united+0.500
CTV+0.450
 additive+0.366
 iod+0.360
SHARE+0.315
Neg logit contributions
between-0.579
 Gaw-0.541
 undertaking-0.497
pty-0.480
abus-0.472
Token options
Token ID3689
Feature activation-1.33e-01

Pos logit contributions
united+0.165
CTV+0.151
 additive+0.126
 iod+0.124
 Bravo+0.112
Neg logit contributions
between-0.146
 Gaw-0.135
 undertaking-0.123
pty-0.118
abus-0.116
Token to
Token ID284
Feature activation+1.25e-03

Pos logit contributions
united+0.117
CTV+0.107
 additive+0.089
 iod+0.087
SHARE+0.079
Neg logit contributions
between-0.105
 Gaw-0.098
 undertaking-0.089
pty-0.085
abus-0.083
Token consider
Token ID2074
Feature activation-3.10e-02

Pos logit contributions
between+0.001
 Gaw+0.001
 undertaking+0.001
pty+0.001
abus+0.001
Neg logit contributions
united-0.001
CTV-0.001
 additive-0.001
 iod-0.001
SHARE-0.001
Token.
Token ID13
Feature activation-1.16e-02

Pos logit contributions
united+0.028
CTV+0.026
 additive+0.022
 iod+0.022
SHARE+0.020
Neg logit contributions
between-0.023
 Gaw-0.022
 undertaking-0.020
pty-0.019
abus-0.018
Token K
Token ID509
Feature activation-1.13e-02

Pos logit contributions
united+0.020
CTV+0.018
 additive+0.015
 iod+0.015
 Bravo+0.014
Neg logit contributions
between-0.017
 Gaw-0.016
 undertaking-0.015
pty-0.014
abus-0.014
Tokenaff
Token ID2001
Feature activation-4.28e-02

Pos logit contributions
united+0.010
CTV+0.009
 additive+0.008
 iod+0.008
SHARE+0.007
Neg logit contributions
between-0.009
 Gaw-0.008
 undertaking-0.007
pty-0.007
devices-0.007
Tokenir
Token ID343
Feature activation-7.86e-02

Pos logit contributions
united+0.038
CTV+0.035
 additive+0.029
 iod+0.029
SHARE+0.026
Neg logit contributions
between-0.033
 Gaw-0.031
 undertaking-0.028
pty-0.027
abus-0.026
Token lime
Token ID28738
Feature activation-1.44e-02

Pos logit contributions
united+0.073
CTV+0.067
 additive+0.056
 iod+0.056
SHARE+0.051
Neg logit contributions
between-0.058
 Gaw-0.054
 undertaking-0.049
pty-0.046
abus-0.045
Token leaves
Token ID5667
Feature activation-4.60e-02

Pos logit contributions
united+0.013
CTV+0.012
 additive+0.010
 iod+0.010
SHARE+0.009
Neg logit contributions
between-0.011
 Gaw-0.010
 undertaking-0.009
pty-0.009
abus-0.008
Token impart
Token ID23553
Feature activation-6.41e-01

Pos logit contributions
united+0.039
CTV+0.035
 additive+0.029
 iod+0.028
SHARE+0.025
Neg logit contributions
between-0.038
 Gaw-0.036
 undertaking-0.033
pty-0.031
abus-0.031
Token intense
Token ID8157
Feature activation-3.81e-02

Pos logit contributions
united+0.618
CTV+0.569
 additive+0.487
 iod+0.479
 Bravo+0.438
Neg logit contributions
between-0.450
 Gaw-0.414
 undertaking-0.372
pty-0.353
abus-0.349
Token fruit
Token ID8234
Feature activation-1.34e-01

Pos logit contributions
united+0.034
CTV+0.032
 additive+0.026
 iod+0.026
SHARE+0.024
Neg logit contributions
between-0.029
 Gaw-0.027
 undertaking-0.024
pty-0.023
abus-0.023
Tokeniness
Token ID1272
Feature activation+1.59e-01

Pos logit contributions
united+0.137
CTV+0.127
 additive+0.109
 iod+0.107
SHARE+0.099
Neg logit contributions
between-0.087
 Gaw-0.079
 undertaking-0.070
pty-0.066
abus-0.065
Token without
Token ID1231
Feature activation-1.03e-01

Pos logit contributions
between+0.128
 Gaw+0.119
 undertaking+0.108
pty+0.103
abus+0.102
Neg logit contributions
united-0.138
CTV-0.126
 additive-0.104
 iod-0.102
SHARE-0.092
Token the
Token ID262
Feature activation-8.12e-02

Pos logit contributions
united+0.101
CTV+0.094
 additive+0.080
 iod+0.079
 Bravo+0.072
Neg logit contributions
between-0.071
 Gaw-0.065
 undertaking-0.058
pty-0.055
abus-0.054
Token all
Token ID477
Feature activation-2.60e-02

Pos logit contributions
between+0.066
 Gaw+0.061
 undertaking+0.055
pty+0.052
abus+0.051
Neg logit contributions
united-0.088
CTV-0.082
 additive-0.069
 iod-0.068
 Bravo-0.062
Token the
Token ID262
Feature activation-9.43e-02

Pos logit contributions
united+0.025
CTV+0.023
 additive+0.019
 iod+0.019
 Bravo+0.017
Neg logit contributions
between-0.019
 Gaw-0.017
 undertaking-0.016
pty-0.015
abus-0.015
Token right
Token ID826
Feature activation-1.29e-01

Pos logit contributions
united+0.087
CTV+0.079
 additive+0.067
 iod+0.066
 Bravo+0.060
Neg logit contributions
between-0.071
 Gaw-0.065
 undertaking-0.059
pty-0.057
abus-0.056
Token things
Token ID1243
Feature activation+8.55e-02

Pos logit contributions
united+0.144
CTV+0.134
 additive+0.116
 iod+0.115
SHARE+0.107
Neg logit contributions
between-0.073
 Gaw-0.065
 undertaking-0.057
pty-0.053
abus-0.051
Token goal
Token ID3061
Feature activation-4.41e-01

Pos logit contributions
between+0.067
 Gaw+0.062
 undertaking+0.056
pty+0.054
abus+0.053
Neg logit contributions
united-0.076
CTV-0.070
 additive-0.058
 iod-0.057
SHARE-0.052
Tokenkeepers
Token ID24952
Feature activation-6.36e-01

Pos logit contributions
united+0.398
CTV+0.364
 additive+0.304
 iod+0.299
SHARE+0.271
Neg logit contributions
between-0.339
 Gaw-0.314
 undertaking-0.284
pty-0.271
abus-0.267
Token should
Token ID815
Feature activation-1.02e-02

Pos logit contributions
united+0.542
CTV+0.494
 additive+0.407
 iod+0.400
SHARE+0.360
Neg logit contributions
between-0.522
 Gaw-0.485
 undertaking-0.443
pty-0.423
abus-0.417
Token,"
Token ID553
Feature activation-4.50e-02

Pos logit contributions
united+0.009
CTV+0.008
 additive+0.006
 iod+0.006
 Bravo+0.006
Neg logit contributions
between-0.008
 Gaw-0.008
 undertaking-0.007
pty-0.007
abus-0.007
Token Y
Token ID575
Feature activation-2.79e-02

Pos logit contributions
united+0.045
CTV+0.041
 additive+0.035
 iod+0.035
 Bravo+0.032
Neg logit contributions
between-0.030
 Gaw-0.028
 undertaking-0.025
pty-0.024
abus-0.023
Tokenall
Token ID439
Feature activation-3.16e-02

Pos logit contributions
united+0.029
CTV+0.027
 additive+0.023
 iod+0.023
SHARE+0.021
Neg logit contributions
between-0.018
 Gaw-0.016
 undertaking-0.014
pty-0.013
abus-0.013
Tokenop
Token ID404
Feature activation+8.82e-02

Pos logit contributions
united+0.034
CTV+0.031
 additive+0.027
 iod+0.027
SHARE+0.025
Neg logit contributions
between-0.019
 Gaw-0.017
 undertaking-0.015
pty-0.014
devices-0.014
Token G
Token ID402
Feature activation+4.68e-02

Pos logit contributions
united+0.020
CTV+0.018
 additive+0.015
 iod+0.015
SHARE+0.014
Neg logit contributions
between-0.016
 Gaw-0.015
 undertaking-0.014
pty-0.013
abus-0.013
Tokeness
Token ID408
Feature activation+4.75e-02

Pos logit contributions
between+0.035
 Gaw+0.032
 undertaking+0.029
pty+0.028
abus+0.027
Neg logit contributions
united-0.043
CTV-0.040
 additive-0.033
 iod-0.033
SHARE-0.030
Tokenberg
Token ID3900
Feature activation+3.66e-02

Pos logit contributions
between+0.031
 Gaw+0.029
 undertaking+0.026
pty+0.024
devices+0.024
Neg logit contributions
united-0.048
CTV-0.044
 additive-0.038
 iod-0.037
 Bravo-0.034
Tokenwitz
Token ID28155
Feature activation+2.05e-01

Pos logit contributions
between+0.028
 Gaw+0.026
 undertaking+0.024
pty+0.023
abus+0.022
Neg logit contributions
united-0.033
CTV-0.030
 additive-0.025
 iod-0.025
SHARE-0.022
Token West
Token ID2688
Feature activation-3.46e-02

Pos logit contributions
between+0.159
 Gaw+0.147
 undertaking+0.133
pty+0.127
abus+0.125
Neg logit contributions
united-0.183
CTV-0.168
 additive-0.140
 iod-0.138
SHARE-0.125
Tokenchester
Token ID35983
Feature activation-6.32e-01

Pos logit contributions
united+0.031
CTV+0.028
 additive+0.023
 iod+0.023
SHARE+0.021
Neg logit contributions
between-0.027
 Gaw-0.025
 undertaking-0.023
pty-0.022
abus-0.021
Token 1
Token ID352
Feature activation-3.28e-01

Pos logit contributions
united+0.458
CTV+0.412
 additive+0.326
 iod+0.319
SHARE+0.278
Neg logit contributions
between-0.598
 Gaw-0.562
 undertaking-0.519
pty-0.500
abus-0.492
Token hour
Token ID1711
Feature activation-1.36e-01

Pos logit contributions
united+0.274
CTV+0.249
 additive+0.204
 iod+0.202
SHARE+0.181
Neg logit contributions
between-0.274
 Gaw-0.255
 undertaking-0.234
pty-0.222
abus-0.219
Token ago
Token ID2084
Feature activation+7.51e-03

Pos logit contributions
united+0.140
CTV+0.130
 additive+0.112
 iod+0.110
SHARE+0.102
Neg logit contributions
between-0.087
 Gaw-0.079
 undertaking-0.070
pty-0.066
abus-0.064
Token Pretty
Token ID20090
Feature activation-6.75e-02

Pos logit contributions
between+0.006
 Gaw+0.005
 undertaking+0.005
pty+0.005
abus+0.005
Neg logit contributions
united-0.007
CTV-0.006
 additive-0.005
 iod-0.005
SHARE-0.004
Token simple
Token ID2829
Feature activation-2.61e-01

Pos logit contributions
united+0.060
CTV+0.055
 additive+0.046
 iod+0.045
 Bravo+0.041
Neg logit contributions
between-0.053
 Gaw-0.049
 undertaking-0.044
pty-0.042
abus-0.041
Token Gutenberg
Token ID20336
Feature activation-9.07e-02

Pos logit contributions
between+0.035
 Gaw+0.032
 undertaking+0.029
pty+0.027
abus+0.027
Neg logit contributions
united-0.046
CTV-0.043
 additive-0.036
 iod-0.035
SHARE-0.032
Token (
Token ID357
Feature activation-7.47e-02

Pos logit contributions
united+0.078
CTV+0.071
 additive+0.059
 iod+0.058
SHARE+0.052
Neg logit contributions
between-0.074
 Gaw-0.069
 undertaking-0.062
pty-0.060
abus-0.059
Tokenwww
Token ID2503
Feature activation-7.61e-02

Pos logit contributions
united+0.068
CTV+0.063
 additive+0.052
 iod+0.052
SHARE+0.047
Neg logit contributions
between-0.057
 Gaw-0.053
 undertaking-0.048
pty-0.045
abus-0.044
Token.
Token ID13
Feature activation+1.42e-02

Pos logit contributions
united+0.070
CTV+0.064
 additive+0.054
 iod+0.053
SHARE+0.048
Neg logit contributions
between-0.057
 Gaw-0.053
 undertaking-0.048
pty-0.045
abus-0.045
Tokeng
Token ID70
Feature activation+1.13e-01

Pos logit contributions
between+0.011
 Gaw+0.010
 undertaking+0.009
pty+0.008
abus+0.008
Neg logit contributions
united-0.013
CTV-0.012
 additive-0.010
 iod-0.010
SHARE-0.009
Tokenutenberg
Token ID19028
Feature activation-6.21e-01

Pos logit contributions
between+0.148
 Gaw+0.142
 undertaking+0.134
pty+0.130
devices+0.129
Neg logit contributions
united-0.041
CTV-0.032
 additive-0.016
 iod-0.015
SHARE-0.008
Token.
Token ID13
Feature activation-1.20e-01

Pos logit contributions
united+0.569
CTV+0.519
 additive+0.432
 iod+0.426
SHARE+0.387
Neg logit contributions
between-0.471
 Gaw-0.440
 undertaking-0.396
pty-0.376
abus-0.369
Tokenorg
Token ID2398
Feature activation-2.98e-02

Pos logit contributions
united+0.117
CTV+0.107
 additive+0.091
 iod+0.090
SHARE+0.082
Neg logit contributions
between-0.084
 Gaw-0.077
 undertaking-0.069
pty-0.065
abus-0.064
Token).
Token ID737
Feature activation-8.81e-02

Pos logit contributions
united+0.028
CTV+0.025
 additive+0.021
 iod+0.021
SHARE+0.019
Neg logit contributions
between-0.022
 Gaw-0.021
 undertaking-0.019
pty-0.018
abus-0.017
Token Any
Token ID4377
Feature activation-1.38e-01

Pos logit contributions
united+0.077
CTV+0.070
 additive+0.058
 iod+0.057
SHARE+0.052
Neg logit contributions
between-0.071
 Gaw-0.065
 undertaking-0.060
pty-0.057
abus-0.056
Token file
Token ID2393
Feature activation-9.43e-02

Pos logit contributions
united+0.134
CTV+0.123
 additive+0.104
 iod+0.103
SHARE+0.094
Neg logit contributions
between-0.097
 Gaw-0.089
 undertaking-0.080
pty-0.076
abus-0.075
Token should
Token ID815
Feature activation+1.11e-01

Pos logit contributions
between+0.046
 Gaw+0.042
 undertaking+0.038
pty+0.037
abus+0.036
Neg logit contributions
united-0.051
CTV-0.047
 additive-0.039
 iod-0.038
SHARE-0.035
Token stay
Token ID2652
Feature activation-1.39e-01

Pos logit contributions
between+0.092
 Gaw+0.086
 undertaking+0.078
pty+0.075
abus+0.074
Neg logit contributions
united-0.094
CTV-0.085
 additive-0.070
 iod-0.069
SHARE-0.062
Token in
Token ID287
Feature activation+8.27e-02

Pos logit contributions
united+0.107
CTV+0.096
 additive+0.077
 iod+0.076
SHARE+0.067
Neg logit contributions
between-0.125
 Gaw-0.117
 undertaking-0.108
pty-0.104
abus-0.102
Token the
Token ID262
Feature activation-5.68e-03

Pos logit contributions
between+0.062
 Gaw+0.057
 undertaking+0.052
pty+0.050
abus+0.049
Neg logit contributions
united-0.076
CTV-0.070
 additive-0.059
 iod-0.058
 Bravo-0.052
Token mountain
Token ID8598
Feature activation+1.43e-01

Pos logit contributions
united+0.005
CTV+0.005
 additive+0.004
 iod+0.004
SHARE+0.004
Neg logit contributions
between-0.004
 Gaw-0.004
 undertaking-0.004
pty-0.003
abus-0.003
Token shack
Token ID32772
Feature activation-6.20e-01

Pos logit contributions
between+0.121
 Gaw+0.113
 undertaking+0.103
pty+0.099
abus+0.097
Neg logit contributions
united-0.119
CTV-0.108
 additive-0.088
 iod-0.087
SHARE-0.078
Token,
Token ID11
Feature activation-5.18e-02

Pos logit contributions
united+0.553
CTV+0.505
 additive+0.422
 iod+0.413
SHARE+0.374
Neg logit contributions
between-0.482
 Gaw-0.448
 undertaking-0.404
pty-0.389
abus-0.382
Token and
Token ID290
Feature activation-4.27e-02

Pos logit contributions
united+0.047
CTV+0.042
 additive+0.036
 iod+0.035
 Bravo+0.032
Neg logit contributions
between-0.040
 Gaw-0.037
 undertaking-0.033
pty-0.032
abus-0.032
Token please
Token ID3387
Feature activation-1.38e-01

Pos logit contributions
united+0.037
CTV+0.034
 additive+0.028
 iod+0.028
 Bravo+0.025
Neg logit contributions
between-0.034
 Gaw-0.031
 undertaking-0.028
pty-0.027
abus-0.027
Token rest
Token ID1334
Feature activation+1.27e-01

Pos logit contributions
united+0.111
CTV+0.101
 additive+0.082
 iod+0.080
SHARE+0.071
Neg logit contributions
between-0.120
 Gaw-0.112
 undertaking-0.103
pty-0.099
abus-0.097
Token and
Token ID290
Feature activation-1.77e-02

Pos logit contributions
between+0.100
 Gaw+0.093
 undertaking+0.084
pty+0.080
abus+0.079
Neg logit contributions
united-0.113
CTV-0.103
 additive-0.086
 iod-0.084
SHARE-0.076
Token 16
Token ID1467
Feature activation-7.96e-03

Pos logit contributions
between+0.045
 Gaw+0.042
 undertaking+0.039
pty+0.037
abus+0.037
Neg logit contributions
united-0.044
CTV-0.040
 additive-0.032
 iod-0.032
SHARE-0.028
Token,
Token ID11
Feature activation-2.36e-02

Pos logit contributions
united+0.006
CTV+0.006
 additive+0.005
 iod+0.005
SHARE+0.004
Neg logit contributions
between-0.007
 Gaw-0.006
 undertaking-0.006
pty-0.006
abus-0.006
Token 1981
Token ID14745
Feature activation+1.05e-01

Pos logit contributions
united+0.027
CTV+0.025
 additive+0.022
 iod+0.021
SHARE+0.020
Neg logit contributions
between-0.013
 Gaw-0.012
 undertaking-0.010
pty-0.009
abus-0.009
Token
Token ID198
Feature activation+8.69e-03

Pos logit contributions
between+0.076
 Gaw+0.070
 undertaking+0.063
pty+0.060
abus+0.059
Neg logit contributions
united-0.099
CTV-0.091
 additive-0.077
 iod-0.076
SHARE-0.069
Token
Token ID198
Feature activation-1.33e-02

Pos logit contributions
between+0.006
 Gaw+0.006
 undertaking+0.005
pty+0.005
abus+0.005
Neg logit contributions
united-0.008
CTV-0.007
 additive-0.006
 iod-0.006
SHARE-0.006
TokenBirth
Token ID38480
Feature activation-6.10e-01

Pos logit contributions
united+0.010
CTV+0.009
 additive+0.007
 iod+0.007
 Bravo+0.006
Neg logit contributions
between-0.012
 Gaw-0.011
 undertaking-0.010
pty-0.010
abus-0.010
Tokenplace
Token ID5372
Feature activation-1.74e-01

Pos logit contributions
united+0.467
CTV+0.417
 additive+0.331
 iod+0.328
 Bravo+0.288
Neg logit contributions
between-0.556
 Gaw-0.524
 undertaking-0.481
pty-0.466
devices-0.455
Token:
Token ID25
Feature activation-3.44e-01

Pos logit contributions
united+0.108
CTV+0.095
 additive+0.072
 iod+0.070
SHARE+0.059
Neg logit contributions
between-0.182
 Gaw-0.172
 undertaking-0.160
pty-0.155
abus-0.153
Token Long
Token ID5882
Feature activation-2.40e-01

Pos logit contributions
united+0.325
CTV+0.298
 additive+0.251
 iod+0.247
SHARE+0.226
Neg logit contributions
between-0.251
 Gaw-0.231
 undertaking-0.209
pty-0.198
abus-0.195
Token Beach
Token ID8511
Feature activation-2.89e-02

Pos logit contributions
united+0.219
CTV+0.201
 additive+0.168
 iod+0.165
SHARE+0.150
Neg logit contributions
between-0.183
 Gaw-0.169
 undertaking-0.153
pty-0.146
abus-0.143
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
united+0.024
CTV+0.022
 additive+0.018
 iod+0.018
SHARE+0.016
Neg logit contributions
between-0.024
 Gaw-0.022
 undertaking-0.020
pty-0.019
abus-0.019
Token
Token ID198
Feature activation-1.49e-02

Pos logit contributions
united+0.002
CTV+0.002
 additive+0.002
 iod+0.002
 Bravo+0.001
Neg logit contributions
between-0.002
 Gaw-0.002
 undertaking-0.002
pty-0.001
abus-0.001
Token
Token ID198
Feature activation-3.30e-02

Pos logit contributions
united+0.014
CTV+0.013
 additive+0.010
 iod+0.010
SHARE+0.009
Neg logit contributions
between-0.011
 Gaw-0.010
 undertaking-0.009
pty-0.009
abus-0.009
TokenAt
Token ID2953
Feature activation-1.07e-01

Pos logit contributions
united+0.029
CTV+0.026
 additive+0.021
 iod+0.021
SHARE+0.019
Neg logit contributions
between-0.027
 Gaw-0.025
 undertaking-0.023
pty-0.022
abus-0.021
Token G
Token ID402
Feature activation+8.10e-02

Pos logit contributions
united+0.105
CTV+0.097
 additive+0.082
 iod+0.081
 Bravo+0.074
Neg logit contributions
between-0.074
 Gaw-0.068
 undertaking-0.061
pty-0.058
abus-0.057
Tokenf
Token ID69
Feature activation-3.28e-02

Pos logit contributions
between+0.063
 Gaw+0.059
 undertaking+0.053
pty+0.051
abus+0.050
Neg logit contributions
united-0.072
CTV-0.066
 additive-0.055
 iod-0.054
SHARE-0.049
Tokeninity
Token ID6269
Feature activation-6.08e-01

Pos logit contributions
united+0.020
CTV+0.017
 additive+0.013
 iod+0.013
SHARE+0.010
Neg logit contributions
between-0.035
 Gaw-0.033
 undertaking-0.031
pty-0.030
abus-0.030
Token 3
Token ID513
Feature activation-1.92e-01

Pos logit contributions
united+0.537
CTV+0.490
 additive+0.408
 iod+0.400
SHARE+0.362
Neg logit contributions
between-0.482
 Gaw-0.446
 undertaking-0.405
pty-0.387
abus-0.381
Token r
Token ID374
Feature activation-1.72e-01

Pos logit contributions
united+0.164
CTV+0.150
 additive+0.123
 iod+0.121
SHARE+0.109
Neg logit contributions
between-0.157
 Gaw-0.146
 undertaking-0.133
pty-0.127
abus-0.125
Tokenai
Token ID1872
Feature activation+2.74e-03

Pos logit contributions
united+0.158
CTV+0.145
 additive+0.121
 iod+0.120
SHARE+0.109
Neg logit contributions
between-0.130
 Gaw-0.120
 undertaking-0.108
pty-0.103
abus-0.101
TokenN
Token ID45
Feature activation-5.32e-02

Pos logit contributions
between+0.002
 Gaw+0.002
 undertaking+0.002
pty+0.002
abus+0.002
Neg logit contributions
united-0.002
CTV-0.002
 additive-0.002
 iod-0.002
SHARE-0.002
Token had
Token ID550
Feature activation-6.70e-02

Pos logit contributions
united+0.048
CTV+0.043
 additive+0.036
 iod+0.036
SHARE+0.032
Neg logit contributions
between-0.042
 Gaw-0.038
 undertaking-0.035
pty-0.033
abus-0.033
Token who
Token ID508
Feature activation+1.57e-01

Pos logit contributions
united+0.068
CTV+0.062
 additive+0.053
 iod+0.052
 Bravo+0.048
Neg logit contributions
between-0.046
 Gaw-0.041
 undertaking-0.037
pty-0.036
abus-0.035
Token,
Token ID11
Feature activation-9.56e-02

Pos logit contributions
between+0.111
 Gaw+0.102
 undertaking+0.092
pty+0.087
abus+0.086
Neg logit contributions
united-0.151
CTV-0.139
 additive-0.117
 iod-0.116
SHARE-0.106
Token unlike
Token ID5023
Feature activation+1.45e-01

Pos logit contributions
united+0.092
CTV+0.085
 additive+0.072
 iod+0.071
 Bravo+0.065
Neg logit contributions
between-0.067
 Gaw-0.061
 undertaking-0.055
pty-0.053
abus-0.052
Token his
Token ID465
Feature activation-8.50e-02

Pos logit contributions
between+0.110
 Gaw+0.100
 undertaking+0.091
pty+0.088
abus+0.086
Neg logit contributions
united-0.133
CTV-0.122
 additive-0.102
 iod-0.100
 Bravo-0.092
Token brother
Token ID3956
Feature activation+3.65e-02

Pos logit contributions
united+0.075
CTV+0.068
 additive+0.057
 iod+0.056
SHARE+0.050
Neg logit contributions
between-0.068
 Gaw-0.063
 undertaking-0.057
pty-0.055
abus-0.054
Token Bor
Token ID12182
Feature activation-6.04e-01

Pos logit contributions
between+0.030
 Gaw+0.027
 undertaking+0.025
pty+0.024
abus+0.024
Neg logit contributions
united-0.031
CTV-0.029
 additive-0.024
 iod-0.023
 Bravo-0.021
Tokenom
Token ID296
Feature activation-3.22e-02

Pos logit contributions
united+0.571
CTV+0.522
 additive+0.438
 iod+0.434
 Bravo+0.395
Neg logit contributions
between-0.438
 Gaw-0.402
 undertaking-0.365
pty-0.348
devices-0.340
Tokenir
Token ID343
Feature activation-1.63e-01

Pos logit contributions
united+0.028
CTV+0.026
 additive+0.022
 iod+0.021
SHARE+0.019
Neg logit contributions
between-0.025
 Gaw-0.024
 undertaking-0.021
pty-0.020
abus-0.020
Token,
Token ID11
Feature activation-6.83e-03

Pos logit contributions
united+0.132
CTV+0.120
 additive+0.098
 iod+0.096
SHARE+0.086
Neg logit contributions
between-0.140
 Gaw-0.130
 undertaking-0.120
pty-0.115
abus-0.113
Token resists
Token ID47786
Feature activation+1.84e-01

Pos logit contributions
united+0.007
CTV+0.006
 additive+0.005
 iod+0.005
 Bravo+0.005
Neg logit contributions
between-0.005
 Gaw-0.004
 undertaking-0.004
pty-0.004
abus-0.004
Token the
Token ID262
Feature activation-4.58e-02

Pos logit contributions
between+0.141
 Gaw+0.129
 undertaking+0.117
pty+0.114
abus+0.111
Neg logit contributions
united-0.167
CTV-0.153
 additive-0.128
 iod-0.126
 Bravo-0.114
Tokenik
Token ID1134
Feature activation+1.81e-01

Pos logit contributions
united+0.396
CTV+0.365
 additive+0.312
 iod+0.309
 Bravo+0.283
Neg logit contributions
between-0.252
 Gaw-0.231
 undertaking-0.207
pty-0.191
devices-0.190
Tokenov
Token ID709
Feature activation-7.33e-02

Pos logit contributions
between+0.139
 Gaw+0.129
 undertaking+0.117
pty+0.111
abus+0.109
Neg logit contributions
united-0.164
CTV-0.150
 additive-0.126
 iod-0.124
SHARE-0.112
Token and
Token ID290
Feature activation-9.26e-02

Pos logit contributions
united+0.063
CTV+0.057
 additive+0.047
 iod+0.047
SHARE+0.042
Neg logit contributions
between-0.060
 Gaw-0.055
 undertaking-0.050
pty-0.048
abus-0.047
Token And
Token ID843
Feature activation-2.08e-01

Pos logit contributions
united+0.091
CTV+0.084
 additive+0.071
 iod+0.070
 Bravo+0.064
Neg logit contributions
between-0.064
 Gaw-0.059
 undertaking-0.053
pty-0.050
abus-0.049
Tokenrey
Token ID4364
Feature activation+6.34e-02

Pos logit contributions
united+0.203
CTV+0.185
 additive+0.158
 iod+0.155
 Bravo+0.144
Neg logit contributions
between-0.144
 Gaw-0.134
 undertaking-0.121
pty-0.112
devices-0.111
Token Bor
Token ID12182
Feature activation-6.01e-01

Pos logit contributions
between+0.047
 Gaw+0.043
 undertaking+0.039
pty+0.037
abus+0.037
Neg logit contributions
united-0.059
CTV-0.054
 additive-0.046
 iod-0.045
 Bravo-0.041
Tokenisen
Token ID13254
Feature activation-1.23e-01

Pos logit contributions
united+0.539
CTV+0.491
 additive+0.407
 iod+0.402
SHARE+0.362
Neg logit contributions
between-0.465
 Gaw-0.436
 undertaking-0.396
pty-0.372
devices-0.366
Tokenko
Token ID7204
Feature activation-1.24e-01

Pos logit contributions
united+0.113
CTV+0.104
 additive+0.087
 iod+0.086
SHARE+0.078
Neg logit contributions
between-0.092
 Gaw-0.085
 undertaking-0.076
pty-0.073
abus-0.071
Token is
Token ID318
Feature activation+2.36e-02

Pos logit contributions
united+0.106
CTV+0.097
 additive+0.080
 iod+0.079
SHARE+0.071
Neg logit contributions
between-0.101
 Gaw-0.094
 undertaking-0.086
pty-0.082
abus-0.081
Token scheduled
Token ID7530
Feature activation-3.83e-01

Pos logit contributions
between+0.019
 Gaw+0.018
 undertaking+0.016
pty+0.016
abus+0.015
Neg logit contributions
united-0.020
CTV-0.018
 additive-0.015
 iod-0.015
 Bravo-0.014
Token to
Token ID284
Feature activation-6.53e-02

Pos logit contributions
united+0.362
CTV+0.334
 additive+0.281
 iod+0.277
SHARE+0.253
Neg logit contributions
between-0.278
 Gaw-0.256
 undertaking-0.231
pty-0.219
abus-0.215
Token
Token ID247
Feature activation+3.06e-02

Pos logit contributions
united+0.076
CTV+0.070
 additive+0.057
 iod+0.056
SHARE+0.051
Neg logit contributions
between-0.074
 Gaw-0.068
 undertaking-0.062
pty-0.060
abus-0.059
Tokens
Token ID82
Feature activation-2.22e-02

Pos logit contributions
between+0.022
 Gaw+0.020
 undertaking+0.018
pty+0.017
abus+0.017
Neg logit contributions
united-0.029
CTV-0.027
 additive-0.023
 iod-0.022
SHARE-0.020
Token agent
Token ID5797
Feature activation-3.73e-01

Pos logit contributions
united+0.018
CTV+0.016
 additive+0.013
 iod+0.013
SHARE+0.012
Neg logit contributions
between-0.019
 Gaw-0.018
 undertaking-0.017
pty-0.016
abus-0.016
Token,
Token ID11
Feature activation-7.94e-02

Pos logit contributions
united+0.329
CTV+0.301
 additive+0.250
 iod+0.246
SHARE+0.222
Neg logit contributions
between-0.294
 Gaw-0.273
 undertaking-0.248
pty-0.237
abus-0.233
Token Scott
Token ID4746
Feature activation-4.16e-02

Pos logit contributions
united+0.079
CTV+0.073
 additive+0.062
 iod+0.061
SHARE+0.056
Neg logit contributions
between-0.054
 Gaw-0.049
 undertaking-0.044
pty-0.042
abus-0.041
Token Bor
Token ID12182
Feature activation-5.98e-01

Pos logit contributions
united+0.038
CTV+0.035
 additive+0.029
 iod+0.029
SHARE+0.026
Neg logit contributions
between-0.031
 Gaw-0.029
 undertaking-0.026
pty-0.025
abus-0.025
Tokenas
Token ID292
Feature activation-3.36e-02

Pos logit contributions
united+0.610
CTV+0.563
 additive+0.480
 iod+0.476
SHARE+0.437
Neg logit contributions
between-0.391
 Gaw-0.358
 undertaking-0.317
pty-0.298
devices-0.291
Token.
Token ID13
Feature activation-4.62e-02

Pos logit contributions
united+0.029
CTV+0.026
 additive+0.022
 iod+0.022
SHARE+0.019
Neg logit contributions
between-0.027
 Gaw-0.025
 undertaking-0.023
pty-0.022
abus-0.022
Token With
Token ID2080
Feature activation-1.50e-02

Pos logit contributions
united+0.041
CTV+0.037
 additive+0.031
 iod+0.031
SHARE+0.028
Neg logit contributions
between-0.036
 Gaw-0.034
 undertaking-0.030
pty-0.029
abus-0.029
Token the
Token ID262
Feature activation-7.48e-02

Pos logit contributions
united+0.014
CTV+0.013
 additive+0.011
 iod+0.011
SHARE+0.010
Neg logit contributions
between-0.011
 Gaw-0.010
 undertaking-0.009
pty-0.009
abus-0.009
Token slot
Token ID10852
Feature activation-3.11e-01

Pos logit contributions
united+0.067
CTV+0.062
 additive+0.051
 iod+0.050
SHARE+0.046
Neg logit contributions
between-0.058
 Gaw-0.054
 undertaking-0.049
pty-0.046
abus-0.046
Token small
Token ID1402
Feature activation-1.02e-01

Pos logit contributions
between+0.012
 Gaw+0.011
 undertaking+0.010
pty+0.010
abus+0.010
Neg logit contributions
united-0.014
CTV-0.013
 additive-0.011
 iod-0.010
SHARE-0.009
Token distance
Token ID5253
Feature activation-1.12e-01

Pos logit contributions
united+0.076
CTV+0.068
 additive+0.054
 iod+0.053
SHARE+0.047
Neg logit contributions
between-0.094
 Gaw-0.088
 undertaking-0.081
pty-0.078
abus-0.077
Token to
Token ID284
Feature activation+2.61e-02

Pos logit contributions
united+0.080
CTV+0.072
 additive+0.056
 iod+0.055
SHARE+0.048
Neg logit contributions
between-0.108
 Gaw-0.101
 undertaking-0.094
pty-0.090
abus-0.089
Token the
Token ID262
Feature activation-4.85e-02

Pos logit contributions
between+0.019
 Gaw+0.018
 undertaking+0.016
pty+0.015
abus+0.015
Neg logit contributions
united-0.024
CTV-0.022
 additive-0.019
 iod-0.019
SHARE-0.017
Token mountain
Token ID8598
Feature activation+2.03e-01

Pos logit contributions
united+0.042
CTV+0.038
 additive+0.032
 iod+0.031
SHARE+0.028
Neg logit contributions
between-0.039
 Gaw-0.037
 undertaking-0.033
pty-0.032
abus-0.031
Token shack
Token ID32772
Feature activation-5.92e-01

Pos logit contributions
between+0.160
 Gaw+0.149
 undertaking+0.135
pty+0.129
abus+0.127
Neg logit contributions
united-0.179
CTV-0.163
 additive-0.135
 iod-0.133
SHARE-0.121
Token,
Token ID11
Feature activation-2.87e-02

Pos logit contributions
united+0.519
CTV+0.473
 additive+0.393
 iod+0.386
SHARE+0.349
Neg logit contributions
between-0.470
 Gaw-0.436
 undertaking-0.396
pty-0.380
abus-0.374
Token and
Token ID290
Feature activation-4.52e-02

Pos logit contributions
united+0.027
CTV+0.025
 additive+0.021
 iod+0.021
SHARE+0.019
Neg logit contributions
between-0.020
 Gaw-0.019
 undertaking-0.017
pty-0.016
abus-0.016
Token by
Token ID416
Feature activation-9.08e-02

Pos logit contributions
united+0.043
CTV+0.039
 additive+0.033
 iod+0.033
 Bravo+0.030
Neg logit contributions
between-0.033
 Gaw-0.030
 undertaking-0.027
pty-0.026
abus-0.026
Token the
Token ID262
Feature activation-1.76e-02

Pos logit contributions
united+0.087
CTV+0.079
 additive+0.068
 iod+0.067
 Bravo+0.061
Neg logit contributions
between-0.064
 Gaw-0.059
 undertaking-0.053
pty-0.051
abus-0.050
Token time
Token ID640
Feature activation+1.21e-01

Pos logit contributions
united+0.018
CTV+0.016
 additive+0.014
 iod+0.014
 Bravo+0.013
Neg logit contributions
between-0.012
 Gaw-0.011
 undertaking-0.010
pty-0.009
abus-0.009
Token total
Token ID2472
Feature activation+9.72e-02

Pos logit contributions
united+0.068
CTV+0.062
 additive+0.052
 iod+0.051
SHARE+0.046
Neg logit contributions
between-0.058
 Gaw-0.054
 undertaking-0.049
pty-0.047
abus-0.046
Token mass
Token ID2347
Feature activation-1.14e-01

Pos logit contributions
between+0.083
 Gaw+0.077
 undertaking+0.071
pty+0.068
abus+0.067
Neg logit contributions
united-0.080
CTV-0.072
 additive-0.059
 iod-0.058
SHARE-0.052
Token that
Token ID326
Feature activation-4.32e-02

Pos logit contributions
united+0.106
CTV+0.098
 additive+0.082
 iod+0.081
SHARE+0.074
Neg logit contributions
between-0.084
 Gaw-0.078
 undertaking-0.070
pty-0.067
abus-0.066
Token the
Token ID262
Feature activation-1.22e-01

Pos logit contributions
united+0.038
CTV+0.035
 additive+0.029
 iod+0.029
SHARE+0.026
Neg logit contributions
between-0.034
 Gaw-0.031
 undertaking-0.028
pty-0.027
abus-0.027
Token v
Token ID410
Feature activation-3.24e-01

Pos logit contributions
united+0.110
CTV+0.101
 additive+0.084
 iod+0.083
SHARE+0.075
Neg logit contributions
between-0.094
 Gaw-0.087
 undertaking-0.079
pty-0.075
abus-0.074
Tokenort
Token ID419
Feature activation-5.91e-01

Pos logit contributions
united+0.234
CTV+0.210
 additive+0.166
 iod+0.163
SHARE+0.142
Neg logit contributions
between-0.308
 Gaw-0.288
 undertaking-0.267
pty-0.258
abus-0.254
Tokenons
Token ID684
Feature activation-4.02e-01

Pos logit contributions
united+0.435
CTV+0.391
 additive+0.310
 iod+0.304
SHARE+0.266
Neg logit contributions
between-0.553
 Gaw-0.519
 undertaking-0.480
pty-0.462
abus-0.456
Token carry
Token ID3283
Feature activation-2.19e-01

Pos logit contributions
united+0.323
CTV+0.292
 additive+0.238
 iod+0.234
SHARE+0.207
Neg logit contributions
between-0.348
 Gaw-0.326
 undertaking-0.298
pty-0.287
abus-0.283
Token needs
Token ID2476
Feature activation+7.20e-02

Pos logit contributions
united+0.216
CTV+0.200
 additive+0.171
 iod+0.169
SHARE+0.154
Neg logit contributions
between-0.149
 Gaw-0.137
 undertaking-0.121
pty-0.116
abus-0.113
Token to
Token ID284
Feature activation-2.85e-02

Pos logit contributions
between+0.053
 Gaw+0.049
 undertaking+0.044
pty+0.042
abus+0.041
Neg logit contributions
united-0.068
CTV-0.062
 additive-0.053
 iod-0.052
SHARE-0.047
Token match
Token ID2872
Feature activation-4.12e-02

Pos logit contributions
united+0.026
CTV+0.024
 additive+0.020
 iod+0.020
SHARE+0.018
Neg logit contributions
between-0.021
 Gaw-0.020
 undertaking-0.018
pty-0.017
abus-0.017
Token publication
Token ID9207
Feature activation+6.99e-02

Pos logit contributions
between+0.044
 Gaw+0.040
 undertaking+0.035
pty+0.033
abus+0.032
Neg logit contributions
united-0.083
CTV-0.077
 additive-0.067
 iod-0.066
SHARE-0.061
Token in
Token ID287
Feature activation+4.52e-02

Pos logit contributions
between+0.054
 Gaw+0.050
 undertaking+0.046
pty+0.043
abus+0.043
Neg logit contributions
united-0.063
CTV-0.057
 additive-0.048
 iod-0.047
SHARE-0.043
Token the
Token ID262
Feature activation-2.69e-02

Pos logit contributions
between+0.033
 Gaw+0.031
 undertaking+0.028
pty+0.026
abus+0.026
Neg logit contributions
united-0.043
CTV-0.039
 additive-0.033
 iod-0.032
SHARE-0.030
Token Ast
Token ID8304
Feature activation-2.34e-01

Pos logit contributions
united+0.026
CTV+0.024
 additive+0.020
 iod+0.020
SHARE+0.018
Neg logit contributions
between-0.019
 Gaw-0.017
 undertaking-0.016
pty-0.015
abus-0.014
Tokenroph
Token ID10051
Feature activation-9.91e-02

Pos logit contributions
united+0.254
CTV+0.236
 additive+0.204
 iod+0.201
SHARE+0.187
Neg logit contributions
between-0.137
 Gaw-0.124
 undertaking-0.108
pty-0.101
abus-0.099
Tokenysical
Token ID15380
Feature activation-5.88e-01

Pos logit contributions
united+0.050
CTV+0.042
 additive+0.029
 iod+0.027
SHARE+0.021
Neg logit contributions
between-0.116
 Gaw-0.110
 undertaking-0.104
pty-0.101
abus-0.100
Token Journal
Token ID4913
Feature activation-3.06e-01

Pos logit contributions
united+0.394
CTV+0.349
 additive+0.271
 iod+0.265
SHARE+0.226
Neg logit contributions
between-0.587
 Gaw-0.556
 undertaking-0.515
pty-0.499
abus-0.493
Token (
Token ID357
Feature activation-5.22e-02

Pos logit contributions
united+0.277
CTV+0.253
 additive+0.213
 iod+0.209
 Bravo+0.189
Neg logit contributions
between-0.235
 Gaw-0.217
 undertaking-0.196
pty-0.188
abus-0.184
Tokenar
Token ID283
Feature activation-1.83e-01

Pos logit contributions
united+0.046
CTV+0.042
 additive+0.035
 iod+0.034
SHARE+0.031
Neg logit contributions
between-0.042
 Gaw-0.039
 undertaking-0.035
pty-0.033
abus-0.033
TokenX
Token ID55
Feature activation-4.70e-02

Pos logit contributions
united+0.153
CTV+0.140
 additive+0.115
 iod+0.112
SHARE+0.101
Neg logit contributions
between-0.152
 Gaw-0.142
 undertaking-0.130
pty-0.124
devices-0.121
Tokeniv
Token ID452
Feature activation+1.70e-01

Pos logit contributions
united+0.054
CTV+0.050
 additive+0.044
 iod+0.043
SHARE+0.041
Neg logit contributions
between-0.024
 Gaw-0.023
 undertaking-0.019
pty-0.018
devices-0.017
Token format
Token ID5794
Feature activation-1.65e-01

Pos logit contributions
united+0.082
CTV+0.075
 additive+0.063
 iod+0.062
SHARE+0.056
Neg logit contributions
between-0.070
 Gaw-0.064
 undertaking-0.058
pty-0.056
abus-0.055
Token,
Token ID11
Feature activation-9.19e-02

Pos logit contributions
united+0.150
CTV+0.137
 additive+0.115
 iod+0.113
SHARE+0.102
Neg logit contributions
between-0.127
 Gaw-0.117
 undertaking-0.106
pty-0.101
abus-0.100
Token enabling
Token ID15882
Feature activation-6.05e-02

Pos logit contributions
united+0.099
CTV+0.092
 additive+0.080
 iod+0.079
SHARE+0.073
Neg logit contributions
between-0.054
 Gaw-0.049
 undertaking-0.042
pty-0.040
abus-0.039
Token a
Token ID257
Feature activation+1.36e-02

Pos logit contributions
united+0.051
CTV+0.046
 additive+0.038
 iod+0.037
SHARE+0.034
Neg logit contributions
between-0.050
 Gaw-0.047
 undertaking-0.043
pty-0.041
abus-0.040
Token single
Token ID2060
Feature activation-3.84e-01

Pos logit contributions
between+0.011
 Gaw+0.011
 undertaking+0.010
pty+0.009
abus+0.009
Neg logit contributions
united-0.011
CTV-0.010
 additive-0.008
 iod-0.008
SHARE-0.007
Token binary
Token ID13934
Feature activation-5.87e-01

Pos logit contributions
united+0.341
CTV+0.312
 additive+0.256
 iod+0.254
SHARE+0.230
Neg logit contributions
between-0.302
 Gaw-0.281
 undertaking-0.256
pty-0.243
abus-0.237
Token package
Token ID5301
Feature activation-5.75e-02

Pos logit contributions
united+0.536
CTV+0.491
 additive+0.411
 iod+0.405
SHARE+0.367
Neg logit contributions
between-0.446
 Gaw-0.412
 undertaking-0.373
pty-0.355
abus-0.349
Token to
Token ID284
Feature activation-2.51e-02

Pos logit contributions
united+0.053
CTV+0.048
 additive+0.041
 iod+0.040
SHARE+0.036
Neg logit contributions
between-0.043
 Gaw-0.040
 undertaking-0.036
pty-0.034
abus-0.034
Token work
Token ID670
Feature activation-8.81e-02

Pos logit contributions
united+0.024
CTV+0.023
 additive+0.019
 iod+0.019
SHARE+0.017
Neg logit contributions
between-0.018
 Gaw-0.016
 undertaking-0.014
pty-0.014
abus-0.013
Token perfectly
Token ID7138
Feature activation-2.47e-01

Pos logit contributions
united+0.072
CTV+0.066
 additive+0.053
 iod+0.053
SHARE+0.047
Neg logit contributions
between-0.075
 Gaw-0.070
 undertaking-0.064
pty-0.061
abus-0.060
Token and
Token ID290
Feature activation-5.21e-02

Pos logit contributions
united+0.209
CTV+0.191
 additive+0.156
 iod+0.154
SHARE+0.139
Neg logit contributions
between-0.204
 Gaw-0.189
 undertaking-0.173
pty-0.165
abus-0.162
TokenGet
Token ID3855
Feature activation-2.26e-01

Pos logit contributions
united+0.062
CTV+0.055
 additive+0.042
 iod+0.041
SHARE+0.036
Neg logit contributions
between-0.094
 Gaw-0.089
 undertaking-0.083
pty-0.080
abus-0.079
TokenMass
Token ID20273
Feature activation-2.61e-01

Pos logit contributions
united+0.176
CTV+0.159
 additive+0.128
 iod+0.125
SHARE+0.111
Neg logit contributions
between-0.202
 Gaw-0.189
 undertaking-0.174
pty-0.167
abus-0.165
Token(
Token ID7
Feature activation+2.75e-02

Pos logit contributions
united+0.227
CTV+0.207
 additive+0.172
 iod+0.169
SHARE+0.152
Neg logit contributions
between-0.210
 Gaw-0.195
 undertaking-0.177
pty-0.169
abus-0.167
Token ambient
Token ID25237
Feature activation-2.42e-01

Pos logit contributions
between+0.022
 Gaw+0.021
 undertaking+0.019
pty+0.018
abus+0.018
Neg logit contributions
united-0.023
CTV-0.021
 additive-0.018
 iod-0.017
SHARE-0.016
TokenD
Token ID35
Feature activation-1.78e-01

Pos logit contributions
united+0.201
CTV+0.183
 additive+0.149
 iod+0.148
SHARE+0.132
Neg logit contributions
between-0.204
 Gaw-0.189
 undertaking-0.173
pty-0.166
abus-0.164
Tokenensity
Token ID6377
Feature activation-5.85e-01

Pos logit contributions
united+0.118
CTV+0.105
 additive+0.080
 iod+0.079
SHARE+0.068
Neg logit contributions
between-0.180
 Gaw-0.168
 undertaking-0.157
pty-0.152
abus-0.150
Token ).
Token ID6739
Feature activation-1.49e-01

Pos logit contributions
united+0.471
CTV+0.427
 additive+0.346
 iod+0.341
SHARE+0.303
Neg logit contributions
between-0.508
 Gaw-0.474
 undertaking-0.435
pty-0.417
abus-0.411
Token //
Token ID3373
Feature activation-1.55e-01

Pos logit contributions
united+0.127
CTV+0.116
 additive+0.095
 iod+0.094
SHARE+0.084
Neg logit contributions
between-0.122
 Gaw-0.114
 undertaking-0.104
pty-0.099
abus-0.098
Token This
Token ID770
Feature activation-4.03e-02

Pos logit contributions
united+0.135
CTV+0.124
 additive+0.103
 iod+0.101
SHARE+0.091
Neg logit contributions
between-0.124
 Gaw-0.115
 undertaking-0.105
pty-0.100
abus-0.099
Token is
Token ID318
Feature activation+6.53e-02

Pos logit contributions
united+0.037
CTV+0.034
 additive+0.029
 iod+0.028
SHARE+0.026
Neg logit contributions
between-0.030
 Gaw-0.028
 undertaking-0.025
pty-0.024
abus-0.024
Token because
Token ID780
Feature activation+3.05e-02

Pos logit contributions
between+0.050
 Gaw+0.046
 undertaking+0.041
pty+0.040
abus+0.039
Neg logit contributions
united-0.060
CTV-0.055
 additive-0.046
 iod-0.045
SHARE-0.041
Token Far
Token ID6755
Feature activation-4.81e-03

Pos logit contributions
between+0.024
 Gaw+0.022
 undertaking+0.020
pty+0.019
abus+0.019
Neg logit contributions
united-0.029
CTV-0.027
 additive-0.022
 iod-0.022
SHARE-0.020
Tokenrah
Token ID11392
Feature activation+1.51e-01

Pos logit contributions
united+0.004
CTV+0.003
 additive+0.003
 iod+0.003
 Bravo+0.002
Neg logit contributions
between-0.004
 Gaw-0.004
 undertaking-0.004
pty-0.003
abus-0.003
Token W
Token ID370
Feature activation+5.29e-02

Pos logit contributions
between+0.094
 Gaw+0.085
 undertaking+0.075
pty+0.070
abus+0.069
Neg logit contributions
united-0.159
CTV-0.148
 additive-0.127
 iod-0.126
SHARE-0.116
Tokenether
Token ID6750
Feature activation-1.91e-01

Pos logit contributions
between+0.039
 Gaw+0.036
 undertaking+0.032
pty+0.031
abus+0.030
Neg logit contributions
united-0.049
CTV-0.045
 additive-0.038
 iod-0.038
SHARE-0.034
Tokens
Token ID82
Feature activation+1.08e-01

Pos logit contributions
united+0.183
CTV+0.168
 additive+0.142
 iod+0.140
 Bravo+0.128
Neg logit contributions
between-0.136
 Gaw-0.125
 undertaking-0.113
pty-0.107
abus-0.106
Token Mysteries
Token ID28298
Feature activation-5.83e-01

Pos logit contributions
between+0.088
 Gaw+0.082
 undertaking+0.075
pty+0.071
abus+0.070
Neg logit contributions
united-0.093
CTV-0.085
 additive-0.070
 iod-0.069
SHARE-0.062
Token,
Token ID11
Feature activation-4.30e-02

Pos logit contributions
united+0.495
CTV+0.451
 additive+0.371
 iod+0.365
SHARE+0.328
Neg logit contributions
between-0.480
 Gaw-0.447
 undertaking-0.408
pty-0.390
abus-0.385
Token comic
Token ID9048
Feature activation+3.73e-02

Pos logit contributions
united+0.039
CTV+0.036
 additive+0.030
 iod+0.029
 Bravo+0.027
Neg logit contributions
between-0.033
 Gaw-0.030
 undertaking-0.027
pty-0.026
abus-0.026
Token book
Token ID1492
Feature activation+2.14e-01

Pos logit contributions
between+0.025
 Gaw+0.023
 undertaking+0.020
pty+0.019
abus+0.019
Neg logit contributions
united-0.037
CTV-0.034
 additive-0.029
 iod-0.029
 Bravo-0.027
Token short
Token ID1790
Feature activation-1.87e-01

Pos logit contributions
between+0.162
 Gaw+0.150
 undertaking+0.136
pty+0.130
abus+0.127
Neg logit contributions
united-0.195
CTV-0.179
 additive-0.150
 iod-0.147
SHARE-0.134
Token stories
Token ID3923
Feature activation-8.53e-02

Pos logit contributions
united+0.171
CTV+0.157
 additive+0.132
 iod+0.129
SHARE+0.118
Neg logit contributions
between-0.141
 Gaw-0.130
 undertaking-0.118
pty-0.112
abus-0.111
Token Bal
Token ID8528
Feature activation+2.86e-01

Pos logit contributions
between+0.063
 Gaw+0.058
 undertaking+0.053
pty+0.050
abus+0.049
Neg logit contributions
united-0.079
CTV-0.072
 additive-0.061
 iod-0.060
 Bravo-0.055
Tokenrog
Token ID3828
Feature activation+9.58e-02

Pos logit contributions
between+0.221
 Gaw+0.206
 undertaking+0.188
pty+0.178
devices+0.175
Neg logit contributions
united-0.256
CTV-0.233
 additive-0.194
 iod-0.191
SHARE-0.172
Token.
Token ID13
Feature activation+8.50e-03

Pos logit contributions
between+0.074
 Gaw+0.068
 undertaking+0.062
pty+0.059
abus+0.059
Neg logit contributions
united-0.086
CTV-0.079
 additive-0.065
 iod-0.064
 Bravo-0.059
Token Gand
Token ID17727
Feature activation+4.79e-02

Pos logit contributions
between+0.007
 Gaw+0.006
 undertaking+0.006
pty+0.005
abus+0.005
Neg logit contributions
united-0.008
CTV-0.007
 additive-0.006
 iod-0.006
 Bravo-0.005
Tokenalf
Token ID1604
Feature activation+1.99e-01

Pos logit contributions
between+0.033
 Gaw+0.030
 undertaking+0.027
pty+0.026
abus+0.025
Neg logit contributions
united-0.047
CTV-0.043
 additive-0.037
 iod-0.036
SHARE-0.033
Token faces
Token ID6698
Feature activation+3.89e-01

Pos logit contributions
between+0.148
 Gaw+0.136
 undertaking+0.123
pty+0.117
abus+0.115
Neg logit contributions
united-0.185
CTV-0.170
 additive-0.143
 iod-0.141
SHARE-0.129
Token the
Token ID262
Feature activation+3.06e-02

Pos logit contributions
between+0.316
 Gaw+0.292
 undertaking+0.267
pty+0.256
abus+0.252
Neg logit contributions
united-0.334
CTV-0.305
 additive-0.252
 iod-0.248
 Bravo-0.223
Token Bal
Token ID8528
Feature activation+2.57e-01

Pos logit contributions
between+0.022
 Gaw+0.020
 undertaking+0.018
pty+0.017
abus+0.017
Neg logit contributions
united-0.030
CTV-0.027
 additive-0.023
 iod-0.023
 Bravo-0.021
Tokenrog
Token ID3828
Feature activation+6.57e-02

Pos logit contributions
between+0.160
 Gaw+0.147
 undertaking+0.131
pty+0.122
abus+0.118
Neg logit contributions
united-0.269
CTV-0.249
 additive-0.213
 iod-0.210
 Bravo-0.194
Token,
Token ID11
Feature activation-2.50e-02

Pos logit contributions
between+0.053
 Gaw+0.049
 undertaking+0.044
pty+0.042
abus+0.042
Neg logit contributions
united-0.057
CTV-0.052
 additive-0.043
 iod-0.043
 Bravo-0.038
Token and
Token ID290
Feature activation-4.24e-02

Pos logit contributions
united+0.026
CTV+0.024
 additive+0.021
 iod+0.021
 Bravo+0.019
Neg logit contributions
between-0.015
 Gaw-0.014
 undertaking-0.012
pty-0.012
abus-0.012
Token come
Token ID1282
Feature activation-9.05e-02

Pos logit contributions
between+0.050
 Gaw+0.046
 undertaking+0.042
pty+0.040
abus+0.040
Neg logit contributions
united-0.054
CTV-0.049
 additive-0.040
 iod-0.040
SHARE-0.036
Token.
Token ID13
Feature activation+2.61e-02

Pos logit contributions
united+0.076
CTV+0.069
 additive+0.057
 iod+0.056
SHARE+0.050
Neg logit contributions
between-0.075
 Gaw-0.070
 undertaking-0.064
pty-0.062
abus-0.061
Token She
Token ID1375
Feature activation-1.25e-01

Pos logit contributions
between+0.020
 Gaw+0.019
 undertaking+0.017
pty+0.016
abus+0.016
Neg logit contributions
united-0.023
CTV-0.021
 additive-0.018
 iod-0.017
SHARE-0.016
Token finds
Token ID7228
Feature activation+3.35e-01

Pos logit contributions
united+0.116
CTV+0.107
 additive+0.090
 iod+0.088
SHARE+0.080
Neg logit contributions
between-0.094
 Gaw-0.086
 undertaking-0.078
pty-0.074
abus-0.073
Token a
Token ID257
Feature activation+4.80e-02

Pos logit contributions
between+0.330
 Gaw+0.310
 undertaking+0.288
pty+0.279
abus+0.276
Neg logit contributions
united-0.230
CTV-0.205
 additive-0.159
 iod-0.156
SHARE-0.135
Token sword
Token ID8429
Feature activation+3.96e-01

Pos logit contributions
between+0.039
 Gaw+0.037
 undertaking+0.034
pty+0.032
abus+0.032
Neg logit contributions
united-0.041
CTV-0.037
 additive-0.031
 iod-0.030
SHARE-0.027
Token,
Token ID11
Feature activation-2.27e-02

Pos logit contributions
between+0.307
 Gaw+0.285
 undertaking+0.258
pty+0.247
abus+0.243
Neg logit contributions
united-0.355
CTV-0.325
 additive-0.271
 iod-0.267
SHARE-0.241
Token hops
Token ID29438
Feature activation+4.53e-03

Pos logit contributions
united+0.021
CTV+0.020
 additive+0.017
 iod+0.016
SHARE+0.015
Neg logit contributions
between-0.016
 Gaw-0.015
 undertaking-0.014
pty-0.013
abus-0.013
Token on
Token ID319
Feature activation-1.75e-01

Pos logit contributions
between+0.004
 Gaw+0.004
 undertaking+0.004
pty+0.004
abus+0.004
Neg logit contributions
united-0.003
CTV-0.003
 additive-0.002
 iod-0.002
SHARE-0.002
Token her
Token ID607
Feature activation-3.31e-01

Pos logit contributions
united+0.161
CTV+0.148
 additive+0.125
 iod+0.123
 Bravo+0.112
Neg logit contributions
between-0.130
 Gaw-0.119
 undertaking-0.108
pty-0.103
abus-0.101
Token dragon
Token ID10441
Feature activation+1.81e-01

Pos logit contributions
united+0.328
CTV+0.304
 additive+0.259
 iod+0.255
SHARE+0.234
Neg logit contributions
between-0.224
 Gaw-0.205
 undertaking-0.183
pty-0.174
abus-0.170
Token gamble
Token ID32385
Feature activation-8.77e-02

Pos logit contributions
between+0.030
 Gaw+0.027
 undertaking+0.025
pty+0.024
abus+0.023
Neg logit contributions
united-0.039
CTV-0.035
 additive-0.030
 iod-0.030
SHARE-0.027
Token'
Token ID6
Feature activation+1.14e-01

Pos logit contributions
united+0.082
CTV+0.075
 additive+0.063
 iod+0.062
SHARE+0.057
Neg logit contributions
between-0.065
 Gaw-0.060
 undertaking-0.054
pty-0.051
devices-0.050
Token
Token ID198
Feature activation+4.42e-02

Pos logit contributions
between+0.087
 Gaw+0.081
 undertaking+0.073
pty+0.070
abus+0.069
Neg logit contributions
united-0.103
CTV-0.095
 additive-0.079
 iod-0.078
SHARE-0.071
Token
Token ID198
Feature activation+4.71e-02

Pos logit contributions
between+0.033
 Gaw+0.031
 undertaking+0.028
pty+0.027
abus+0.027
Neg logit contributions
united-0.040
CTV-0.037
 additive-0.031
 iod-0.030
SHARE-0.028
TokenWhile
Token ID3633
Feature activation+2.38e-01

Pos logit contributions
between+0.032
 Gaw+0.030
 undertaking+0.027
pty+0.025
abus+0.025
Neg logit contributions
united-0.047
CTV-0.043
 additive-0.035
 iod-0.035
SHARE-0.034
Token Lord
Token ID4453
Feature activation+4.53e-01

Pos logit contributions
between+0.158
 Gaw+0.142
 undertaking+0.124
pty+0.122
abus+0.120
Neg logit contributions
united-0.240
CTV-0.221
 additive-0.191
 iod-0.188
 Bravo-0.173
Token Hes
Token ID44773
Feature activation-1.46e-01

Pos logit contributions
between+0.337
 Gaw+0.308
 undertaking+0.279
pty+0.266
abus+0.261
Neg logit contributions
united-0.422
CTV-0.387
 additive-0.327
 iod-0.321
 Bravo-0.293
Tokenelt
Token ID2120
Feature activation-2.62e-02

Pos logit contributions
united+0.141
CTV+0.132
 additive+0.111
 iod+0.109
SHARE+0.101
Neg logit contributions
between-0.103
 Gaw-0.093
 undertaking-0.084
pty-0.080
abus-0.078
Tokenine
Token ID500
Feature activation+3.51e-02

Pos logit contributions
united+0.028
CTV+0.026
 additive+0.023
 iod+0.023
SHARE+0.021
Neg logit contributions
between-0.015
 Gaw-0.014
 undertaking-0.012
pty-0.011
abus-0.011
Token,
Token ID11
Feature activation+4.26e-02

Pos logit contributions
between+0.025
 Gaw+0.023
 undertaking+0.021
pty+0.020
abus+0.019
Neg logit contributions
united-0.034
CTV-0.031
 additive-0.026
 iod-0.026
SHARE-0.024
Token a
Token ID257
Feature activation+5.65e-02

Pos logit contributions
between+0.028
 Gaw+0.025
 undertaking+0.022
pty+0.021
abus+0.021
Neg logit contributions
united-0.043
CTV-0.040
 additive-0.035
 iod-0.034
 Bravo-0.032
Tokenache
Token ID4891
Feature activation+1.43e-01

Pos logit contributions
between+0.103
 Gaw+0.095
 undertaking+0.085
pty+0.080
devices+0.079
Neg logit contributions
united-0.148
CTV-0.136
 additive-0.115
 iod-0.114
SHARE-0.104
Token and
Token ID290
Feature activation-1.40e-02

Pos logit contributions
between+0.103
 Gaw+0.095
 undertaking+0.086
pty+0.081
abus+0.080
Neg logit contributions
united-0.136
CTV-0.125
 additive-0.106
 iod-0.104
SHARE-0.095
Token a
Token ID257
Feature activation+7.84e-02

Pos logit contributions
united+0.013
CTV+0.012
 additive+0.010
 iod+0.010
 Bravo+0.009
Neg logit contributions
between-0.011
 Gaw-0.010
 undertaking-0.009
pty-0.008
abus-0.008
Token bit
Token ID1643
Feature activation-1.11e-01

Pos logit contributions
between+0.062
 Gaw+0.057
 undertaking+0.052
pty+0.050
abus+0.049
Neg logit contributions
united-0.069
CTV-0.063
 additive-0.052
 iod-0.052
SHARE-0.047
Token of
Token ID286
Feature activation+1.08e-02

Pos logit contributions
united+0.105
CTV+0.097
 additive+0.082
 iod+0.081
SHARE+0.073
Neg logit contributions
between-0.080
 Gaw-0.074
 undertaking-0.066
pty-0.063
abus-0.062
Token Paul
Token ID3362
Feature activation+4.84e-01

Pos logit contributions
between+0.008
 Gaw+0.007
 undertaking+0.006
pty+0.006
abus+0.006
Neg logit contributions
united-0.010
CTV-0.009
 additive-0.008
 iod-0.008
 Bravo-0.007
Token Newman
Token ID27698
Feature activation+5.36e-03

Pos logit contributions
between+0.356
 Gaw+0.325
 undertaking+0.297
pty+0.281
devices+0.278
Neg logit contributions
united-0.454
CTV-0.416
 additive-0.351
 iod-0.344
 Bravo-0.318
Token about
Token ID546
Feature activation-7.18e-03

Pos logit contributions
between+0.004
 Gaw+0.004
 undertaking+0.004
pty+0.003
abus+0.003
Neg logit contributions
united-0.005
CTV-0.004
 additive-0.004
 iod-0.004
 Bravo-0.003
Token him
Token ID683
Feature activation-1.87e-01

Pos logit contributions
united+0.005
CTV+0.005
 additive+0.004
 iod+0.004
SHARE+0.003
Neg logit contributions
between-0.007
 Gaw-0.006
 undertaking-0.006
pty-0.006
abus-0.006
Token'.
Token ID4458
Feature activation+3.00e-01

Pos logit contributions
united+0.185
CTV+0.170
 additive+0.145
 iod+0.143
SHARE+0.131
Neg logit contributions
between-0.129
 Gaw-0.118
 undertaking-0.105
pty-0.100
abus-0.098
Token Photograph
Token ID18903
Feature activation+2.17e-01

Pos logit contributions
between+0.171
 Gaw+0.153
 undertaking+0.134
pty+0.125
abus+0.122
Neg logit contributions
united-0.331
CTV-0.308
 additive-0.266
 iod-0.263
SHARE-0.245
Tokenists
Token ID1023
Feature activation-6.48e-03

Pos logit contributions
between+0.087
 Gaw+0.079
 undertaking+0.069
pty+0.064
abus+0.063
Neg logit contributions
united-0.161
CTV-0.149
 additive-0.129
 iod-0.128
SHARE-0.118
Token have
Token ID423
Feature activation-1.59e-02

Pos logit contributions
united+0.006
CTV+0.005
 additive+0.004
 iod+0.004
SHARE+0.004
Neg logit contributions
between-0.005
 Gaw-0.005
 undertaking-0.004
pty-0.004
abus-0.004
Token been
Token ID587
Feature activation-3.52e-02

Pos logit contributions
united+0.015
CTV+0.013
 additive+0.011
 iod+0.011
SHARE+0.010
Neg logit contributions
between-0.012
 Gaw-0.011
 undertaking-0.010
pty-0.009
abus-0.009
Token present
Token ID1944
Feature activation-2.44e-02

Pos logit contributions
united+0.032
CTV+0.030
 additive+0.025
 iod+0.025
SHARE+0.022
Neg logit contributions
between-0.026
 Gaw-0.024
 undertaking-0.022
pty-0.021
abus-0.021
Token in
Token ID287
Feature activation+1.68e-02

Pos logit contributions
united+0.022
CTV+0.020
 additive+0.017
 iod+0.016
SHARE+0.015
Neg logit contributions
between-0.019
 Gaw-0.018
 undertaking-0.016
pty-0.015
abus-0.015
Token Greece
Token ID10315
Feature activation+4.86e-01

Pos logit contributions
between+0.009
 Gaw+0.008
 undertaking+0.007
abus+0.006
pty+0.006
Neg logit contributions
united-0.019
CTV-0.018
 additive-0.015
 iod-0.015
 Bravo-0.014
Token from
Token ID422
Feature activation-3.42e-02

Pos logit contributions
between+0.353
 Gaw+0.326
 undertaking+0.292
pty+0.279
abus+0.274
Neg logit contributions
united-0.459
CTV-0.421
 additive-0.356
 iod-0.350
SHARE-0.319
Token the
Token ID262
Feature activation-3.21e-02

Pos logit contributions
united+0.032
CTV+0.030
 additive+0.025
 iod+0.025
 Bravo+0.023
Neg logit contributions
between-0.024
 Gaw-0.022
 undertaking-0.020
pty-0.019
abus-0.019
Token 1900
Token ID21489
Feature activation+1.83e-01

Pos logit contributions
united+0.034
CTV+0.032
 additive+0.027
 iod+0.027
 Bravo+0.025
Neg logit contributions
between-0.019
 Gaw-0.018
 undertaking-0.015
pty-0.015
abus-0.014
Token
Token ID447
Feature activation+2.18e-02

Pos logit contributions
between+0.128
 Gaw+0.118
 undertaking+0.105
pty+0.100
abus+0.098
Neg logit contributions
united-0.178
CTV-0.164
 additive-0.139
 iod-0.137
SHARE-0.125
Token
Token ID247
Feature activation+4.98e-02

Pos logit contributions
between+0.018
 Gaw+0.017
 undertaking+0.015
pty+0.015
abus+0.014
Neg logit contributions
united-0.018
CTV-0.017
 additive-0.014
 iod-0.013
SHARE-0.012
Token communities
Token ID5348
Feature activation-1.70e-01

Pos logit contributions
united+0.044
CTV+0.040
 additive+0.034
 iod+0.033
SHARE+0.030
Neg logit contributions
between-0.034
 Gaw-0.032
 undertaking-0.029
pty-0.027
abus-0.027
Token that
Token ID326
Feature activation+1.08e-02

Pos logit contributions
united+0.155
CTV+0.142
 additive+0.119
 iod+0.117
SHARE+0.106
Neg logit contributions
between-0.130
 Gaw-0.121
 undertaking-0.108
pty-0.104
abus-0.103
Token bear
Token ID6842
Feature activation+1.83e-01

Pos logit contributions
between+0.009
 Gaw+0.008
 undertaking+0.007
pty+0.007
abus+0.007
Neg logit contributions
united-0.009
CTV-0.009
 additive-0.007
 iod-0.007
SHARE-0.006
Token the
Token ID262
Feature activation+1.77e-02

Pos logit contributions
between+0.135
 Gaw+0.124
 undertaking+0.112
pty+0.107
abus+0.105
Neg logit contributions
united-0.171
CTV-0.157
 additive-0.133
 iod-0.131
SHARE-0.119
Token extraction
Token ID22236
Feature activation-8.50e-02

Pos logit contributions
between+0.012
 Gaw+0.011
 undertaking+0.009
pty+0.009
abus+0.009
Neg logit contributions
united-0.018
CTV-0.016
 additive-0.014
 iod-0.014
SHARE-0.013
Token costs
Token ID3484
Feature activation+1.92e-01

Pos logit contributions
united+0.076
CTV+0.070
 additive+0.059
 iod+0.058
SHARE+0.052
Neg logit contributions
between-0.065
 Gaw-0.060
 undertaking-0.054
pty-0.052
abus-0.051
Token.
Token ID13
Feature activation+6.44e-02

Pos logit contributions
between+0.144
 Gaw+0.133
 undertaking+0.120
pty+0.115
abus+0.113
Neg logit contributions
united-0.177
CTV-0.163
 additive-0.137
 iod-0.135
SHARE-0.122
Token
Token ID198
Feature activation+2.49e-02

Pos logit contributions
between+0.050
 Gaw+0.046
 undertaking+0.042
pty+0.040
abus+0.040
Neg logit contributions
united-0.057
CTV-0.053
 additive-0.044
 iod-0.043
 Bravo-0.039
Token
Token ID198
Feature activation+2.59e-02

Pos logit contributions
between+0.019
 Gaw+0.017
 undertaking+0.016
pty+0.015
abus+0.015
Neg logit contributions
united-0.023
CTV-0.021
 additive-0.018
 iod-0.017
SHARE-0.016
TokenL
Token ID43
Feature activation-8.28e-02

Pos logit contributions
between+0.020
 Gaw+0.019
 undertaking+0.017
pty+0.016
abus+0.016
Neg logit contributions
united-0.023
CTV-0.021
 additive-0.017
 iod-0.017
SHARE-0.016
TokenNG
Token ID10503
Feature activation+1.53e-01

Pos logit contributions
united+0.091
CTV+0.086
 additive+0.074
 iod+0.073
SHARE+0.068
Neg logit contributions
between-0.047
 Gaw-0.043
 undertaking-0.037
pty-0.034
devices-0.033
Token lan
Token ID26992
Feature activation+4.73e-03

Pos logit contributions
between+0.004
 Gaw+0.003
 undertaking+0.003
pty+0.003
abus+0.003
Neg logit contributions
united-0.004
CTV-0.004
 additive-0.003
 iod-0.003
SHARE-0.003
Tokenak
Token ID461
Feature activation+2.29e-01

Pos logit contributions
between+0.003
 Gaw+0.003
 undertaking+0.003
pty+0.003
abus+0.003
Neg logit contributions
united-0.004
CTV-0.004
 additive-0.003
 iod-0.003
SHARE-0.003
Tokenila
Token ID10102
Feature activation+6.74e-02

Pos logit contributions
between+0.164
 Gaw+0.151
 undertaking+0.136
pty+0.128
abus+0.126
Neg logit contributions
united-0.220
CTV-0.202
 additive-0.170
 iod-0.169
SHARE-0.153
Token i
Token ID1312
Feature activation+1.40e-01

Pos logit contributions
between+0.053
 Gaw+0.049
 undertaking+0.045
pty+0.043
abus+0.042
Neg logit contributions
united-0.060
CTV-0.054
 additive-0.045
 iod-0.045
SHARE-0.040
Tokenā
Token ID10235
Feature activation+5.92e-01

Pos logit contributions
between+0.113
 Gaw+0.105
 undertaking+0.096
pty+0.092
abus+0.090
Neg logit contributions
united-0.120
CTV-0.109
 additive-0.090
 iod-0.089
SHARE-0.080
Token Kal
Token ID12612
Feature activation+3.51e-02

Pos logit contributions
between+0.471
 Gaw+0.437
 undertaking+0.397
pty+0.379
abus+0.374
Neg logit contributions
united-0.519
CTV-0.474
 additive-0.394
 iod-0.388
SHARE-0.350
Tokenan
Token ID272
Feature activation+3.02e-01

Pos logit contributions
between+0.021
 Gaw+0.019
 undertaking+0.017
pty+0.016
abus+0.016
Neg logit contributions
united-0.037
CTV-0.035
 additive-0.030
 iod-0.029
SHARE-0.027
Tokenial
Token ID498
Feature activation+1.55e-01

Pos logit contributions
between+0.202
 Gaw+0.184
 undertaking+0.164
pty+0.155
abus+0.152
Neg logit contributions
united-0.303
CTV-0.280
 additive-0.239
 iod-0.236
SHARE-0.217
Tokeni
Token ID72
Feature activation+2.34e-01

Pos logit contributions
between+0.105
 Gaw+0.096
 undertaking+0.086
pty+0.081
abus+0.079
Neg logit contributions
united-0.154
CTV-0.141
 additive-0.120
 iod-0.119
SHARE-0.109
Token
Token ID134
Feature activation+3.04e-01

Pos logit contributions
between+0.188
 Gaw+0.174
 undertaking+0.159
pty+0.152
abus+0.149
Neg logit contributions
united-0.204
CTV-0.186
 additive-0.154
 iod-0.152
SHARE-0.137
Token
Token ID119
Feature activation-3.60e-02

Pos logit contributions
between+0.290
 Gaw+0.273
 undertaking+0.253
pty+0.244
abus+0.240
Neg logit contributions
united-0.217
CTV-0.194
 additive-0.153
 iod-0.150
SHARE-0.130
Token which
Token ID543
Feature activation+3.09e-01

Pos logit contributions
united+0.078
CTV+0.073
 additive+0.063
 iod+0.061
 Bravo+0.057
Neg logit contributions
between-0.056
 Gaw-0.051
 undertaking-0.046
pty-0.044
abus-0.044
Token you
Token ID345
Feature activation+1.16e-01

Pos logit contributions
between+0.226
 Gaw+0.208
 undertaking+0.188
pty+0.179
abus+0.176
Neg logit contributions
united-0.290
CTV-0.267
 additive-0.226
 iod-0.222
 Bravo-0.203
Token can
Token ID460
Feature activation+4.53e-02

Pos logit contributions
between+0.095
 Gaw+0.089
 undertaking+0.081
pty+0.078
abus+0.076
Neg logit contributions
united-0.098
CTV-0.089
 additive-0.074
 iod-0.073
SHARE-0.065
Token't
Token ID470
Feature activation-2.05e-02

Pos logit contributions
between+0.036
 Gaw+0.033
 undertaking+0.030
pty+0.029
abus+0.028
Neg logit contributions
united-0.040
CTV-0.037
 additive-0.031
 iod-0.030
 Bravo-0.027
Token really
Token ID1107
Feature activation+4.06e-02

Pos logit contributions
united+0.017
CTV+0.016
 additive+0.013
 iod+0.013
SHARE+0.012
Neg logit contributions
between-0.017
 Gaw-0.016
 undertaking-0.014
pty-0.014
abus-0.014
Token pick
Token ID2298
Feature activation+1.97e-01

Pos logit contributions
between+0.032
 Gaw+0.029
 undertaking+0.027
pty+0.025
abus+0.025
Neg logit contributions
united-0.036
CTV-0.033
 additive-0.028
 iod-0.027
SHARE-0.024
Token out
Token ID503
Feature activation-4.00e-02

Pos logit contributions
between+0.205
 Gaw+0.194
 undertaking+0.181
pty+0.175
abus+0.173
Neg logit contributions
united-0.124
CTV-0.109
 additive-0.082
 iod-0.080
SHARE-0.068
Token with
Token ID351
Feature activation+2.38e-01

Pos logit contributions
united+0.036
CTV+0.033
 additive+0.027
 iod+0.027
SHARE+0.024
Neg logit contributions
between-0.031
 Gaw-0.029
 undertaking-0.026
pty-0.025
abus-0.025
Token the
Token ID262
Feature activation+5.42e-02

Pos logit contributions
between+0.174
 Gaw+0.160
 undertaking+0.144
pty+0.137
abus+0.136
Neg logit contributions
united-0.223
CTV-0.206
 additive-0.174
 iod-0.171
 Bravo-0.156
Token camera
Token ID4676
Feature activation+1.93e-01

Pos logit contributions
between+0.042
 Gaw+0.039
 undertaking+0.035
pty+0.034
abus+0.033
Neg logit contributions
united-0.048
CTV-0.044
 additive-0.037
 iod-0.037
SHARE-0.033
Token in
Token ID287
Feature activation+9.26e-02

Pos logit contributions
between+0.155
 Gaw+0.144
 undertaking+0.130
pty+0.125
abus+0.123
Neg logit contributions
united-0.168
CTV-0.153
 additive-0.127
 iod-0.125
SHARE-0.113
Token but
Token ID475
Feature activation+7.88e-02

Pos logit contributions
united+0.118
CTV+0.109
 additive+0.092
 iod+0.091
SHARE+0.083
Neg logit contributions
between-0.091
 Gaw-0.084
 undertaking-0.075
pty-0.072
abus-0.071
Token he
Token ID339
Feature activation+6.94e-02

Pos logit contributions
between+0.055
 Gaw+0.051
 undertaking+0.045
pty+0.044
abus+0.043
Neg logit contributions
united-0.076
CTV-0.070
 additive-0.060
 iod-0.059
 Bravo-0.054
Token might
Token ID1244
Feature activation+6.72e-02

Pos logit contributions
between+0.051
 Gaw+0.047
 undertaking+0.042
pty+0.040
abus+0.039
Neg logit contributions
united-0.065
CTV-0.060
 additive-0.050
 iod-0.050
SHARE-0.045
Token also
Token ID635
Feature activation+1.78e-01

Pos logit contributions
between+0.043
 Gaw+0.039
 undertaking+0.035
pty+0.033
abus+0.032
Neg logit contributions
united-0.069
CTV-0.064
 additive-0.055
 iod-0.054
SHARE-0.050
Token have
Token ID423
Feature activation+1.39e-02

Pos logit contributions
between+0.139
 Gaw+0.128
 undertaking+0.117
pty+0.111
abus+0.109
Neg logit contributions
united-0.160
CTV-0.146
 additive-0.122
 iod-0.120
SHARE-0.109
Token one
Token ID530
Feature activation+1.36e-02

Pos logit contributions
between+0.010
 Gaw+0.009
 undertaking+0.008
pty+0.008
abus+0.008
Neg logit contributions
united-0.013
CTV-0.012
 additive-0.010
 iod-0.010
 Bravo-0.009
Token caveat
Token ID36531
Feature activation+1.30e-01

Pos logit contributions
between+0.010
 Gaw+0.009
 undertaking+0.008
pty+0.008
abus+0.008
Neg logit contributions
united-0.012
CTV-0.011
 additive-0.010
 iod-0.010
SHARE-0.009
Token.
Token ID13
Feature activation+3.29e-02

Pos logit contributions
between+0.110
 Gaw+0.103
 undertaking+0.094
pty+0.090
abus+0.088
Neg logit contributions
united-0.108
CTV-0.098
 additive-0.080
 iod-0.079
SHARE-0.070
Token Yes
Token ID3363
Feature activation-8.84e-02

Pos logit contributions
between+0.025
 Gaw+0.023
 undertaking+0.021
pty+0.020
abus+0.020
Neg logit contributions
united-0.030
CTV-0.027
 additive-0.023
 iod-0.022
 Bravo-0.020
Token,
Token ID11
Feature activation+2.68e-02

Pos logit contributions
united+0.073
CTV+0.066
 additive+0.054
 iod+0.053
SHARE+0.047
Neg logit contributions
between-0.075
 Gaw-0.070
 undertaking-0.064
pty-0.062
abus-0.061
Token his
Token ID465
Feature activation-3.49e-02

Pos logit contributions
between+0.020
 Gaw+0.018
 undertaking+0.016
pty+0.016
abus+0.015
Neg logit contributions
united-0.025
CTV-0.023
 additive-0.020
 iod-0.019
 Bravo-0.017
Token appreciated
Token ID16373
Feature activation+5.22e-02

Pos logit contributions
between+0.085
 Gaw+0.079
 undertaking+0.072
pty+0.068
abus+0.067
Neg logit contributions
united-0.091
CTV-0.083
 additive-0.068
 iod-0.067
SHARE-0.061
Token that
Token ID326
Feature activation+1.48e-01

Pos logit contributions
between+0.037
 Gaw+0.034
 undertaking+0.030
pty+0.029
abus+0.029
Neg logit contributions
united-0.050
CTV-0.046
 additive-0.040
 iod-0.039
 Bravo-0.036
Token they
Token ID484
Feature activation-5.83e-02

Pos logit contributions
between+0.114
 Gaw+0.106
 undertaking+0.095
pty+0.091
abus+0.090
Neg logit contributions
united-0.133
CTV-0.122
 additive-0.103
 iod-0.100
 Bravo-0.091
Token were
Token ID547
Feature activation-1.16e-01

Pos logit contributions
united+0.047
CTV+0.043
 additive+0.035
 iod+0.034
SHARE+0.031
Neg logit contributions
between-0.050
 Gaw-0.047
 undertaking-0.043
pty-0.041
abus-0.040
Token able
Token ID1498
Feature activation-5.37e-02

Pos logit contributions
united+0.112
CTV+0.104
 additive+0.088
 iod+0.087
SHARE+0.079
Neg logit contributions
between-0.082
 Gaw-0.075
 undertaking-0.067
pty-0.064
abus-0.063
Token to
Token ID284
Feature activation+1.10e-02

Pos logit contributions
united+0.051
CTV+0.047
 additive+0.040
 iod+0.039
SHARE+0.036
Neg logit contributions
between-0.039
 Gaw-0.035
 undertaking-0.032
pty-0.030
abus-0.030
Token keep
Token ID1394
Feature activation-1.88e-01

Pos logit contributions
between+0.010
 Gaw+0.009
 undertaking+0.008
pty+0.008
abus+0.008
Neg logit contributions
united-0.009
CTV-0.008
 additive-0.006
 iod-0.006
SHARE-0.006
Token things
Token ID1243
Feature activation+1.87e-01

Pos logit contributions
united+0.174
CTV+0.159
 additive+0.135
 iod+0.132
 Bravo+0.120
Neg logit contributions
between-0.140
 Gaw-0.129
 undertaking-0.116
pty-0.111
abus-0.110
Token fresh
Token ID4713
Feature activation+1.80e-01

Pos logit contributions
between+0.154
 Gaw+0.143
 undertaking+0.131
pty+0.125
abus+0.123
Neg logit contributions
united-0.158
CTV-0.144
 additive-0.119
 iod-0.117
SHARE-0.105
Token with
Token ID351
Feature activation+1.64e-01

Pos logit contributions
between+0.140
 Gaw+0.130
 undertaking+0.118
pty+0.112
abus+0.111
Neg logit contributions
united-0.161
CTV-0.147
 additive-0.123
 iod-0.121
SHARE-0.109
Token The
Token ID383
Feature activation+3.30e-02

Pos logit contributions
between+0.122
 Gaw+0.113
 undertaking+0.101
pty+0.097
abus+0.095
Neg logit contributions
united-0.152
CTV-0.140
 additive-0.118
 iod-0.116
 Bravo-0.105
Token the
Token ID262
Feature activation-4.97e-02

Pos logit contributions
united+0.017
CTV+0.015
 additive+0.013
 iod+0.013
 Bravo+0.012
Neg logit contributions
between-0.013
 Gaw-0.012
 undertaking-0.011
pty-0.010
abus-0.010
Token broader
Token ID11622
Feature activation+5.55e-02

Pos logit contributions
united+0.047
CTV+0.043
 additive+0.037
 iod+0.036
 Bravo+0.033
Neg logit contributions
between-0.036
 Gaw-0.033
 undertaking-0.029
pty-0.028
abus-0.028
Token context
Token ID4732
Feature activation-8.40e-02

Pos logit contributions
between+0.042
 Gaw+0.039
 undertaking+0.035
pty+0.034
abus+0.033
Neg logit contributions
united-0.050
CTV-0.046
 additive-0.039
 iod-0.038
SHARE-0.034
Token of
Token ID286
Feature activation-3.77e-02

Pos logit contributions
united+0.078
CTV+0.072
 additive+0.061
 iod+0.060
SHARE+0.054
Neg logit contributions
between-0.062
 Gaw-0.057
 undertaking-0.052
pty-0.049
abus-0.048
Token a
Token ID257
Feature activation+3.19e-02

Pos logit contributions
united+0.034
CTV+0.031
 additive+0.026
 iod+0.026
 Bravo+0.023
Neg logit contributions
between-0.029
 Gaw-0.027
 undertaking-0.024
pty-0.023
abus-0.023
Token highly
Token ID4047
Feature activation-6.18e-02

Pos logit contributions
between+0.024
 Gaw+0.023
 undertaking+0.020
pty+0.019
abus+0.019
Neg logit contributions
united-0.029
CTV-0.027
 additive-0.022
 iod-0.022
SHARE-0.020
Token competitive
Token ID7606
Feature activation+4.45e-02

Pos logit contributions
united+0.054
CTV+0.049
 additive+0.040
 iod+0.040
SHARE+0.036
Neg logit contributions
between-0.050
 Gaw-0.046
 undertaking-0.042
pty-0.040
abus-0.040
Token industry
Token ID2831
Feature activation-1.59e-01

Pos logit contributions
between+0.035
 Gaw+0.032
 undertaking+0.029
pty+0.028
abus+0.027
Neg logit contributions
united-0.040
CTV-0.036
 additive-0.030
 iod-0.030
SHARE-0.027
Token,
Token ID11
Feature activation-4.26e-02

Pos logit contributions
united+0.132
CTV+0.120
 additive+0.098
 iod+0.096
SHARE+0.086
Neg logit contributions
between-0.134
 Gaw-0.125
 undertaking-0.114
pty-0.110
abus-0.108
Token many
Token ID867
Feature activation+1.25e-01

Pos logit contributions
united+0.040
CTV+0.037
 additive+0.031
 iod+0.031
 Bravo+0.028
Neg logit contributions
between-0.031
 Gaw-0.028
 undertaking-0.026
pty-0.025
abus-0.024
Token of
Token ID286
Feature activation-2.18e-02

Pos logit contributions
between+0.094
 Gaw+0.087
 undertaking+0.078
pty+0.075
abus+0.073
Neg logit contributions
united-0.114
CTV-0.105
 additive-0.089
 iod-0.087
SHARE-0.079
Token below
Token ID2174
Feature activation+2.59e-02

Pos logit contributions
united+0.082
CTV+0.073
 additive+0.057
 iod+0.056
SHARE+0.048
Neg logit contributions
between-0.118
 Gaw-0.111
 undertaking-0.103
pty-0.099
abus-0.098
Token to
Token ID284
Feature activation+1.66e-01

Pos logit contributions
between+0.019
 Gaw+0.017
 undertaking+0.015
pty+0.015
abus+0.014
Neg logit contributions
united-0.025
CTV-0.023
 additive-0.019
 iod-0.019
SHARE-0.017
Token become
Token ID1716
Feature activation-5.34e-03

Pos logit contributions
between+0.137
 Gaw+0.128
 undertaking+0.117
pty+0.112
abus+0.110
Neg logit contributions
united-0.141
CTV-0.128
 additive-0.106
 iod-0.104
SHARE-0.093
Token an
Token ID281
Feature activation+7.43e-02

Pos logit contributions
united+0.006
CTV+0.005
 additive+0.004
 iod+0.004
SHARE+0.004
Neg logit contributions
between-0.003
 Gaw-0.003
 undertaking-0.003
pty-0.003
render-0.002
Token In
Token ID554
Feature activation+1.21e-02

Pos logit contributions
between+0.057
 Gaw+0.053
 undertaking+0.048
pty+0.046
abus+0.045
Neg logit contributions
united-0.067
CTV-0.061
 additive-0.051
 iod-0.050
SHARE-0.046
TokenDaily
Token ID28545
Feature activation-1.73e-01

Pos logit contributions
between+0.011
 Gaw+0.011
 undertaking+0.010
pty+0.010
abus+0.009
Neg logit contributions
united-0.009
CTV-0.008
 additive-0.006
 iod-0.006
SHARE-0.005
Token supporter
Token ID15525
Feature activation+2.14e-02

Pos logit contributions
united+0.141
CTV+0.128
 iod+0.104
 additive+0.104
SHARE+0.093
Neg logit contributions
between-0.146
 Gaw-0.136
 undertaking-0.127
pty-0.119
render-0.117
Token.
Token ID13
Feature activation+3.58e-02

Pos logit contributions
between+0.017
 Gaw+0.015
 undertaking+0.014
pty+0.013
abus+0.013
Neg logit contributions
united-0.019
CTV-0.018
 additive-0.015
 iod-0.014
SHARE-0.013
Token Powered
Token ID45090
Feature activation+3.25e-02

Pos logit contributions
between+0.030
 Gaw+0.027
 undertaking+0.025
pty+0.024
abus+0.024
Neg logit contributions
united-0.030
CTV-0.028
 additive-0.022
 iod-0.022
SHARE-0.020
Token by
Token ID416
Feature activation-1.57e-02

Pos logit contributions
between+0.026
 Gaw+0.024
 undertaking+0.023
pty+0.021
abus+0.021
Neg logit contributions
united-0.028
CTV-0.025
 additive-0.021
 iod-0.021
SHARE-0.019
Token Press
Token ID4332
Feature activation-6.08e-02

Pos logit contributions
united+0.012
CTV+0.011
 iod+0.009
 additive+0.008
 Bravo+0.007
Neg logit contributions
between-0.014
 Gaw-0.013
 undertaking-0.012
pty-0.012
devices-0.012
Token
Token ID198
Feature activation+4.02e-02

Pos logit contributions
between+0.046
 Gaw+0.043
 undertaking+0.039
pty+0.037
abus+0.036
Neg logit contributions
united-0.056
CTV-0.052
 additive-0.043
 iod-0.042
SHARE-0.039
Tokenvoid
Token ID19382
Feature activation+2.59e-01

Pos logit contributions
between+0.034
 Gaw+0.032
 undertaking+0.029
pty+0.028
abus+0.027
Neg logit contributions
united-0.033
CTV-0.030
 additive-0.025
 iod-0.024
SHARE-0.022
Token V
Token ID569
Feature activation-1.08e-01

Pos logit contributions
between+0.209
 Gaw+0.195
 undertaking+0.177
pty+0.168
abus+0.166
Neg logit contributions
united-0.224
CTV-0.204
 additive-0.168
 iod-0.166
SHARE-0.150
Tokenort
Token ID419
Feature activation-5.09e-01

Pos logit contributions
united+0.079
CTV+0.071
 additive+0.056
 iod+0.055
SHARE+0.048
Neg logit contributions
between-0.102
 Gaw-0.095
 undertaking-0.088
pty-0.085
abus-0.084
Tokenon
Token ID261
Feature activation-2.06e-01

Pos logit contributions
united+0.384
CTV+0.345
 additive+0.275
 iod+0.270
SHARE+0.238
Neg logit contributions
between-0.468
 Gaw-0.438
 undertaking-0.404
pty-0.389
abus-0.384
TokenSim
Token ID8890
Feature activation-2.68e-01

Pos logit contributions
united+0.148
CTV+0.132
 additive+0.104
 iod+0.102
SHARE+0.088
Neg logit contributions
between-0.197
 Gaw-0.185
 undertaking-0.171
pty-0.165
abus-0.163
Token::
Token ID3712
Feature activation+3.60e-02

Pos logit contributions
united+0.202
CTV+0.182
 additive+0.145
 iod+0.142
SHARE+0.125
Neg logit contributions
between-0.246
 Gaw-0.231
 undertaking-0.213
pty-0.205
abus-0.202
TokenPop
Token ID16979
Feature activation+7.54e-02

Pos logit contributions
between+0.028
 Gaw+0.026
 undertaking+0.024
pty+0.023
abus+0.022
Neg logit contributions
united-0.032
CTV-0.029
 additive-0.024
 iod-0.024
SHARE-0.022
Tokenulate
Token ID5039
Feature activation-1.85e-01

Pos logit contributions
between+0.077
 Gaw+0.072
 undertaking+0.067
pty+0.065
abus+0.064
Neg logit contributions
united-0.049
CTV-0.044
 additive-0.033
 iod-0.033
SHARE-0.028
TokenD
Token ID35
Feature activation-1.33e-01

Pos logit contributions
united+0.153
CTV+0.139
 additive+0.114
 iod+0.112
SHARE+0.100
Neg logit contributions
between-0.156
 Gaw-0.146
 undertaking-0.134
pty-0.128
abus-0.126
Tokenensity
Token ID6377
Feature activation-4.31e-01

Pos logit contributions
united+0.087
CTV+0.077
 additive+0.058
 iod+0.057
SHARE+0.048
Neg logit contributions
between-0.136
 Gaw-0.129
 undertaking-0.120
pty-0.115
abus-0.114
Token He
Token ID679
Feature activation+7.33e-02

Pos logit contributions
between+0.011
 Gaw+0.010
 undertaking+0.009
pty+0.009
abus+0.009
Neg logit contributions
united-0.014
CTV-0.012
 additive-0.010
 iod-0.010
 Bravo-0.009
Token began
Token ID2540
Feature activation-1.35e-01

Pos logit contributions
between+0.062
 Gaw+0.058
 undertaking+0.053
pty+0.051
abus+0.050
Neg logit contributions
united-0.060
CTV-0.055
 additive-0.045
 iod-0.044
SHARE-0.040
Token training
Token ID3047
Feature activation-1.71e-01

Pos logit contributions
united+0.128
CTV+0.118
 additive+0.100
 iod+0.099
SHARE+0.090
Neg logit contributions
between-0.096
 Gaw-0.089
 undertaking-0.078
pty-0.076
abus-0.075
Token the
Token ID262
Feature activation-1.16e-01

Pos logit contributions
united+0.156
CTV+0.143
 additive+0.120
 iod+0.118
 Bravo+0.107
Neg logit contributions
between-0.129
 Gaw-0.119
 undertaking-0.108
pty-0.103
abus-0.102
Token turtles
Token ID36288
Feature activation+2.66e-01

Pos logit contributions
united+0.111
CTV+0.102
 additive+0.087
 iod+0.086
 Bravo+0.078
Neg logit contributions
between-0.083
 Gaw-0.076
 undertaking-0.068
pty-0.065
abus-0.064
Token in
Token ID287
Feature activation-6.43e-02

Pos logit contributions
between+0.206
 Gaw+0.191
 undertaking+0.174
pty+0.165
abus+0.162
Neg logit contributions
united-0.239
CTV-0.219
 additive-0.182
 iod-0.180
SHARE-0.163
Token the
Token ID262
Feature activation-9.51e-02

Pos logit contributions
united+0.059
CTV+0.054
 additive+0.045
 iod+0.044
 Bravo+0.040
Neg logit contributions
between-0.049
 Gaw-0.045
 undertaking-0.041
pty-0.039
abus-0.039
Token art
Token ID1242
Feature activation+2.59e-01

Pos logit contributions
united+0.086
CTV+0.079
 additive+0.066
 iod+0.065
SHARE+0.059
Neg logit contributions
between-0.073
 Gaw-0.068
 undertaking-0.061
pty-0.058
abus-0.058
Token of
Token ID286
Feature activation-6.49e-02

Pos logit contributions
between+0.188
 Gaw+0.173
 undertaking+0.156
pty+0.148
abus+0.145
Neg logit contributions
united-0.245
CTV-0.225
 additive-0.191
 iod-0.187
SHARE-0.171
Token nin
Token ID13462
Feature activation+1.38e-01

Pos logit contributions
united+0.062
CTV+0.057
 additive+0.048
 iod+0.047
SHARE+0.043
Neg logit contributions
between-0.047
 Gaw-0.043
 undertaking-0.039
pty-0.037
abus-0.036
Tokenj
Token ID73
Feature activation-3.88e-02

Pos logit contributions
between+0.114
 Gaw+0.107
 undertaking+0.098
pty+0.093
abus+0.092
Neg logit contributions
united-0.117
CTV-0.106
 additive-0.087
 iod-0.086
 Bravo-0.077
Token One
Token ID1881
Feature activation+7.94e-03

Pos logit contributions
between+0.056
 Gaw+0.052
 undertaking+0.047
pty+0.045
abus+0.045
Neg logit contributions
united-0.058
CTV-0.053
 additive-0.043
 iod-0.043
SHARE-0.038
Token Jill
Token ID22772
Feature activation+1.00e-01

Pos logit contributions
between+0.006
 Gaw+0.005
 undertaking+0.005
pty+0.005
abus+0.005
Neg logit contributions
united-0.007
CTV-0.007
 additive-0.006
 iod-0.006
 Bravo-0.005
Token ste
Token ID2876
Feature activation-4.22e-02

Pos logit contributions
between+0.069
 Gaw+0.064
 undertaking+0.057
pty+0.054
abus+0.053
Neg logit contributions
united-0.098
CTV-0.090
 additive-0.077
 iod-0.076
SHARE-0.069
Tokenin
Token ID259
Feature activation-1.26e-02

Pos logit contributions
united+0.035
CTV+0.031
 additive+0.025
 iod+0.025
SHARE+0.022
Neg logit contributions
between-0.036
 Gaw-0.034
 undertaking-0.031
pty-0.030
abus-0.029
Token supporter
Token ID15525
Feature activation-4.07e-02

Pos logit contributions
united+0.011
CTV+0.010
 additive+0.009
 iod+0.009
SHARE+0.008
Neg logit contributions
between-0.010
 Gaw-0.009
 undertaking-0.008
pty-0.008
abus-0.008
Token told
Token ID1297
Feature activation-1.76e-02

Pos logit contributions
united+0.037
CTV+0.034
 additive+0.029
 iod+0.028
SHARE+0.026
Neg logit contributions
between-0.031
 Gaw-0.028
 undertaking-0.026
pty-0.024
abus-0.024
Token us
Token ID514
Feature activation-1.88e-01

Pos logit contributions
united+0.012
CTV+0.010
 additive+0.008
 iod+0.008
SHARE+0.007
Neg logit contributions
between-0.018
 Gaw-0.017
 undertaking-0.016
pty-0.015
abus-0.015
Token three
Token ID1115
Feature activation+4.58e-02

Pos logit contributions
united+0.166
CTV+0.152
 additive+0.126
 iod+0.124
SHARE+0.112
Neg logit contributions
between-0.148
 Gaw-0.137
 undertaking-0.124
pty-0.119
abus-0.117
Token whole
Token ID2187
Feature activation+1.84e-01

Pos logit contributions
between+0.036
 Gaw+0.033
 undertaking+0.030
pty+0.029
abus+0.028
Neg logit contributions
united-0.041
CTV-0.037
 additive-0.031
 iod-0.031
SHARE-0.028
Token buses
Token ID16893
Feature activation+1.77e-01

Pos logit contributions
between+0.144
 Gaw+0.133
 undertaking+0.121
pty+0.116
abus+0.114
Neg logit contributions
united-0.165
CTV-0.151
 additive-0.125
 iod-0.124
SHARE-0.112
Token of
Token ID286
Feature activation+4.84e-02

Pos logit contributions
between+0.147
 Gaw+0.137
 undertaking+0.126
pty+0.119
abus+0.118
Neg logit contributions
united-0.149
CTV-0.137
 additive-0.112
 iod-0.110
SHARE-0.099
Token one
Token ID530
Feature activation+1.16e-02

Pos logit contributions
united+0.007
CTV+0.007
 additive+0.006
 iod+0.006
SHARE+0.005
Neg logit contributions
between-0.006
 Gaw-0.005
 undertaking-0.005
pty-0.004
abus-0.004
Token of
Token ID286
Feature activation-2.30e-03

Pos logit contributions
between+0.009
 Gaw+0.008
 undertaking+0.007
pty+0.007
abus+0.007
Neg logit contributions
united-0.011
CTV-0.010
 additive-0.008
 iod-0.008
 Bravo-0.008
Token my
Token ID616
Feature activation+1.85e-02

Pos logit contributions
united+0.002
CTV+0.002
 additive+0.002
 iod+0.002
 Bravo+0.001
Neg logit contributions
between-0.002
 Gaw-0.002
 undertaking-0.001
pty-0.001
abus-0.001
Token favorite
Token ID4004
Feature activation-5.56e-02

Pos logit contributions
between+0.015
 Gaw+0.014
 undertaking+0.013
pty+0.012
abus+0.012
Neg logit contributions
united-0.016
CTV-0.015
 additive-0.012
 iod-0.012
SHARE-0.011
Token fl
Token ID781
Feature activation-1.03e-01

Pos logit contributions
united+0.049
CTV+0.045
 additive+0.038
 iod+0.037
SHARE+0.033
Neg logit contributions
between-0.044
 Gaw-0.040
 undertaking-0.037
pty-0.035
abus-0.035
Tokenours
Token ID4662
Feature activation-4.38e-01

Pos logit contributions
united+0.085
CTV+0.077
 additive+0.063
 iod+0.061
SHARE+0.055
Neg logit contributions
between-0.086
 Gaw-0.081
 undertaking-0.075
pty-0.071
abus-0.070
Token to
Token ID284
Feature activation+3.74e-02

Pos logit contributions
united+0.388
CTV+0.355
 additive+0.298
 iod+0.293
SHARE+0.263
Neg logit contributions
between-0.343
 Gaw-0.318
 undertaking-0.288
pty-0.277
abus-0.272
Token work
Token ID670
Feature activation+2.51e-02

Pos logit contributions
between+0.035
 Gaw+0.033
 undertaking+0.031
pty+0.029
abus+0.029
Neg logit contributions
united-0.027
CTV-0.024
 additive-0.019
 iod-0.019
SHARE-0.017
Token with
Token ID351
Feature activation+1.17e-01

Pos logit contributions
between+0.016
 Gaw+0.015
 undertaking+0.013
pty+0.013
abus+0.012
Neg logit contributions
united-0.025
CTV-0.024
 additive-0.020
 iod-0.020
SHARE-0.018
Token,
Token ID11
Feature activation-1.74e-02

Pos logit contributions
between+0.089
 Gaw+0.083
 undertaking+0.075
pty+0.071
abus+0.070
Neg logit contributions
united-0.106
CTV-0.097
 additive-0.081
 iod-0.080
SHARE-0.072
Token although
Token ID3584
Feature activation+1.44e-01

Pos logit contributions
united+0.017
CTV+0.015
 additive+0.013
 iod+0.013
SHARE+0.012
Neg logit contributions
between-0.012
 Gaw-0.011
 undertaking-0.010
pty-0.010
abus-0.010
TokenString
Token ID10100
Feature activation+4.76e-02

Pos logit contributions
united+0.084
CTV+0.077
 additive+0.064
 iod+0.062
SHARE+0.057
Neg logit contributions
between-0.074
 Gaw-0.069
 undertaking-0.062
pty-0.059
abus-0.058
TokenAl
Token ID2348
Feature activation-8.54e-02

Pos logit contributions
between+0.034
 Gaw+0.032
 undertaking+0.029
pty+0.027
abus+0.027
Neg logit contributions
united-0.045
CTV-0.042
 additive-0.035
 iod-0.034
SHARE-0.032
Tokenignment
Token ID16747
Feature activation-3.75e-01

Pos logit contributions
united+0.048
CTV+0.041
 additive+0.029
 iod+0.028
SHARE+0.023
Neg logit contributions
between-0.095
 Gaw-0.091
 undertaking-0.085
pty-0.082
abus-0.081
Token]
Token ID60
Feature activation-1.38e-01

Pos logit contributions
united+0.276
CTV+0.248
 additive+0.196
 iod+0.192
SHARE+0.169
Neg logit contributions
between-0.352
 Gaw-0.331
 undertaking-0.306
pty-0.294
abus-0.291
Token::
Token ID3712
Feature activation-8.48e-02

Pos logit contributions
united+0.102
CTV+0.092
 additive+0.073
 iod+0.071
SHARE+0.063
Neg logit contributions
between-0.128
 Gaw-0.120
 undertaking-0.111
pty-0.107
abus-0.105
TokenCenter
Token ID23656
Feature activation-4.64e-01

Pos logit contributions
united+0.062
CTV+0.056
 additive+0.044
 iod+0.043
SHARE+0.038
Neg logit contributions
between-0.079
 Gaw-0.075
 undertaking-0.070
pty-0.067
abus-0.066
Token $
Token ID720
Feature activation-5.75e-02

Pos logit contributions
united+0.369
CTV+0.334
 additive+0.271
 iod+0.266
SHARE+0.236
Neg logit contributions
between-0.406
 Gaw-0.380
 undertaking-0.349
pty-0.335
abus-0.330
Tokens
Token ID82
Feature activation+9.95e-03

Pos logit contributions
united+0.056
CTV+0.052
 additive+0.044
 iod+0.043
SHARE+0.040
Neg logit contributions
between-0.040
 Gaw-0.037
 undertaking-0.033
pty-0.031
abus-0.031
TokenFormat
Token ID26227
Feature activation-1.81e-01

Pos logit contributions
between+0.008
 Gaw+0.008
 undertaking+0.007
pty+0.007
abus+0.007
Neg logit contributions
united-0.008
CTV-0.008
 additive-0.006
 iod-0.006
SHARE-0.006
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
united+0.164
CTV+0.151
 additive+0.125
 iod+0.123
SHARE+0.113
Neg logit contributions
between-0.138
 Gaw-0.129
 undertaking-0.117
pty-0.111
abus-0.109
TokenLine
Token ID13949
Feature activation+4.56e-02

Pos logit contributions
united+0.089
CTV+0.081
 additive+0.066
 iod+0.065
SHARE+0.059
Neg logit contributions
between-0.089
 Gaw-0.083
 undertaking-0.077
pty-0.073
abus-0.072
Token from
Token ID422
Feature activation+2.48e-02

Pos logit contributions
between+0.160
 Gaw+0.149
 undertaking+0.134
pty+0.128
abus+0.126
Neg logit contributions
united-0.193
CTV-0.177
 additive-0.148
 iod-0.146
SHARE-0.133
Token Kaiser
Token ID32670
Feature activation-1.02e-01

Pos logit contributions
between+0.019
 Gaw+0.017
 undertaking+0.016
pty+0.015
abus+0.015
Neg logit contributions
united-0.023
CTV-0.021
 additive-0.017
 iod-0.017
SHARE-0.016
Token Family
Token ID7884
Feature activation+3.92e-02

Pos logit contributions
united+0.085
CTV+0.077
 additive+0.063
 iod+0.062
SHARE+0.056
Neg logit contributions
between-0.086
 Gaw-0.080
 undertaking-0.073
pty-0.071
abus-0.070
Token Foundation
Token ID5693
Feature activation-1.47e-01

Pos logit contributions
between+0.042
 Gaw+0.040
 undertaking+0.037
pty+0.036
abus+0.035
Neg logit contributions
united-0.024
CTV-0.021
 additive-0.015
 iod-0.015
SHARE-0.013
Token,
Token ID11
Feature activation+2.65e-02

Pos logit contributions
united+0.133
CTV+0.122
 additive+0.102
 iod+0.101
SHARE+0.091
Neg logit contributions
between-0.112
 Gaw-0.103
 undertaking-0.094
pty-0.089
abus-0.088
Token promoted
Token ID13722
Feature activation-4.55e-01

Pos logit contributions
between+0.019
 Gaw+0.018
 undertaking+0.016
pty+0.015
abus+0.015
Neg logit contributions
united-0.025
CTV-0.023
 additive-0.020
 iod-0.019
SHARE-0.018
Token prominently
Token ID31015
Feature activation+7.21e-03

Pos logit contributions
united+0.384
CTV+0.349
 additive+0.285
 iod+0.282
SHARE+0.253
Neg logit contributions
between-0.378
 Gaw-0.353
 undertaking-0.322
pty-0.308
abus-0.302
Token in
Token ID287
Feature activation-1.59e-02

Pos logit contributions
between+0.006
 Gaw+0.006
 undertaking+0.005
pty+0.005
abus+0.005
Neg logit contributions
united-0.006
CTV-0.005
 additive-0.004
 iod-0.004
SHARE-0.004
Token the
Token ID262
Feature activation-3.14e-02

Pos logit contributions
united+0.015
CTV+0.013
 additive+0.011
 iod+0.011
SHARE+0.010
Neg logit contributions
between-0.012
 Gaw-0.011
 undertaking-0.010
pty-0.009
abus-0.009
Token media
Token ID2056
Feature activation-1.50e-01

Pos logit contributions
united+0.027
CTV+0.025
 additive+0.020
 iod+0.020
SHARE+0.018
Neg logit contributions
between-0.026
 Gaw-0.024
 undertaking-0.022
pty-0.021
abus-0.020
Token,
Token ID11
Feature activation-1.33e-02

Pos logit contributions
united+0.128
CTV+0.117
 additive+0.096
 iod+0.094
SHARE+0.085
Neg logit contributions
between-0.123
 Gaw-0.114
 undertaking-0.105
pty-0.100
abus-0.098
Token June
Token ID2795
Feature activation+5.85e-03

Pos logit contributions
united+0.137
CTV+0.124
 additive+0.100
 iod+0.098
SHARE+0.087
Neg logit contributions
between-0.154
 Gaw-0.143
 undertaking-0.132
pty-0.126
devices-0.125
Token 26
Token ID2608
Feature activation-3.02e-02

Pos logit contributions
between+0.005
 Gaw+0.005
 undertaking+0.004
pty+0.004
abus+0.004
Neg logit contributions
united-0.005
CTV-0.004
 additive-0.003
 iod-0.003
SHARE-0.003
Token.
Token ID13
Feature activation+5.31e-02

Pos logit contributions
united+0.027
CTV+0.025
 additive+0.021
 iod+0.020
SHARE+0.019
Neg logit contributions
between-0.023
 Gaw-0.022
 undertaking-0.020
pty-0.019
abus-0.018
Token
Token ID198
Feature activation-1.00e-02

Pos logit contributions
between+0.042
 Gaw+0.039
 undertaking+0.035
pty+0.034
abus+0.033
Neg logit contributions
united-0.047
CTV-0.043
 additive-0.036
 iod-0.035
SHARE-0.032
Token
Token ID198
Feature activation-1.98e-02

Pos logit contributions
united+0.009
CTV+0.009
 additive+0.007
 iod+0.007
SHARE+0.006
Neg logit contributions
between-0.007
 Gaw-0.007
 undertaking-0.006
pty-0.006
abus-0.006
TokenThanks
Token ID9690
Feature activation-3.87e-01

Pos logit contributions
united+0.017
CTV+0.015
 additive+0.012
 iod+0.012
SHARE+0.011
Neg logit contributions
between-0.017
 Gaw-0.015
 undertaking-0.014
pty-0.014
abus-0.013
Token,
Token ID11
Feature activation+6.93e-03

Pos logit contributions
united+0.324
CTV+0.295
 additive+0.242
 iod+0.238
SHARE+0.213
Neg logit contributions
between-0.323
 Gaw-0.302
 undertaking-0.275
pty-0.264
abus-0.259
Token Wii
Token ID16591
Feature activation+2.73e-02

Pos logit contributions
between+0.005
 Gaw+0.005
 undertaking+0.004
pty+0.004
abus+0.004
Neg logit contributions
united-0.006
CTV-0.006
 additive-0.005
 iod-0.005
SHARE-0.004
TokenUM
Token ID5883
Feature activation-6.02e-02

Pos logit contributions
between+0.023
 Gaw+0.022
 undertaking+0.020
pty+0.019
abus+0.019
Neg logit contributions
united-0.022
CTV-0.020
 additive-0.017
 iod-0.016
SHARE-0.015
Tokenaster
Token ID1603
Feature activation+6.68e-02

Pos logit contributions
united+0.054
CTV+0.050
 additive+0.041
 iod+0.041
SHARE+0.037
Neg logit contributions
between-0.046
 Gaw-0.043
 undertaking-0.039
pty-0.037
abus-0.036
TokenRace
Token ID35157
Feature activation-1.94e-01

Pos logit contributions
between+0.052
 Gaw+0.048
 undertaking+0.044
pty+0.042
abus+0.041
Neg logit contributions
united-0.060
CTV-0.055
 additive-0.046
 iod-0.045
SHARE-0.041
Token
Token ID198
Feature activation+6.25e-02

Pos logit contributions
between+0.058
 Gaw+0.054
 undertaking+0.049
pty+0.046
abus+0.046
Neg logit contributions
united-0.071
CTV-0.066
 additive-0.055
 iod-0.054
SHARE-0.049
TokenOfficials
Token ID25883
Feature activation-7.94e-02

Pos logit contributions
between+0.050
 Gaw+0.047
 undertaking+0.043
pty+0.041
abus+0.040
Neg logit contributions
united-0.054
CTV-0.049
 additive-0.040
 iod-0.040
SHARE-0.036
Token said
Token ID531
Feature activation+8.96e-02

Pos logit contributions
united+0.073
CTV+0.067
 additive+0.056
 iod+0.055
SHARE+0.050
Neg logit contributions
between-0.060
 Gaw-0.055
 undertaking-0.050
pty-0.047
abus-0.047
Token May
Token ID1737
Feature activation-1.81e-02

Pos logit contributions
between+0.060
 Gaw+0.055
 undertaking+0.049
pty+0.047
abus+0.046
Neg logit contributions
united-0.089
CTV-0.083
 additive-0.070
 iod-0.069
SHARE-0.064
Tokenra
Token ID430
Feature activation-3.00e-02

Pos logit contributions
united+0.016
CTV+0.014
 additive+0.012
 iod+0.012
SHARE+0.010
Neg logit contributions
between-0.015
 Gaw-0.014
 undertaking-0.012
pty-0.012
abus-0.012
Token Martinez
Token ID20741
Feature activation-4.13e-01

Pos logit contributions
united+0.028
CTV+0.026
 additive+0.021
 iod+0.021
SHARE+0.019
Neg logit contributions
between-0.022
 Gaw-0.021
 undertaking-0.019
pty-0.018
abus-0.017
Token was
Token ID373
Feature activation+3.07e-02

Pos logit contributions
united+0.361
CTV+0.330
 additive+0.274
 iod+0.269
SHARE+0.243
Neg logit contributions
between-0.329
 Gaw-0.306
 undertaking-0.278
pty-0.265
abus-0.261
Token brought
Token ID3181
Feature activation-1.06e-01

Pos logit contributions
between+0.024
 Gaw+0.022
 undertaking+0.020
pty+0.019
abus+0.019
Neg logit contributions
united-0.028
CTV-0.026
 additive-0.021
 iod-0.021
SHARE-0.019
Token to
Token ID284
Feature activation+9.60e-02

Pos logit contributions
united+0.092
CTV+0.084
 additive+0.070
 iod+0.069
SHARE+0.062
Neg logit contributions
between-0.084
 Gaw-0.078
 undertaking-0.071
pty-0.068
abus-0.067
Token the
Token ID262
Feature activation+1.97e-02

Pos logit contributions
between+0.072
 Gaw+0.067
 undertaking+0.060
pty+0.057
abus+0.056
Neg logit contributions
united-0.088
CTV-0.081
 additive-0.068
 iod-0.067
SHARE-0.061
Token jail
Token ID7356
Feature activation-1.00e-01

Pos logit contributions
between+0.018
 Gaw+0.017
 undertaking+0.016
pty+0.015
devices+0.015
Neg logit contributions
united-0.015
CTV-0.013
 additive-0.010
 iod-0.010
SHARE-0.009