TOP ACTIVATIONS
MAX = 0.578

state . Ex ercise . High - intensity exercise
of metabolic ex ercise which has many
of metabolic ex ercise , in which
a questionable choice against rocket launchers and grenades .
the face of some scept icism , the C IP D
Ent itled To Hold Such Views ." ... Charles
Birmingham School of Medicine . Views expressed are his own and
to keep Red Hat or CentOS servers operating smoothly and you
on , the machine wh irs into action , producing a
and Anat ol iy D erk ach . Vi
developments are knee - j erk . They 're often characterized
had been repaid , D erk ach said app
away from Kirby 's bomb astic style of storytelling . According
he certainly has the bomb astic personality that would serve as
based Anat ol iy D erk ach , the owner of
asked to speak to D erk ach , and was put
were given dr astic dem otions for
a skin condition , an autos omal dominant palm opl ant
an already - f ant astic creation . Scott
being fat , not all 53 Euro - region countries are

MIN ACTIVATIONS
MIN = -0.668

report in an effort to smear the fired worker and create
when I do a pap smear and Medicare or private insurance
, and so is this smear campaign . NOT
, saying it is a smear campaign against his website [
co - worker during an undercover operation , according to the
when he was arrested by undercover police officers in November 2008
by Jo Roy le ( below ), the sk ipper and
important victories at West Brom wich Albion and Stoke City achieved
even as its bottom ( below water ) rises up to
specific relationships like above / below , or left / right
Luc io , a Browns ville Democrat who announced his support
of M . de Tre ville 's house on the r
year , split into two rival groups in September . Police
specific relationship like above / below , while also possessing elements
- and Herman Mel ville . . .
. Sanders out - raised rival Hillary Clinton for the fourth
Road , in North Ridge ville . It has stayed in
the game against West Brom wich Albion at Anfield in October
Two nights later , a rival group did the same nearby
Mr Cameron said Britain should rival Dubai as one of the

INTERVAL 0.266 - 0.578
CONTAINS 1.336%

by state - owned Guang d ong D aba osh an
Regarding Arduino compatibility itself , doing it well on anything other
They got Bill Ward out of the asylum to play
esp rit origin el des Cors aires [...] En cas de
Catalonia could be a way out of the present dead lock

INTERVAL -0.045 - 0.266
CONTAINS 74.393%

are ways this could have been handled without striking her ,"
and silk weaving . Today , the same types of looms
was built on farmland owned by the Sherman family .
Wife CBS Tat iana Mas l any Or phan Black BBC
and the lighting wasn t ideal , either .

INTERVAL -0.356 - -0.045
CONTAINS 24.046%

ojure / tools . n repl | 12 44 | |
number of journeys on the Tube has increased by 30 %;
any Mercenary war caster and non - character war j acks
colleague Nicole O zer has discussed , there is a long
and took images of the pin hole at a 40 degree

INTERVAL -0.668 - -0.356
CONTAINS 0.225%

$ art ext = ($ text - split "\ r
AT M CC ON NE LL Trump has often
HBO Jim Parsons The Big Bang Theory CBS Amy Poe hler
make up the majority of customers , she said .
, Ying Chen , were thru - h iking the 211
Token state
Token ID1181
Feature activation+1.64e-02

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
nown-0.003
 smear-0.003
 undercover-0.002
 rival-0.002
 informants-0.002
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
rek+0.013
ercise+0.011
iaries+0.011
agy+0.011
 launchers+0.011
Neg logit contributions
 smear-0.014
nown-0.014
 undercover-0.012
 rival-0.011
 Blackwell-0.011
Token
Token ID198
Feature activation-4.09e-04

Pos logit contributions
nown+0.012
 smear+0.012
 undercover+0.011
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.011
ercise-0.010
iaries-0.010
agy-0.009
 Views-0.009
Token
Token ID198
Feature activation-2.05e-03

Pos logit contributions
nown+0.000
 smear+0.000
 undercover+0.000
 rival+0.000
 informants+0.000
Neg logit contributions
rek-0.000
ercise-0.000
iaries-0.000
agy-0.000
 Views-0.000
TokenEx
Token ID3109
Feature activation+1.22e-01

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.002
 rival+0.001
below+0.001
Neg logit contributions
rek-0.002
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Tokenercise
Token ID23697
Feature activation+5.78e-01

Pos logit contributions
rek+0.022
ercise+0.011
iaries+0.010
agy+0.008
 launchers+0.008
Neg logit contributions
 smear-0.173
nown-0.173
 undercover-0.162
 rival-0.157
 informants-0.155
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
rek+0.441
ercise+0.394
iaries+0.383
 launchers+0.377
agy+0.376
Neg logit contributions
 smear-0.482
nown-0.482
 undercover-0.432
 rival-0.404
 informants-0.396
Token High
Token ID3334
Feature activation-1.89e-03

Pos logit contributions
 smear+0.013
nown+0.013
 undercover+0.012
 rival+0.011
 informants+0.011
Neg logit contributions
rek-0.011
ercise-0.009
iaries-0.009
agy-0.009
 launchers-0.009
Token-
Token ID12
Feature activation+2.65e-03

Pos logit contributions
nown+0.001
 smear+0.001
 undercover+0.001
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.002
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Tokenintensity
Token ID47799
Feature activation-8.50e-02

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.002
nown-0.002
 undercover-0.002
 rival-0.002
 informants-0.002
Token exercise
Token ID5517
Feature activation+2.49e-01

Pos logit contributions
 smear+0.078
nown+0.078
 undercover+0.071
 rival+0.067
 informants+0.065
Neg logit contributions
rek-0.058
ercise-0.050
iaries-0.050
agy-0.048
 launchers-0.048
Token of
Token ID286
Feature activation-2.50e-03

Pos logit contributions
 smear+0.044
nown+0.044
 undercover+0.039
 rival+0.037
 Blackwell+0.036
Neg logit contributions
rek-0.040
ercise-0.035
iaries-0.035
agy-0.034
 launchers-0.034
Token metabolic
Token ID19737
Feature activation+2.58e-02

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.002
 rival+0.002
 informants+0.002
Neg logit contributions
rek-0.002
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Token
Token ID564
Feature activation-1.70e-03

Pos logit contributions
rek+0.018
ercise+0.016
iaries+0.016
agy+0.016
 launchers+0.015
Neg logit contributions
 smear-0.023
nown-0.023
 undercover-0.021
 rival-0.019
 informants-0.019
Token
Token ID246
Feature activation+2.25e-02

Pos logit contributions
 smear+0.001
nown+0.001
 undercover+0.001
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.001
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Tokenex
Token ID1069
Feature activation+2.25e-01

Pos logit contributions
rek+0.012
ercise+0.010
iaries+0.009
agy+0.009
 launchers+0.009
Neg logit contributions
 smear-0.025
nown-0.025
 undercover-0.023
 rival-0.022
 informants-0.021
Tokenercise
Token ID23697
Feature activation+5.77e-01

Pos logit contributions
rek+0.018
ercise+0.000
iaries-0.005
agy-0.007
 launchers-0.009
Neg logit contributions
 smear-0.343
nown-0.343
 undercover-0.324
 rival-0.313
 informants-0.311
Token
Token ID447
Feature activation-3.75e-03

Pos logit contributions
rek+0.460
ercise+0.408
iaries+0.401
agy+0.394
 launchers+0.392
Neg logit contributions
 smear-0.465
nown-0.463
 undercover-0.415
 rival-0.388
 informants-0.380
Token
Token ID247
Feature activation-2.04e-02

Pos logit contributions
nown+0.003
 smear+0.003
 undercover+0.003
 rival+0.003
 informants+0.002
Neg logit contributions
rek-0.003
ercise-0.003
iaries-0.003
agy-0.003
 launchers-0.003
Token which
Token ID543
Feature activation-3.67e-03

Pos logit contributions
 smear+0.018
nown+0.018
 undercover+0.016
 rival+0.015
 informants+0.015
Neg logit contributions
rek-0.015
ercise-0.013
iaries-0.013
agy-0.013
 launchers-0.013
Token has
Token ID468
Feature activation+8.98e-02

Pos logit contributions
nown+0.003
 smear+0.003
 undercover+0.003
 rival+0.003
below+0.002
Neg logit contributions
rek-0.003
ercise-0.003
iaries-0.002
 launchers-0.002
agy-0.002
Token many
Token ID867
Feature activation+6.84e-02

Pos logit contributions
rek+0.070
ercise+0.062
iaries+0.060
agy+0.060
 launchers+0.060
Neg logit contributions
nown-0.074
 smear-0.074
 undercover-0.066
 rival-0.061
below-0.060
Token of
Token ID286
Feature activation-1.31e-02

Pos logit contributions
 smear+0.055
nown+0.055
 undercover+0.049
 rival+0.046
 informants+0.045
Neg logit contributions
rek-0.051
ercise-0.045
iaries-0.044
agy-0.043
 launchers-0.043
Token metabolic
Token ID19737
Feature activation+1.44e-02

Pos logit contributions
 smear+0.012
nown+0.012
 undercover+0.011
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.009
ercise-0.008
iaries-0.008
agy-0.008
 launchers-0.008
Token
Token ID564
Feature activation-3.44e-03

Pos logit contributions
rek+0.010
ercise+0.009
iaries+0.009
agy+0.009
 launchers+0.009
Neg logit contributions
 smear-0.013
nown-0.013
 undercover-0.011
 rival-0.011
 informants-0.011
Token
Token ID246
Feature activation+1.56e-02

Pos logit contributions
nown+0.003
 smear+0.003
 undercover+0.003
 rival+0.002
 informants+0.002
Neg logit contributions
rek-0.003
ercise-0.002
iaries-0.002
agy-0.002
 launchers-0.002
Tokenex
Token ID1069
Feature activation+2.20e-01

Pos logit contributions
rek+0.011
ercise+0.010
iaries+0.010
agy+0.009
 launchers+0.009
Neg logit contributions
 smear-0.014
nown-0.014
 undercover-0.012
 rival-0.012
 informants-0.012
Tokenercise
Token ID23697
Feature activation+5.65e-01

Pos logit contributions
rek+0.021
ercise+0.001
iaries-0.001
agy-0.004
 launchers-0.005
Neg logit contributions
 smear-0.332
nown-0.331
 undercover-0.313
 rival-0.303
 informants-0.300
Token
Token ID447
Feature activation-1.52e-02

Pos logit contributions
rek+0.498
ercise+0.450
iaries+0.438
agy+0.433
 launchers+0.432
Neg logit contributions
 smear-0.407
nown-0.406
 undercover-0.358
 rival-0.330
 informants-0.325
Token
Token ID247
Feature activation-2.03e-02

Pos logit contributions
nown+0.012
 smear+0.012
 undercover+0.011
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.012
ercise-0.011
iaries-0.011
agy-0.010
 launchers-0.010
Token,
Token ID11
Feature activation-4.93e-03

Pos logit contributions
 smear+0.017
nown+0.017
 undercover+0.015
 rival+0.014
 informants+0.014
Neg logit contributions
rek-0.015
ercise-0.014
iaries-0.013
agy-0.013
 launchers-0.013
Token in
Token ID287
Feature activation+9.84e-03

Pos logit contributions
 smear+0.004
nown+0.004
 undercover+0.004
 rival+0.003
 informants+0.003
Neg logit contributions
rek-0.004
ercise-0.003
iaries-0.003
agy-0.003
 launchers-0.003
Token which
Token ID543
Feature activation-1.32e-02

Pos logit contributions
rek+0.007
ercise+0.006
iaries+0.006
agy+0.006
 launchers+0.006
Neg logit contributions
 smear-0.008
nown-0.008
 undercover-0.008
 rival-0.007
 informants-0.007
Token a
Token ID257
Feature activation-1.11e-02

Pos logit contributions
nown+0.098
 smear+0.098
 undercover+0.088
 rival+0.082
 informants+0.081
Neg logit contributions
rek-0.089
ercise-0.078
iaries-0.077
agy-0.075
 launchers-0.075
Token questionable
Token ID18269
Feature activation-9.52e-02

Pos logit contributions
 smear+0.009
nown+0.009
 undercover+0.008
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.009
ercise-0.008
iaries-0.008
agy-0.008
 launchers-0.008
Token choice
Token ID3572
Feature activation+7.93e-02

Pos logit contributions
nown+0.079
 smear+0.079
 undercover+0.071
 rival+0.066
 informants+0.065
Neg logit contributions
rek-0.074
ercise-0.065
iaries-0.064
agy-0.063
 launchers-0.063
Token against
Token ID1028
Feature activation-2.29e-01

Pos logit contributions
rek+0.060
ercise+0.053
iaries+0.052
agy+0.051
 launchers+0.051
Neg logit contributions
 smear-0.067
nown-0.067
 undercover-0.060
 rival-0.056
 Blackwell-0.055
Token rocket
Token ID10701
Feature activation+9.19e-03

Pos logit contributions
nown+0.193
 smear+0.193
 undercover+0.173
 rival+0.162
 informants+0.159
Neg logit contributions
rek-0.174
ercise-0.152
iaries-0.151
 launchers-0.148
agy-0.147
Token launchers
Token ID41065
Feature activation+5.57e-01

Pos logit contributions
rek+0.006
ercise+0.005
iaries+0.005
agy+0.005
 Views+0.005
Neg logit contributions
 smear-0.009
nown-0.009
 undercover-0.008
 rival-0.008
 informants-0.007
Token and
Token ID290
Feature activation+6.03e-03

Pos logit contributions
rek+0.418
ercise+0.365
iaries+0.361
 launchers+0.354
agy+0.353
Neg logit contributions
 smear-0.474
nown-0.473
 undercover-0.425
 rival-0.399
 informants-0.392
Token grenades
Token ID28850
Feature activation+2.19e-01

Pos logit contributions
rek+0.005
ercise+0.004
iaries+0.004
 launchers+0.004
agy+0.004
Neg logit contributions
nown-0.005
 smear-0.005
 undercover-0.004
 rival-0.004
below-0.004
Token.
Token ID13
Feature activation-1.76e-02

Pos logit contributions
rek+0.169
ercise+0.148
iaries+0.146
 launchers+0.144
agy+0.143
Neg logit contributions
 smear-0.182
nown-0.182
 undercover-0.163
 rival-0.152
 informants-0.149
Token
Token ID198
Feature activation-2.24e-03

Pos logit contributions
nown+0.015
 smear+0.015
 undercover+0.013
 rival+0.012
 informants+0.012
Neg logit contributions
rek-0.013
ercise-0.012
iaries-0.012
agy-0.011
 launchers-0.011
Token
Token ID198
Feature activation-6.13e-03

Pos logit contributions
nown+0.002
 smear+0.002
 undercover+0.002
 rival+0.002
 informants+0.002
Neg logit contributions
rek-0.002
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Token the
Token ID262
Feature activation+9.35e-03

Pos logit contributions
rek+0.016
ercise+0.014
iaries+0.014
agy+0.014
 launchers+0.014
Neg logit contributions
 smear-0.018
nown-0.018
 undercover-0.017
 rival-0.016
 informants-0.015
Token face
Token ID1986
Feature activation-8.28e-02

Pos logit contributions
rek+0.007
ercise+0.007
iaries+0.006
 launchers+0.006
agy+0.006
Neg logit contributions
nown-0.008
 smear-0.008
 undercover-0.007
 rival-0.006
 informants-0.006
Token of
Token ID286
Feature activation-4.41e-03

Pos logit contributions
nown+0.071
 smear+0.071
 undercover+0.064
 rival+0.059
 informants+0.059
Neg logit contributions
rek-0.062
ercise-0.054
iaries-0.053
 launchers-0.052
agy-0.052
Token some
Token ID617
Feature activation+6.08e-02

Pos logit contributions
nown+0.004
 smear+0.004
 undercover+0.003
 rival+0.003
below+0.003
Neg logit contributions
rek-0.003
ercise-0.003
iaries-0.003
 launchers-0.003
 Views-0.003
Token scept
Token ID30186
Feature activation-1.50e-01

Pos logit contributions
rek+0.046
ercise+0.041
iaries+0.040
 launchers+0.039
agy+0.039
Neg logit contributions
nown-0.051
 smear-0.051
 undercover-0.046
 rival-0.043
below-0.042
Tokenicism
Token ID11965
Feature activation+5.47e-01

Pos logit contributions
 smear+0.207
nown+0.207
 undercover+0.194
 rival+0.188
below+0.185
Neg logit contributions
rek-0.031
ercise-0.018
iaries-0.016
agy-0.014
 launchers-0.014
Token,
Token ID11
Feature activation+8.71e-03

Pos logit contributions
rek+0.417
ercise+0.366
iaries+0.361
agy+0.353
 launchers+0.353
Neg logit contributions
nown-0.460
 smear-0.458
 undercover-0.411
 rival-0.385
 informants-0.378
Token the
Token ID262
Feature activation+2.47e-03

Pos logit contributions
rek+0.006
ercise+0.006
iaries+0.006
agy+0.005
 launchers+0.005
Neg logit contributions
nown-0.008
 smear-0.008
 undercover-0.007
 rival-0.006
 informants-0.006
Token C
Token ID327
Feature activation-3.94e-02

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
 launchers+0.002
agy+0.002
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.002
 informants-0.002
TokenIP
Token ID4061
Feature activation-7.29e-02

Pos logit contributions
nown+0.027
 smear+0.027
 undercover+0.024
 rival+0.022
 informants+0.022
Neg logit contributions
rek-0.036
ercise-0.032
iaries-0.032
agy-0.031
 launchers-0.031
TokenD
Token ID35
Feature activation+2.28e-01

Pos logit contributions
 smear+0.060
nown+0.060
 undercover+0.054
 rival+0.050
 informants+0.049
Neg logit contributions
rek-0.057
ercise-0.050
iaries-0.049
agy-0.048
 launchers-0.048
Token Ent
Token ID7232
Feature activation+1.25e-01

Pos logit contributions
 smear+0.014
nown+0.014
 undercover+0.013
 rival+0.012
 Blackwell+0.012
Neg logit contributions
rek-0.014
ercise-0.012
iaries-0.012
agy-0.012
 launchers-0.012
Tokenitled
Token ID7803
Feature activation+3.40e-01

Pos logit contributions
rek+0.054
ercise+0.043
iaries+0.043
 launchers+0.042
agy+0.041
Neg logit contributions
 smear-0.144
nown-0.144
 undercover-0.133
 rival-0.128
below-0.126
Token To
Token ID1675
Feature activation-5.68e-02

Pos logit contributions
rek+0.288
ercise+0.257
iaries+0.255
agy+0.250
 launchers+0.250
Neg logit contributions
 smear-0.256
nown-0.254
 undercover-0.226
 rival-0.211
 Blackwell-0.205
Token Hold
Token ID9340
Feature activation+1.25e-01

Pos logit contributions
 smear+0.046
nown+0.046
 undercover+0.041
 rival+0.039
 informants+0.038
Neg logit contributions
rek-0.045
ercise-0.039
iaries-0.039
agy-0.038
 launchers-0.038
Token Such
Token ID8013
Feature activation-8.22e-02

Pos logit contributions
rek+0.100
ercise+0.089
iaries+0.088
agy+0.086
 launchers+0.086
Neg logit contributions
 smear-0.100
nown-0.100
 undercover-0.089
 rival-0.084
 informants-0.082
Token Views
Token ID29978
Feature activation+5.44e-01

Pos logit contributions
 smear+0.068
nown+0.068
 undercover+0.061
 rival+0.057
 informants+0.056
Neg logit contributions
rek-0.064
ercise-0.056
iaries-0.056
agy-0.054
 launchers-0.054
Token."
Token ID526
Feature activation+9.68e-02

Pos logit contributions
rek+0.411
ercise+0.361
iaries+0.356
agy+0.348
 launchers+0.347
Neg logit contributions
 smear-0.459
nown-0.459
 undercover-0.412
 rival-0.387
 informants-0.380
Token...
Token ID986
Feature activation+2.80e-02

Pos logit contributions
rek+0.076
ercise+0.067
iaries+0.066
 Views+0.065
agy+0.065
Neg logit contributions
nown-0.079
 smear-0.079
 undercover-0.071
 rival-0.066
 informants-0.065
Token
Token ID198
Feature activation-3.35e-04

Pos logit contributions
rek+0.022
ercise+0.019
iaries+0.019
agy+0.019
 launchers+0.019
Neg logit contributions
 smear-0.023
nown-0.023
 undercover-0.021
 rival-0.019
 informants-0.019
Token
Token ID198
Feature activation-2.04e-03

Pos logit contributions
nown+0.000
 smear+0.000
 undercover+0.000
 rival+0.000
 informants+0.000
Neg logit contributions
rek-0.000
ercise-0.000
iaries-0.000
agy-0.000
 Views-0.000
TokenCharles
Token ID28711
Feature activation-1.22e-01

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.002
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.002
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Token Birmingham
Token ID18899
Feature activation-3.87e-01

Pos logit contributions
 smear+0.018
nown+0.018
 undercover+0.015
 rival+0.012
 informants+0.012
Neg logit contributions
rek-0.052
ercise-0.048
iaries-0.047
agy-0.047
 launchers-0.047
Token School
Token ID3961
Feature activation-1.34e-01

Pos logit contributions
 smear+0.320
nown+0.319
 undercover+0.286
 rival+0.269
 informants+0.262
Neg logit contributions
rek-0.300
ercise-0.264
iaries-0.261
agy-0.256
 launchers-0.255
Token of
Token ID286
Feature activation-1.15e-02

Pos logit contributions
 smear+0.112
nown+0.112
 undercover+0.101
 rival+0.094
 informants+0.092
Neg logit contributions
rek-0.103
ercise-0.091
iaries-0.089
agy-0.088
 Views-0.087
Token Medicine
Token ID11558
Feature activation+1.17e-01

Pos logit contributions
nown+0.011
 smear+0.011
 undercover+0.010
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.007
ercise-0.006
iaries-0.006
 Views-0.006
agy-0.006
Token.
Token ID13
Feature activation-2.24e-02

Pos logit contributions
rek+0.090
ercise+0.079
iaries+0.078
agy+0.077
 launchers+0.076
Neg logit contributions
 smear-0.097
nown-0.097
 undercover-0.087
 rival-0.082
 informants-0.080
Token Views
Token ID29978
Feature activation+5.38e-01

Pos logit contributions
 smear+0.019
nown+0.019
 undercover+0.018
 rival+0.016
 informants+0.016
Neg logit contributions
rek-0.017
ercise-0.014
iaries-0.014
agy-0.014
 Views-0.014
Token expressed
Token ID6241
Feature activation-1.92e-02

Pos logit contributions
rek+0.438
ercise+0.387
iaries+0.383
 Views+0.377
 launchers+0.375
Neg logit contributions
nown-0.425
 smear-0.422
 undercover-0.375
 rival-0.350
 informants-0.344
Token are
Token ID389
Feature activation-5.66e-03

Pos logit contributions
nown+0.016
 smear+0.016
 undercover+0.015
 rival+0.014
 informants+0.013
Neg logit contributions
rek-0.014
ercise-0.013
iaries-0.012
agy-0.012
 launchers-0.012
Token his
Token ID465
Feature activation-1.81e-02

Pos logit contributions
 smear+0.005
nown+0.005
 undercover+0.004
 rival+0.004
 informants+0.004
Neg logit contributions
rek-0.004
ercise-0.004
iaries-0.004
agy-0.004
 launchers-0.004
Token own
Token ID898
Feature activation+2.73e-01

Pos logit contributions
 smear+0.020
nown+0.019
 undercover+0.018
 rival+0.017
 informants+0.017
Neg logit contributions
rek-0.009
ercise-0.008
iaries-0.008
agy-0.007
 launchers-0.007
Token and
Token ID290
Feature activation+7.01e-03

Pos logit contributions
rek+0.215
ercise+0.190
iaries+0.188
agy+0.183
 launchers+0.183
Neg logit contributions
 smear-0.222
nown-0.221
 undercover-0.199
 rival-0.187
 informants-0.182
Token to
Token ID284
Feature activation+1.65e-02

Pos logit contributions
rek+0.007
ercise+0.006
iaries+0.006
agy+0.006
 launchers+0.006
Neg logit contributions
 smear-0.008
nown-0.008
 undercover-0.007
 rival-0.006
 informants-0.006
Token keep
Token ID1394
Feature activation+2.00e-01

Pos logit contributions
rek+0.013
ercise+0.011
iaries+0.011
agy+0.011
 launchers+0.011
Neg logit contributions
nown-0.014
 smear-0.014
 undercover-0.012
 rival-0.011
 informants-0.011
Token Red
Token ID2297
Feature activation+2.25e-01

Pos logit contributions
rek+0.147
ercise+0.128
iaries+0.127
agy+0.124
 launchers+0.124
Neg logit contributions
nown-0.174
 smear-0.174
 undercover-0.156
 rival-0.147
 informants-0.144
Token Hat
Token ID10983
Feature activation+7.92e-02

Pos logit contributions
rek+0.165
ercise+0.144
iaries+0.143
agy+0.139
 launchers+0.138
Neg logit contributions
 smear-0.195
nown-0.194
 undercover-0.176
 rival-0.166
below-0.162
Token or
Token ID393
Feature activation+2.08e-01

Pos logit contributions
rek+0.057
ercise+0.050
iaries+0.050
agy+0.048
 launchers+0.048
Neg logit contributions
 smear-0.069
nown-0.069
 undercover-0.063
 rival-0.059
 informants-0.058
Token CentOS
Token ID32418
Feature activation+5.30e-01

Pos logit contributions
rek+0.143
ercise+0.124
iaries+0.122
 launchers+0.120
agy+0.119
Neg logit contributions
nown-0.190
 smear-0.189
 undercover-0.172
 rival-0.161
 informants-0.159
Token servers
Token ID9597
Feature activation+1.27e-01

Pos logit contributions
rek+0.356
ercise+0.307
iaries+0.303
agy+0.295
 launchers+0.293
Neg logit contributions
 smear-0.493
nown-0.492
 undercover-0.447
 rival-0.423
 informants-0.415
Token operating
Token ID5361
Feature activation+9.80e-02

Pos logit contributions
rek+0.085
ercise+0.073
iaries+0.073
agy+0.071
 launchers+0.070
Neg logit contributions
 smear-0.118
nown-0.118
 undercover-0.107
 rival-0.102
 informants-0.099
Token smoothly
Token ID21461
Feature activation-6.58e-03

Pos logit contributions
rek+0.075
ercise+0.066
iaries+0.065
agy+0.064
 launchers+0.064
Neg logit contributions
 smear-0.082
nown-0.082
 undercover-0.073
 rival-0.069
 informants-0.067
Token and
Token ID290
Feature activation+1.32e-02

Pos logit contributions
 smear+0.006
nown+0.006
 undercover+0.005
 rival+0.005
 informants+0.005
Neg logit contributions
rek-0.005
ercise-0.004
iaries-0.004
agy-0.004
 launchers-0.004
Token you
Token ID345
Feature activation-4.40e-02

Pos logit contributions
rek+0.010
ercise+0.009
iaries+0.009
agy+0.009
 launchers+0.009
Neg logit contributions
 smear-0.011
nown-0.011
 undercover-0.010
 rival-0.009
 informants-0.009
Token on
Token ID319
Feature activation-1.54e-02

Pos logit contributions
nown+0.069
 smear+0.068
 undercover+0.060
 rival+0.056
below+0.055
Neg logit contributions
rek-0.075
ercise-0.067
iaries-0.066
agy-0.065
 launchers-0.065
Token,
Token ID11
Feature activation+1.86e-02

Pos logit contributions
 smear+0.013
nown+0.013
 undercover+0.012
 rival+0.011
 informants+0.011
Neg logit contributions
rek-0.011
ercise-0.010
iaries-0.010
agy-0.010
 launchers-0.010
Token the
Token ID262
Feature activation+7.82e-03

Pos logit contributions
rek+0.015
ercise+0.013
iaries+0.013
 launchers+0.013
agy+0.013
Neg logit contributions
nown-0.015
 smear-0.015
 undercover-0.013
 rival-0.013
 informants-0.012
Token machine
Token ID4572
Feature activation-1.92e-01

Pos logit contributions
rek+0.006
ercise+0.006
iaries+0.006
 launchers+0.005
agy+0.005
Neg logit contributions
nown-0.006
 smear-0.006
 undercover-0.005
 rival-0.005
below-0.005
Token wh
Token ID348
Feature activation+5.58e-03

Pos logit contributions
nown+0.163
 smear+0.163
 undercover+0.147
 rival+0.137
 informants+0.135
Neg logit contributions
rek-0.145
ercise-0.127
iaries-0.125
agy-0.123
 launchers-0.123
Tokenirs
Token ID17062
Feature activation+5.09e-01

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
agy+0.003
 launchers+0.003
Neg logit contributions
 smear-0.006
nown-0.006
 undercover-0.005
 rival-0.005
 informants-0.005
Token into
Token ID656
Feature activation+5.26e-02

Pos logit contributions
rek+0.388
ercise+0.342
iaries+0.336
agy+0.330
 launchers+0.329
Neg logit contributions
nown-0.426
 smear-0.425
 undercover-0.382
 rival-0.358
below-0.351
Token action
Token ID2223
Feature activation+1.21e-01

Pos logit contributions
rek+0.041
ercise+0.036
iaries+0.035
agy+0.035
 launchers+0.035
Neg logit contributions
 smear-0.043
nown-0.043
 undercover-0.039
 rival-0.037
 informants-0.036
Token,
Token ID11
Feature activation+1.79e-02

Pos logit contributions
rek+0.092
ercise+0.081
iaries+0.080
agy+0.078
 launchers+0.078
Neg logit contributions
 smear-0.101
nown-0.101
 undercover-0.091
 rival-0.085
 informants-0.083
Token producing
Token ID9194
Feature activation-2.84e-02

Pos logit contributions
rek+0.014
ercise+0.012
iaries+0.012
agy+0.012
 launchers+0.012
Neg logit contributions
 smear-0.015
nown-0.015
 undercover-0.013
 rival-0.013
 informants-0.012
Token a
Token ID257
Feature activation-8.09e-03

Pos logit contributions
nown+0.023
 smear+0.023
 undercover+0.021
 rival+0.020
below+0.019
Neg logit contributions
rek-0.022
ercise-0.019
iaries-0.019
 launchers-0.019
agy-0.019
Token and
Token ID290
Feature activation+1.08e-02

Pos logit contributions
 smear+0.090
nown+0.090
 undercover+0.082
 rival+0.077
 informants+0.076
Neg logit contributions
rek-0.068
ercise-0.059
iaries-0.058
agy-0.057
 launchers-0.056
Token Anat
Token ID28880
Feature activation-1.55e-02

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 launchers+0.007
Neg logit contributions
 smear-0.009
nown-0.009
 undercover-0.008
 rival-0.008
 informants-0.007
Tokenol
Token ID349
Feature activation-3.51e-02

Pos logit contributions
 smear+0.007
nown+0.007
 undercover+0.005
 rival+0.005
 informants+0.004
Neg logit contributions
rek-0.018
ercise-0.017
iaries-0.017
agy-0.016
 launchers-0.016
Tokeniy
Token ID7745
Feature activation-4.39e-02

Pos logit contributions
 smear+0.027
nown+0.027
 undercover+0.024
 rival+0.022
 informants+0.022
Neg logit contributions
rek-0.030
ercise-0.026
iaries-0.026
agy-0.026
 launchers-0.025
Token D
Token ID360
Feature activation+8.36e-02

Pos logit contributions
nown+0.037
 smear+0.037
 undercover+0.033
 rival+0.031
 informants+0.030
Neg logit contributions
rek-0.034
ercise-0.030
iaries-0.029
agy-0.029
 launchers-0.029
Tokenerk
Token ID9587
Feature activation+5.04e-01

Pos logit contributions
rek+0.063
ercise+0.055
iaries+0.054
agy+0.054
 launchers+0.053
Neg logit contributions
 smear-0.071
nown-0.071
 undercover-0.064
 rival-0.060
 informants-0.059
Tokenach
Token ID620
Feature activation+9.67e-03

Pos logit contributions
rek+0.392
ercise+0.343
iaries+0.338
agy+0.334
 launchers+0.330
Neg logit contributions
 smear-0.418
nown-0.416
 undercover-0.376
 rival-0.352
 informants-0.346
Token.
Token ID13
Feature activation-1.41e-02

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.006
 launchers+0.006
Neg logit contributions
 smear-0.008
nown-0.008
 undercover-0.007
 rival-0.007
 informants-0.007
Token
Token ID198
Feature activation+4.86e-03

Pos logit contributions
 smear+0.012
nown+0.012
 undercover+0.011
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.011
ercise-0.010
iaries-0.009
 Views-0.009
agy-0.009
Token
Token ID198
Feature activation-1.42e-03

Pos logit contributions
rek+0.004
ercise+0.003
iaries+0.003
agy+0.003
 Views+0.003
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.004
 rival-0.003
 informants-0.003
TokenVi
Token ID38432
Feature activation-1.38e-02

Pos logit contributions
 smear+0.001
nown+0.001
 undercover+0.001
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.001
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Token developments
Token ID13312
Feature activation-6.70e-02

Pos logit contributions
nown+0.016
 smear+0.016
 undercover+0.015
 rival+0.014
 informants+0.013
Neg logit contributions
rek-0.015
ercise-0.013
iaries-0.013
 launchers-0.013
agy-0.013
Token are
Token ID389
Feature activation+1.67e-03

Pos logit contributions
nown+0.056
 smear+0.055
 undercover+0.050
 Blackwell+0.046
 rival+0.046
Neg logit contributions
rek-0.051
ercise-0.045
iaries-0.045
 launchers-0.044
agy-0.043
Token knee
Token ID10329
Feature activation+1.27e-01

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
 launchers+0.001
agy+0.001
Neg logit contributions
nown-0.001
 smear-0.001
 undercover-0.001
 rival-0.001
below-0.001
Token-
Token ID12
Feature activation+9.49e-03

Pos logit contributions
rek+0.096
ercise+0.084
iaries+0.084
agy+0.081
 Views+0.081
Neg logit contributions
 smear-0.108
nown-0.107
 undercover-0.097
 rival-0.091
 informants-0.089
Tokenj
Token ID73
Feature activation+1.74e-01

Pos logit contributions
rek+0.006
iaries+0.005
ercise+0.005
 launchers+0.005
 Views+0.005
Neg logit contributions
 smear-0.009
nown-0.009
 undercover-0.009
 rival-0.008
below-0.008
Tokenerk
Token ID9587
Feature activation+5.03e-01

Pos logit contributions
rek+0.031
ercise+0.018
iaries+0.017
 launchers+0.014
 Views+0.014
Neg logit contributions
nown-0.243
 smear-0.243
 undercover-0.227
 rival-0.219
below-0.217
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
rek+0.376
ercise+0.329
iaries+0.326
agy+0.318
 launchers+0.318
Neg logit contributions
nown-0.429
 smear-0.428
 undercover-0.385
 rival-0.361
below-0.354
Token They
Token ID1119
Feature activation+8.80e-02

Pos logit contributions
nown+0.013
 smear+0.013
 undercover+0.011
 rival+0.011
 informants+0.011
Neg logit contributions
rek-0.011
ercise-0.010
iaries-0.010
 Views-0.010
agy-0.009
Token're
Token ID821
Feature activation+2.78e-01

Pos logit contributions
rek+0.064
ercise+0.055
iaries+0.055
agy+0.054
 launchers+0.053
Neg logit contributions
nown-0.078
 smear-0.077
 undercover-0.070
 rival-0.065
 informants-0.064
Token often
Token ID1690
Feature activation+1.03e-01

Pos logit contributions
rek+0.226
ercise+0.199
iaries+0.198
 launchers+0.194
agy+0.193
Neg logit contributions
nown-0.221
 smear-0.218
 undercover-0.194
 rival-0.181
below-0.179
Token characterized
Token ID16264
Feature activation+5.03e-02

Pos logit contributions
rek+0.085
ercise+0.075
iaries+0.075
 launchers+0.073
agy+0.073
Neg logit contributions
nown-0.080
 smear-0.079
 undercover-0.071
 rival-0.066
below-0.065
Token had
Token ID550
Feature activation+1.43e-01

Pos logit contributions
 smear+0.049
nown+0.048
 undercover+0.044
 rival+0.041
below+0.040
Neg logit contributions
rek-0.041
ercise-0.036
iaries-0.035
agy-0.035
 launchers-0.035
Token been
Token ID587
Feature activation-7.19e-03

Pos logit contributions
rek+0.112
ercise+0.098
iaries+0.098
 launchers+0.096
agy+0.096
Neg logit contributions
nown-0.116
 smear-0.116
 undercover-0.103
 rival-0.097
below-0.095
Token repaid
Token ID48417
Feature activation-2.32e-01

Pos logit contributions
 smear+0.006
nown+0.006
 undercover+0.005
 rival+0.005
below+0.005
Neg logit contributions
rek-0.006
ercise-0.005
iaries-0.005
agy-0.005
 launchers-0.005
Token,
Token ID11
Feature activation+3.96e-03

Pos logit contributions
 smear+0.198
nown+0.198
 undercover+0.178
 rival+0.168
 informants+0.164
Neg logit contributions
rek-0.173
ercise-0.151
iaries-0.150
agy-0.146
 launchers-0.146
Token D
Token ID360
Feature activation+7.37e-02

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
agy+0.003
 launchers+0.003
Neg logit contributions
 smear-0.003
nown-0.003
 undercover-0.003
 rival-0.003
 informants-0.003
Tokenerk
Token ID9587
Feature activation+5.03e-01

Pos logit contributions
rek+0.011
ercise+0.006
iaries+0.006
 Views+0.005
 launchers+0.004
Neg logit contributions
nown-0.105
 smear-0.104
 undercover-0.098
 rival-0.095
below-0.094
Tokenach
Token ID620
Feature activation+1.35e-03

Pos logit contributions
rek+0.380
ercise+0.334
iaries+0.328
agy+0.323
 launchers+0.318
Neg logit contributions
 smear-0.427
nown-0.424
 undercover-0.383
 rival-0.361
 informants-0.353
Token said
Token ID531
Feature activation-8.05e-03

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
 smear-0.001
nown-0.001
 undercover-0.001
 rival-0.001
 informants-0.001
Token
Token ID564
Feature activation+2.94e-03

Pos logit contributions
 smear+0.006
nown+0.006
 undercover+0.006
 rival+0.005
 informants+0.005
Neg logit contributions
rek-0.006
ercise-0.006
iaries-0.006
agy-0.006
 launchers-0.005
Token
Token ID250
Feature activation+1.97e-02

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
agy+0.002
 Views+0.002
Neg logit contributions
 smear-0.002
nown-0.002
 undercover-0.002
 rival-0.002
 Blackwell-0.002
Tokenapp
Token ID1324
Feature activation-3.52e-02

Pos logit contributions
rek+0.017
ercise+0.015
iaries+0.015
agy+0.015
 launchers+0.015
Neg logit contributions
 smear-0.014
nown-0.014
 undercover-0.013
 rival-0.012
 informants-0.011
Token away
Token ID1497
Feature activation+5.45e-02

Pos logit contributions
 smear+0.033
nown+0.033
 undercover+0.030
 rival+0.028
 informants+0.028
Neg logit contributions
rek-0.029
ercise-0.025
iaries-0.025
agy-0.024
 launchers-0.024
Token from
Token ID422
Feature activation+7.28e-02

Pos logit contributions
rek+0.038
ercise+0.033
iaries+0.032
agy+0.031
 launchers+0.031
Neg logit contributions
 smear-0.050
nown-0.050
 undercover-0.045
 rival-0.043
 informants-0.042
Token Kirby
Token ID23965
Feature activation+2.53e-02

Pos logit contributions
rek+0.056
ercise+0.049
iaries+0.049
agy+0.048
 launchers+0.048
Neg logit contributions
nown-0.060
 smear-0.060
 undercover-0.054
 rival-0.051
 informants-0.050
Token's
Token ID338
Feature activation-2.91e-02

Pos logit contributions
rek+0.020
ercise+0.018
iaries+0.017
 launchers+0.017
agy+0.017
Neg logit contributions
 smear-0.021
nown-0.021
 undercover-0.018
 rival-0.017
 informants-0.017
Token bomb
Token ID5194
Feature activation-2.58e-01

Pos logit contributions
nown+0.024
 smear+0.024
 undercover+0.021
 rival+0.020
 informants+0.020
Neg logit contributions
rek-0.023
ercise-0.020
iaries-0.020
agy-0.019
 launchers-0.019
Tokenastic
Token ID3477
Feature activation+5.02e-01

Pos logit contributions
 smear+0.357
nown+0.356
 undercover+0.335
 rival+0.324
 informants+0.318
Neg logit contributions
rek-0.056
ercise-0.033
iaries-0.031
agy-0.026
 Views-0.025
Token style
Token ID3918
Feature activation+7.01e-02

Pos logit contributions
rek+0.379
ercise+0.329
iaries+0.327
 Views+0.322
 launchers+0.321
Neg logit contributions
nown-0.428
 smear-0.421
 undercover-0.379
 rival-0.354
below-0.352
Token of
Token ID286
Feature activation-8.36e-04

Pos logit contributions
rek+0.052
ercise+0.046
iaries+0.045
agy+0.044
 launchers+0.044
Neg logit contributions
nown-0.060
 smear-0.060
 undercover-0.054
 rival-0.050
 informants-0.049
Token storytelling
Token ID23689
Feature activation+4.82e-02

Pos logit contributions
nown+0.001
 smear+0.001
 undercover+0.001
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.001
ercise-0.000
iaries-0.000
agy-0.000
 launchers-0.000
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
rek+0.036
ercise+0.032
iaries+0.031
 launchers+0.031
agy+0.030
Neg logit contributions
nown-0.041
 smear-0.041
 undercover-0.037
 rival-0.034
 informants-0.034
Token According
Token ID4784
Feature activation-1.09e-01

Pos logit contributions
nown+0.011
 smear+0.011
 undercover+0.010
 rival+0.009
 informants+0.009
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.009
 Views-0.009
agy-0.009
Token he
Token ID339
Feature activation-4.45e-02

Pos logit contributions
rek+0.007
ercise+0.006
iaries+0.006
agy+0.006
 launchers+0.006
Neg logit contributions
nown-0.007
 smear-0.007
 undercover-0.006
 rival-0.006
below-0.006
Token certainly
Token ID3729
Feature activation+7.17e-02

Pos logit contributions
nown+0.037
 smear+0.037
 undercover+0.033
 rival+0.031
 informants+0.031
Neg logit contributions
rek-0.034
ercise-0.030
iaries-0.029
agy-0.029
 launchers-0.029
Token has
Token ID468
Feature activation+8.69e-02

Pos logit contributions
rek+0.055
ercise+0.048
iaries+0.048
 launchers+0.047
agy+0.047
Neg logit contributions
nown-0.060
 smear-0.059
 undercover-0.053
 rival-0.049
 informants-0.049
Token the
Token ID262
Feature activation+7.57e-03

Pos logit contributions
rek+0.068
ercise+0.059
iaries+0.059
 launchers+0.058
agy+0.057
Neg logit contributions
nown-0.072
 smear-0.071
 undercover-0.064
 rival-0.060
below-0.059
Token bomb
Token ID5194
Feature activation-2.59e-01

Pos logit contributions
rek+0.006
ercise+0.006
iaries+0.005
 launchers+0.005
 Views+0.005
Neg logit contributions
nown-0.006
 smear-0.006
 undercover-0.005
 rival-0.005
below-0.005
Tokenastic
Token ID3477
Feature activation+5.02e-01

Pos logit contributions
 smear+0.246
nown+0.244
 undercover+0.223
 rival+0.212
 informants+0.207
Neg logit contributions
rek-0.169
ercise-0.146
iaries-0.143
agy-0.138
 launchers-0.137
Token personality
Token ID8806
Feature activation+1.54e-01

Pos logit contributions
rek+0.364
ercise+0.315
iaries+0.313
 launchers+0.309
 Views+0.308
Neg logit contributions
nown-0.442
 smear-0.433
 undercover-0.392
 rival-0.366
below-0.364
Token that
Token ID326
Feature activation+7.97e-02

Pos logit contributions
rek+0.117
ercise+0.101
iaries+0.100
 launchers+0.099
agy+0.099
Neg logit contributions
nown-0.132
 smear-0.130
 undercover-0.117
 rival-0.109
 informants-0.107
Token would
Token ID561
Feature activation-1.05e-01

Pos logit contributions
rek+0.061
ercise+0.052
iaries+0.052
 launchers+0.052
agy+0.051
Neg logit contributions
nown-0.068
 smear-0.066
 undercover-0.059
below-0.055
 rival-0.055
Token serve
Token ID4691
Feature activation-7.36e-02

Pos logit contributions
nown+0.082
 smear+0.080
 undercover+0.072
below+0.066
 informants+0.066
Neg logit contributions
rek-0.087
ercise-0.077
iaries-0.076
 launchers-0.075
agy-0.075
Token as
Token ID355
Feature activation-6.68e-02

Pos logit contributions
nown+0.058
 smear+0.058
 undercover+0.051
 rival+0.048
 informants+0.047
Neg logit contributions
rek-0.060
ercise-0.052
iaries-0.052
agy-0.051
 launchers-0.051
Tokenbased
Token ID3106
Feature activation-4.87e-03

Pos logit contributions
rek+0.004
ercise+0.004
iaries+0.004
agy+0.004
 launchers+0.004
Neg logit contributions
 smear-0.005
nown-0.005
 undercover-0.004
 rival-0.004
 informants-0.004
Token Anat
Token ID28880
Feature activation-1.41e-02

Pos logit contributions
 smear+0.004
nown+0.004
 undercover+0.004
 rival+0.003
 informants+0.003
Neg logit contributions
rek-0.004
ercise-0.003
iaries-0.003
agy-0.003
 launchers-0.003
Tokenol
Token ID349
Feature activation-4.34e-02

Pos logit contributions
 smear+0.011
nown+0.011
 undercover+0.010
 rival+0.009
 informants+0.009
Neg logit contributions
rek-0.012
ercise-0.010
iaries-0.010
agy-0.010
 launchers-0.010
Tokeniy
Token ID7745
Feature activation-5.04e-02

Pos logit contributions
 smear+0.032
nown+0.032
 undercover+0.029
 rival+0.027
 informants+0.026
Neg logit contributions
rek-0.037
ercise-0.033
iaries-0.033
agy-0.032
 launchers-0.032
Token D
Token ID360
Feature activation+7.72e-02

Pos logit contributions
 smear+0.044
nown+0.044
 undercover+0.040
 rival+0.038
 informants+0.037
Neg logit contributions
rek-0.036
ercise-0.032
iaries-0.031
agy-0.030
 launchers-0.030
Tokenerk
Token ID9587
Feature activation+5.00e-01

Pos logit contributions
rek+0.012
ercise+0.006
iaries+0.005
 Views+0.004
agy+0.004
Neg logit contributions
nown-0.110
 smear-0.110
 undercover-0.104
 rival-0.100
below-0.099
Tokenach
Token ID620
Feature activation+6.62e-03

Pos logit contributions
rek+0.376
ercise+0.332
iaries+0.325
agy+0.320
 launchers+0.316
Neg logit contributions
 smear-0.425
nown-0.422
 undercover-0.382
 rival-0.360
 informants-0.352
Token,
Token ID11
Feature activation+1.04e-02

Pos logit contributions
rek+0.005
ercise+0.004
iaries+0.004
agy+0.004
 launchers+0.004
Neg logit contributions
 smear-0.006
nown-0.006
 undercover-0.005
 rival-0.005
 informants-0.005
Token the
Token ID262
Feature activation+1.05e-02

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 launchers+0.007
Neg logit contributions
 smear-0.009
nown-0.009
 undercover-0.008
 rival-0.007
below-0.007
Token owner
Token ID4870
Feature activation+2.37e-02

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 launchers+0.007
Neg logit contributions
 smear-0.009
nown-0.009
 undercover-0.008
 rival-0.008
 informants-0.007
Token of
Token ID286
Feature activation-4.46e-03

Pos logit contributions
rek+0.019
ercise+0.017
iaries+0.016
agy+0.016
 launchers+0.016
Neg logit contributions
 smear-0.019
nown-0.019
 undercover-0.017
 rival-0.016
 informants-0.016
Token asked
Token ID1965
Feature activation+6.56e-02

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
 launchers+0.003
agy+0.003
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.003
 rival-0.003
below-0.003
Token to
Token ID284
Feature activation+1.04e-03

Pos logit contributions
rek+0.049
ercise+0.043
iaries+0.043
agy+0.042
 launchers+0.042
Neg logit contributions
 smear-0.055
nown-0.055
 undercover-0.050
 rival-0.047
below-0.046
Token speak
Token ID2740
Feature activation-2.60e-01

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
nown-0.001
 smear-0.001
 undercover-0.001
 rival-0.001
 informants-0.000
Token to
Token ID284
Feature activation-7.36e-04

Pos logit contributions
 smear+0.218
nown+0.217
 undercover+0.195
 rival+0.183
 informants+0.179
Neg logit contributions
rek-0.198
ercise-0.174
iaries-0.172
agy-0.168
 launchers-0.167
Token D
Token ID360
Feature activation+7.35e-02

Pos logit contributions
 smear+0.001
nown+0.001
 undercover+0.001
 rival+0.000
 informants+0.000
Neg logit contributions
rek-0.001
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Tokenerk
Token ID9587
Feature activation+4.98e-01

Pos logit contributions
rek+0.011
ercise+0.005
iaries+0.005
 Views+0.004
 launchers+0.003
Neg logit contributions
nown-0.105
 smear-0.105
 undercover-0.099
 rival-0.096
below-0.095
Tokenach
Token ID620
Feature activation+3.39e-03

Pos logit contributions
rek+0.374
ercise+0.329
iaries+0.321
agy+0.318
 launchers+0.312
Neg logit contributions
 smear-0.426
nown-0.422
 undercover-0.382
 rival-0.360
 informants-0.353
Token,
Token ID11
Feature activation+3.32e-03

Pos logit contributions
rek+0.003
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.003
nown-0.003
 undercover-0.003
 rival-0.002
 informants-0.002
Token and
Token ID290
Feature activation+2.75e-03

Pos logit contributions
rek+0.003
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.003
nown-0.003
 undercover-0.002
 rival-0.002
 informants-0.002
Token was
Token ID373
Feature activation-1.94e-03

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.002
nown-0.002
 undercover-0.002
 rival-0.002
 informants-0.002
Token put
Token ID1234
Feature activation-6.08e-02

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.001
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.002
ercise-0.001
iaries-0.001
 launchers-0.001
agy-0.001
Token were
Token ID547
Feature activation+8.12e-02

Pos logit contributions
 smear+0.025
nown+0.025
 undercover+0.023
 rival+0.021
 informants+0.021
Neg logit contributions
rek-0.021
ercise-0.018
iaries-0.018
agy-0.017
 launchers-0.017
Token given
Token ID1813
Feature activation-5.31e-02

Pos logit contributions
rek+0.060
ercise+0.052
iaries+0.051
agy+0.050
 launchers+0.050
Neg logit contributions
nown-0.070
 smear-0.070
 undercover-0.063
 rival-0.059
below-0.058
Token
Token ID564
Feature activation-2.70e-03

Pos logit contributions
 smear+0.045
nown+0.045
 undercover+0.041
 rival+0.038
 informants+0.037
Neg logit contributions
rek-0.040
ercise-0.035
iaries-0.035
agy-0.034
 launchers-0.034
Token
Token ID250
Feature activation+2.00e-02

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.002
 rival+0.002
 Blackwell+0.002
Neg logit contributions
rek-0.002
ercise-0.002
iaries-0.002
 Views-0.002
agy-0.002
Tokendr
Token ID7109
Feature activation+1.90e-01

Pos logit contributions
rek+0.016
ercise+0.014
iaries+0.014
agy+0.014
 launchers+0.013
Neg logit contributions
 smear-0.016
nown-0.016
 undercover-0.014
 rival-0.014
 informants-0.013
Tokenastic
Token ID3477
Feature activation+4.98e-01

Pos logit contributions
rek+0.110
ercise+0.092
iaries+0.090
agy+0.088
 launchers+0.086
Neg logit contributions
 smear-0.195
nown-0.195
 undercover-0.179
 rival-0.170
 informants-0.167
Token dem
Token ID1357
Feature activation-1.19e-02

Pos logit contributions
rek+0.384
ercise+0.337
iaries+0.334
agy+0.326
 launchers+0.325
Neg logit contributions
 smear-0.413
nown-0.412
 undercover-0.370
 rival-0.348
 informants-0.340
Tokenotions
Token ID36083
Feature activation+1.45e-01

Pos logit contributions
 smear+0.012
nown+0.012
 undercover+0.011
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.007
ercise-0.006
iaries-0.006
agy-0.006
 launchers-0.006
Token
Token ID447
Feature activation-7.36e-03

Pos logit contributions
rek+0.113
ercise+0.099
iaries+0.098
agy+0.096
 launchers+0.096
Neg logit contributions
 smear-0.119
nown-0.119
 undercover-0.107
 rival-0.100
 informants-0.098
Token
Token ID251
Feature activation-3.41e-02

Pos logit contributions
 smear+0.006
nown+0.006
 undercover+0.005
 rival+0.005
 informants+0.005
Neg logit contributions
rek-0.006
ercise-0.006
iaries-0.005
agy-0.005
 launchers-0.005
Token for
Token ID329
Feature activation-1.10e-02

Pos logit contributions
 smear+0.028
nown+0.028
 undercover+0.025
 rival+0.024
 informants+0.023
Neg logit contributions
rek-0.026
ercise-0.023
iaries-0.023
agy-0.022
 launchers-0.022
Token a
Token ID257
Feature activation+2.14e-03

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 launchers+0.007
Neg logit contributions
nown-0.008
 smear-0.008
 undercover-0.007
 rival-0.007
below-0.007
Token skin
Token ID4168
Feature activation-9.38e-02

Pos logit contributions
rek+0.002
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
 smear-0.002
nown-0.002
 undercover-0.002
 rival-0.001
 informants-0.001
Token condition
Token ID4006
Feature activation+1.00e-01

Pos logit contributions
nown+0.075
 smear+0.075
 undercover+0.067
 rival+0.063
 informants+0.061
Neg logit contributions
rek-0.075
ercise-0.066
iaries-0.065
agy-0.064
 launchers-0.064
Token,
Token ID11
Feature activation+7.49e-03

Pos logit contributions
rek+0.076
ercise+0.067
iaries+0.066
agy+0.064
 launchers+0.064
Neg logit contributions
nown-0.085
 smear-0.085
 undercover-0.076
 rival-0.071
 informants-0.070
Token an
Token ID281
Feature activation+1.43e-02

Pos logit contributions
rek+0.006
ercise+0.005
iaries+0.005
agy+0.005
 launchers+0.005
Neg logit contributions
nown-0.006
 smear-0.006
 undercover-0.006
 rival-0.005
 informants-0.005
Token autos
Token ID44619
Feature activation+4.97e-01

Pos logit contributions
rek+0.011
ercise+0.010
iaries+0.010
agy+0.010
 launchers+0.010
Neg logit contributions
 smear-0.011
nown-0.011
 undercover-0.010
 rival-0.010
below-0.009
Tokenomal
Token ID18048
Feature activation-1.80e-01

Pos logit contributions
rek+0.519
ercise+0.474
iaries+0.468
agy+0.462
 launchers+0.459
Neg logit contributions
 smear-0.278
nown-0.277
 undercover-0.236
 rival-0.213
 informants-0.207
Token dominant
Token ID11410
Feature activation+1.55e-01

Pos logit contributions
nown+0.173
 smear+0.172
 undercover+0.157
 rival+0.149
 informants+0.147
Neg logit contributions
rek-0.114
ercise-0.098
iaries-0.096
agy-0.094
 launchers-0.094
Token palm
Token ID18057
Feature activation-3.92e-02

Pos logit contributions
rek+0.105
ercise+0.091
iaries+0.090
agy+0.088
 launchers+0.087
Neg logit contributions
 smear-0.143
nown-0.143
 undercover-0.130
 rival-0.122
 informants-0.120
Tokenopl
Token ID20106
Feature activation+1.46e-01

Pos logit contributions
 smear+0.033
nown+0.033
 undercover+0.030
 rival+0.028
 informants+0.027
Neg logit contributions
rek-0.030
ercise-0.026
iaries-0.026
agy-0.025
 launchers-0.025
Tokenant
Token ID415
Feature activation-5.46e-02

Pos logit contributions
rek+0.075
ercise+0.062
iaries+0.060
agy+0.059
 launchers+0.057
Neg logit contributions
 smear-0.159
nown-0.159
 undercover-0.147
 rival-0.140
 informants-0.138
Token an
Token ID281
Feature activation+4.85e-03

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
 launchers+0.002
 Views+0.002
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.002
 informants-0.002
Token already
Token ID1541
Feature activation-1.54e-01

Pos logit contributions
rek+0.004
ercise+0.004
iaries+0.003
 Views+0.003
 launchers+0.003
Neg logit contributions
 smear-0.004
nown-0.004
 undercover-0.003
 rival-0.003
 informants-0.003
Token-
Token ID12
Feature activation+1.57e-03

Pos logit contributions
nown+0.129
 smear+0.128
 undercover+0.115
 rival+0.108
 informants+0.106
Neg logit contributions
rek-0.118
ercise-0.104
iaries-0.103
agy-0.100
 launchers-0.100
Tokenf
Token ID69
Feature activation+2.20e-01

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
 smear-0.001
nown-0.001
 undercover-0.001
 rival-0.001
 informants-0.001
Tokenant
Token ID415
Feature activation-7.70e-02

Pos logit contributions
rek+0.175
ercise+0.154
iaries+0.152
agy+0.149
 launchers+0.147
Neg logit contributions
 smear-0.178
nown-0.178
 undercover-0.160
 rival-0.149
 informants-0.147
Tokenastic
Token ID3477
Feature activation+4.96e-01

Pos logit contributions
 smear+0.110
nown+0.109
 undercover+0.103
 rival+0.099
 informants+0.098
Neg logit contributions
rek-0.014
ercise-0.007
iaries-0.006
agy-0.005
 launchers-0.005
Token creation
Token ID6282
Feature activation+2.16e-01

Pos logit contributions
rek+0.345
ercise+0.301
iaries+0.296
 Views+0.290
 launchers+0.288
Neg logit contributions
nown-0.449
 smear-0.445
 undercover-0.403
 rival-0.379
 informants-0.377
Token.
Token ID13
Feature activation-1.97e-02

Pos logit contributions
rek+0.165
ercise+0.145
iaries+0.143
 launchers+0.140
agy+0.140
Neg logit contributions
nown-0.181
 smear-0.181
 undercover-0.163
 rival-0.152
 informants-0.150
Token
Token ID198
Feature activation-2.95e-04

Pos logit contributions
nown+0.016
 smear+0.016
 undercover+0.015
 rival+0.014
 informants+0.014
Neg logit contributions
rek-0.015
ercise-0.013
iaries-0.013
 Views-0.013
agy-0.013
Token
Token ID198
Feature activation-3.11e-03

Pos logit contributions
nown+0.000
 smear+0.000
 undercover+0.000
 rival+0.000
 informants+0.000
Neg logit contributions
rek-0.000
ercise-0.000
iaries-0.000
agy-0.000
 Views-0.000
TokenScott
Token ID19040
Feature activation-9.66e-02

Pos logit contributions
 smear+0.003
nown+0.003
 undercover+0.002
 rival+0.002
 informants+0.002
Neg logit contributions
rek-0.002
ercise-0.002
iaries-0.002
agy-0.002
 launchers-0.002
Token being
Token ID852
Feature activation+4.81e-02

Pos logit contributions
rek+0.011
ercise+0.009
iaries+0.009
agy+0.009
 launchers+0.009
Neg logit contributions
nown-0.013
 smear-0.013
 undercover-0.012
 rival-0.011
below-0.011
Token fat
Token ID3735
Feature activation+2.23e-01

Pos logit contributions
rek+0.034
ercise+0.030
iaries+0.030
agy+0.029
 launchers+0.029
Neg logit contributions
nown-0.043
 smear-0.043
 undercover-0.038
 rival-0.036
below-0.036
Token,
Token ID11
Feature activation+1.40e-02

Pos logit contributions
rek+0.168
ercise+0.148
iaries+0.146
agy+0.143
 launchers+0.142
Neg logit contributions
 smear-0.189
nown-0.188
 undercover-0.170
 rival-0.159
 informants-0.156
Token not
Token ID407
Feature activation-1.37e-01

Pos logit contributions
rek+0.011
ercise+0.009
iaries+0.009
agy+0.009
 launchers+0.009
Neg logit contributions
 smear-0.012
nown-0.012
 undercover-0.011
 rival-0.010
 informants-0.010
Token all
Token ID477
Feature activation-1.47e-01

Pos logit contributions
 smear+0.110
nown+0.109
 undercover+0.098
 rival+0.092
 informants+0.090
Neg logit contributions
rek-0.109
ercise-0.096
iaries-0.096
agy-0.093
 launchers-0.093
Token 53
Token ID7192
Feature activation+4.93e-01

Pos logit contributions
 smear+0.124
nown+0.124
 undercover+0.112
 rival+0.105
 informants+0.103
Neg logit contributions
rek-0.111
ercise-0.098
iaries-0.097
agy-0.094
 launchers-0.094
Token Euro
Token ID1898
Feature activation-9.26e-02

Pos logit contributions
rek+0.359
ercise+0.313
iaries+0.311
 launchers+0.302
agy+0.302
Neg logit contributions
nown-0.429
 smear-0.429
 undercover-0.387
 rival-0.363
below-0.355
Token-
Token ID12
Feature activation+1.06e-02

Pos logit contributions
 smear+0.079
nown+0.079
 undercover+0.071
 rival+0.066
 Blackwell+0.065
Neg logit contributions
rek-0.070
ercise-0.061
iaries-0.060
agy-0.059
 Views-0.059
Tokenregion
Token ID36996
Feature activation-1.13e-01

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 launchers+0.007
Neg logit contributions
 smear-0.009
nown-0.009
 undercover-0.008
 rival-0.008
 informants-0.007
Token countries
Token ID2678
Feature activation+2.01e-01

Pos logit contributions
nown+0.110
 smear+0.109
 undercover+0.099
 rival+0.094
below+0.092
Neg logit contributions
rek-0.072
ercise-0.061
iaries-0.061
 launchers-0.059
agy-0.059
Token are
Token ID389
Feature activation+1.54e-03

Pos logit contributions
rek+0.161
ercise+0.142
iaries+0.141
 launchers+0.137
agy+0.137
Neg logit contributions
nown-0.162
 smear-0.161
 undercover-0.144
 rival-0.133
 Blackwell-0.132
Token report
Token ID989
Feature activation+9.09e-02

Pos logit contributions
nown+0.175
 smear+0.172
 undercover+0.156
below+0.148
 rival+0.148
Neg logit contributions
rek-0.130
ercise-0.113
iaries-0.111
 launchers-0.108
 Views-0.108
Token in
Token ID287
Feature activation+1.81e-02

Pos logit contributions
rek+0.068
ercise+0.060
iaries+0.059
agy+0.058
 launchers+0.058
Neg logit contributions
nown-0.077
 smear-0.076
 undercover-0.068
 rival-0.064
below-0.063
Token an
Token ID281
Feature activation+9.14e-03

Pos logit contributions
rek+0.013
ercise+0.011
iaries+0.011
 launchers+0.011
 Views+0.011
Neg logit contributions
nown-0.016
 smear-0.016
 undercover-0.014
 rival-0.014
below-0.013
Token effort
Token ID3626
Feature activation-8.25e-02

Pos logit contributions
rek+0.007
ercise+0.006
iaries+0.006
 launchers+0.006
agy+0.006
Neg logit contributions
nown-0.007
 smear-0.007
 undercover-0.006
 rival-0.006
below-0.006
Token to
Token ID284
Feature activation+5.76e-03

Pos logit contributions
nown+0.073
 smear+0.072
 undercover+0.065
 rival+0.061
below+0.061
Neg logit contributions
rek-0.059
ercise-0.051
iaries-0.050
agy-0.050
 launchers-0.049
Token smear
Token ID35180
Feature activation-6.68e-01

Pos logit contributions
rek+0.005
ercise+0.004
iaries+0.004
 launchers+0.004
agy+0.004
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.004
below-0.003
 rival-0.003
Token the
Token ID262
Feature activation+2.83e-03

Pos logit contributions
nown+0.545
 smear+0.537
 undercover+0.477
 rival+0.445
below+0.444
Neg logit contributions
rek-0.523
ercise-0.464
iaries-0.457
 Views-0.450
 launchers-0.450
Token fired
Token ID6294
Feature activation-3.41e-03

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
 launchers+0.002
 Views+0.002
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.002
below-0.002
Token worker
Token ID8383
Feature activation+1.17e-02

Pos logit contributions
nown+0.003
 smear+0.003
 undercover+0.002
 rival+0.002
below+0.002
Neg logit contributions
rek-0.003
ercise-0.003
iaries-0.002
 launchers-0.002
agy-0.002
Token and
Token ID290
Feature activation+4.34e-03

Pos logit contributions
rek+0.009
ercise+0.008
iaries+0.008
agy+0.008
 launchers+0.007
Neg logit contributions
nown-0.010
 smear-0.010
 undercover-0.009
 rival-0.008
below-0.008
Token create
Token ID2251
Feature activation+3.93e-02

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
 launchers+0.003
agy+0.003
Neg logit contributions
nown-0.004
 smear-0.003
 undercover-0.003
 rival-0.003
below-0.003
Token when
Token ID618
Feature activation+9.68e-02

Pos logit contributions
rek+0.093
ercise+0.081
iaries+0.080
 launchers+0.079
agy+0.079
Neg logit contributions
nown-0.101
 smear-0.100
 undercover-0.089
 rival-0.084
below-0.083
Token I
Token ID314
Feature activation-6.08e-03

Pos logit contributions
rek+0.073
ercise+0.064
iaries+0.063
 launchers+0.062
 Views+0.061
Neg logit contributions
nown-0.082
 smear-0.081
 undercover-0.072
 rival-0.068
below-0.068
Token do
Token ID466
Feature activation+1.28e-01

Pos logit contributions
nown+0.005
 smear+0.005
 undercover+0.004
 rival+0.004
below+0.004
Neg logit contributions
rek-0.005
ercise-0.004
iaries-0.004
agy-0.004
 launchers-0.004
Token a
Token ID257
Feature activation-1.24e-02

Pos logit contributions
rek+0.099
ercise+0.088
iaries+0.088
 launchers+0.085
agy+0.085
Neg logit contributions
nown-0.106
 smear-0.103
 undercover-0.091
 rival-0.087
below-0.087
Token pap
Token ID20461
Feature activation+8.19e-02

Pos logit contributions
nown+0.010
 smear+0.010
 undercover+0.009
 rival+0.008
 informants+0.008
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.009
 Views-0.008
 launchers-0.008
Token smear
Token ID35180
Feature activation-6.66e-01

Pos logit contributions
rek+0.096
ercise+0.089
iaries+0.088
agy+0.087
 launchers+0.086
Neg logit contributions
nown-0.035
 smear-0.034
 undercover-0.028
 rival-0.024
 informants-0.023
Token and
Token ID290
Feature activation+5.58e-03

Pos logit contributions
nown+0.562
 smear+0.550
 undercover+0.496
 rival+0.471
 Blackwell+0.462
Neg logit contributions
rek-0.503
ercise-0.445
iaries-0.435
 launchers-0.428
agy-0.425
Token Medicare
Token ID13771
Feature activation-1.37e-02

Pos logit contributions
rek+0.004
ercise+0.004
iaries+0.004
 launchers+0.004
agy+0.004
Neg logit contributions
nown-0.005
 smear-0.004
 undercover-0.004
 rival-0.004
below-0.004
Token or
Token ID393
Feature activation+1.97e-01

Pos logit contributions
nown+0.012
 smear+0.011
 undercover+0.010
 rival+0.010
below+0.009
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.009
 launchers-0.009
 Views-0.009
Token private
Token ID2839
Feature activation+6.86e-02

Pos logit contributions
rek+0.124
ercise+0.106
iaries+0.104
agy+0.101
 launchers+0.101
Neg logit contributions
 smear-0.192
nown-0.191
 undercover-0.175
 rival-0.166
 informants-0.163
Token insurance
Token ID5096
Feature activation+6.75e-03

Pos logit contributions
rek+0.046
ercise+0.040
iaries+0.039
 launchers+0.038
agy+0.038
Neg logit contributions
nown-0.064
 smear-0.064
 undercover-0.058
 rival-0.055
below-0.054
Token,
Token ID11
Feature activation+8.54e-03

Pos logit contributions
nown+0.100
 smear+0.100
 undercover+0.089
 rival+0.084
 informants+0.082
Neg logit contributions
rek-0.088
ercise-0.077
iaries-0.076
 launchers-0.075
agy-0.075
Token and
Token ID290
Feature activation+4.60e-03

Pos logit contributions
rek+0.007
ercise+0.006
iaries+0.006
 launchers+0.006
agy+0.006
Neg logit contributions
nown-0.007
 smear-0.007
 undercover-0.006
 rival-0.006
below-0.006
Token so
Token ID523
Feature activation-1.08e-01

Pos logit contributions
rek+0.004
ercise+0.003
iaries+0.003
 Views+0.003
 launchers+0.003
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.003
 rival-0.003
below-0.003
Token is
Token ID318
Feature activation-1.50e-02

Pos logit contributions
nown+0.091
 smear+0.090
 undercover+0.081
 rival+0.076
 informants+0.075
Neg logit contributions
rek-0.082
ercise-0.072
iaries-0.071
agy-0.070
 launchers-0.069
Token this
Token ID428
Feature activation-7.53e-02

Pos logit contributions
nown+0.012
 smear+0.012
 undercover+0.011
 rival+0.010
below+0.010
Neg logit contributions
rek-0.011
ercise-0.010
iaries-0.010
 Views-0.010
agy-0.010
Token smear
Token ID35180
Feature activation-6.65e-01

Pos logit contributions
nown+0.060
 smear+0.059
 undercover+0.053
 rival+0.049
below+0.049
Neg logit contributions
rek-0.061
ercise-0.054
iaries-0.053
 launchers-0.052
agy-0.052
Token campaign
Token ID1923
Feature activation-1.91e-01

Pos logit contributions
nown+0.426
 smear+0.417
 undercover+0.366
 rival+0.335
 informants+0.329
Neg logit contributions
rek-0.638
ercise-0.579
iaries-0.570
 launchers-0.564
agy-0.561
Token.
Token ID13
Feature activation-1.40e-02

Pos logit contributions
nown+0.159
 smear+0.157
 undercover+0.141
 rival+0.132
 informants+0.131
Neg logit contributions
rek-0.146
ercise-0.129
iaries-0.126
 launchers-0.125
agy-0.124
Token
Token ID198
Feature activation+9.10e-04

Pos logit contributions
nown+0.012
 smear+0.012
 undercover+0.011
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.010
ercise-0.009
 Views-0.009
iaries-0.009
agy-0.009
Token
Token ID198
Feature activation-7.84e-04

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 Views+0.001
Neg logit contributions
nown-0.001
 smear-0.001
 undercover-0.001
 rival-0.001
 informants-0.001
TokenNOT
Token ID11929
Feature activation-2.66e-01

Pos logit contributions
 smear+0.001
nown+0.001
 undercover+0.001
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.001
ercise-0.001
iaries-0.001
agy-0.001
 Views-0.001
Token,
Token ID11
Feature activation+1.20e-02

Pos logit contributions
rek+0.053
ercise+0.048
iaries+0.048
 launchers+0.047
agy+0.047
Neg logit contributions
nown-0.041
 smear-0.041
 undercover-0.036
 rival-0.033
below-0.032
Token saying
Token ID2282
Feature activation+8.93e-02

Pos logit contributions
rek+0.009
ercise+0.008
iaries+0.008
agy+0.008
 launchers+0.008
Neg logit contributions
 smear-0.010
nown-0.010
 undercover-0.009
 rival-0.009
 informants-0.008
Token it
Token ID340
Feature activation-9.92e-02

Pos logit contributions
rek+0.071
ercise+0.063
iaries+0.062
agy+0.061
 launchers+0.061
Neg logit contributions
nown-0.072
 smear-0.071
 undercover-0.064
 rival-0.060
below-0.058
Token is
Token ID318
Feature activation-7.30e-03

Pos logit contributions
nown+0.084
 smear+0.083
 undercover+0.075
 rival+0.070
below+0.069
Neg logit contributions
rek-0.075
ercise-0.065
iaries-0.065
 launchers-0.064
agy-0.063
Token a
Token ID257
Feature activation-1.13e-02

Pos logit contributions
nown+0.006
 smear+0.006
 undercover+0.005
 rival+0.005
below+0.005
Neg logit contributions
rek-0.006
ercise-0.005
iaries-0.005
agy-0.005
 launchers-0.005
Token smear
Token ID35180
Feature activation-6.61e-01

Pos logit contributions
nown+0.008
 smear+0.008
 undercover+0.007
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.009
agy-0.009
 launchers-0.009
Token campaign
Token ID1923
Feature activation-1.94e-01

Pos logit contributions
nown+0.470
 smear+0.458
 undercover+0.409
 rival+0.377
below+0.373
Neg logit contributions
rek-0.586
ercise-0.529
iaries-0.519
 launchers-0.513
agy-0.510
Token against
Token ID1028
Feature activation-2.25e-01

Pos logit contributions
nown+0.152
 smear+0.148
 undercover+0.132
 rival+0.123
below+0.123
Neg logit contributions
rek-0.159
ercise-0.141
iaries-0.139
 launchers-0.138
agy-0.137
Token his
Token ID465
Feature activation-1.23e-02

Pos logit contributions
nown+0.177
 smear+0.174
 undercover+0.155
below+0.144
 rival+0.143
Neg logit contributions
rek-0.181
ercise-0.161
iaries-0.160
 launchers-0.157
 Views-0.157
Token website
Token ID3052
Feature activation+8.43e-02

Pos logit contributions
nown+0.009
 smear+0.009
 undercover+0.008
 rival+0.008
below+0.007
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.009
 launchers-0.009
agy-0.009
Token [
Token ID685
Feature activation-7.43e-02

Pos logit contributions
rek+0.064
ercise+0.056
iaries+0.055
 launchers+0.054
 Views+0.054
Neg logit contributions
nown-0.071
 smear-0.070
 undercover-0.063
 rival-0.059
below-0.058
Token co
Token ID763
Feature activation-1.93e-01

Pos logit contributions
nown+0.024
 smear+0.024
 undercover+0.021
 rival+0.019
below+0.019
Neg logit contributions
rek-0.023
ercise-0.021
iaries-0.020
 launchers-0.020
 Views-0.020
Token-
Token ID12
Feature activation+9.86e-04

Pos logit contributions
 smear+0.162
nown+0.162
 undercover+0.145
 rival+0.137
 informants+0.133
Neg logit contributions
rek-0.146
ercise-0.128
iaries-0.127
agy-0.124
 launchers-0.124
Tokenworker
Token ID28816
Feature activation-1.82e-01

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
 smear-0.001
nown-0.001
 undercover-0.001
 rival-0.000
 Blackwell-0.000
Token during
Token ID1141
Feature activation+6.31e-02

Pos logit contributions
nown+0.155
 smear+0.155
 undercover+0.137
 rival+0.129
below+0.128
Neg logit contributions
rek-0.136
ercise-0.119
iaries-0.118
agy-0.116
 launchers-0.115
Token an
Token ID281
Feature activation+1.75e-03

Pos logit contributions
rek+0.046
ercise+0.041
iaries+0.040
 launchers+0.040
 Views+0.039
Neg logit contributions
nown-0.054
 smear-0.054
 undercover-0.047
 rival-0.045
below-0.045
Token undercover
Token ID23557
Feature activation-6.02e-01

Pos logit contributions
rek+0.002
ercise+0.001
iaries+0.001
 launchers+0.001
 Views+0.001
Neg logit contributions
nown-0.001
 smear-0.001
 undercover-0.001
 rival-0.001
below-0.001
Token operation
Token ID4905
Feature activation-5.35e-02

Pos logit contributions
nown+0.450
 smear+0.441
 undercover+0.382
 rival+0.361
below+0.360
Neg logit contributions
rek-0.513
ercise-0.464
iaries-0.453
agy-0.446
 launchers-0.445
Token,
Token ID11
Feature activation+4.78e-03

Pos logit contributions
 smear+0.045
nown+0.045
 undercover+0.040
 rival+0.038
below+0.037
Neg logit contributions
rek-0.040
ercise-0.035
iaries-0.035
agy-0.034
 launchers-0.034
Token according
Token ID1864
Feature activation-8.65e-02

Pos logit contributions
rek+0.004
ercise+0.003
iaries+0.003
agy+0.003
 Views+0.003
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.003
 rival-0.003
below-0.003
Token to
Token ID284
Feature activation+2.16e-03

Pos logit contributions
nown+0.077
 smear+0.077
 undercover+0.069
 rival+0.065
 informants+0.064
Neg logit contributions
rek-0.062
ercise-0.053
iaries-0.053
agy-0.052
 Views-0.052
Token the
Token ID262
Feature activation+1.97e-03

Pos logit contributions
rek+0.002
ercise+0.001
iaries+0.001
 launchers+0.001
 Views+0.001
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.001
below-0.001
Token when
Token ID618
Feature activation+1.04e-01

Pos logit contributions
 smear+0.026
nown+0.026
 undercover+0.023
 rival+0.022
below+0.022
Neg logit contributions
rek-0.021
ercise-0.018
iaries-0.018
 Views-0.018
agy-0.017
Token he
Token ID339
Feature activation-4.82e-02

Pos logit contributions
rek+0.084
ercise+0.074
iaries+0.074
 Views+0.073
 launchers+0.073
Neg logit contributions
nown-0.081
 smear-0.081
 undercover-0.071
 rival-0.067
below-0.066
Token was
Token ID373
Feature activation-2.03e-05

Pos logit contributions
nown+0.039
 smear+0.039
 undercover+0.034
 rival+0.032
below+0.032
Neg logit contributions
rek-0.038
ercise-0.033
iaries-0.033
agy-0.032
 launchers-0.032
Token arrested
Token ID5169
Feature activation-1.40e-01

Pos logit contributions
nown+0.000
 smear+0.000
 undercover+0.000
 rival+0.000
below+0.000
Neg logit contributions
rek-0.000
ercise-0.000
iaries-0.000
 launchers-0.000
agy-0.000
Token by
Token ID416
Feature activation+8.64e-02

Pos logit contributions
 smear+0.122
nown+0.122
 undercover+0.109
 rival+0.103
 informants+0.101
Neg logit contributions
rek-0.102
ercise-0.089
iaries-0.088
agy-0.086
 launchers-0.085
Token undercover
Token ID23557
Feature activation-5.99e-01

Pos logit contributions
rek+0.071
ercise+0.063
iaries+0.063
 launchers+0.062
 Views+0.061
Neg logit contributions
nown-0.067
 smear-0.067
 undercover-0.058
below-0.054
 rival-0.054
Token police
Token ID1644
Feature activation-2.02e-01

Pos logit contributions
nown+0.428
 smear+0.425
 undercover+0.364
 rival+0.341
below+0.341
Neg logit contributions
rek-0.530
ercise-0.478
iaries-0.473
 launchers-0.464
 Views-0.464
Token officers
Token ID3790
Feature activation-8.24e-02

Pos logit contributions
nown+0.164
 smear+0.164
 undercover+0.144
 rival+0.136
below+0.133
Neg logit contributions
rek-0.159
ercise-0.140
iaries-0.139
agy-0.136
 launchers-0.136
Token in
Token ID287
Feature activation+1.65e-02

Pos logit contributions
 smear+0.070
nown+0.070
 undercover+0.062
 rival+0.059
below+0.058
Neg logit contributions
rek-0.062
ercise-0.054
iaries-0.053
agy-0.052
 launchers-0.052
Token November
Token ID3389
Feature activation+6.03e-03

Pos logit contributions
rek+0.012
ercise+0.010
iaries+0.010
 launchers+0.010
 Views+0.010
Neg logit contributions
nown-0.014
 smear-0.014
 undercover-0.013
 rival-0.012
below-0.012
Token 2008
Token ID3648
Feature activation-1.43e-01

Pos logit contributions
rek+0.005
ercise+0.005
iaries+0.005
 Views+0.005
 launchers+0.005
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.004
 rival-0.003
 informants-0.003
Token by
Token ID416
Feature activation+8.03e-02

Pos logit contributions
rek+0.072
ercise+0.063
iaries+0.062
agy+0.061
 launchers+0.061
Neg logit contributions
 smear-0.078
nown-0.078
 undercover-0.070
 rival-0.066
 informants-0.065
Token Jo
Token ID5302
Feature activation+6.36e-02

Pos logit contributions
rek+0.062
ercise+0.054
iaries+0.054
agy+0.053
 launchers+0.052
Neg logit contributions
nown-0.067
 smear-0.066
 undercover-0.059
 rival-0.056
 informants-0.055
Token Roy
Token ID9817
Feature activation-7.95e-02

Pos logit contributions
rek+0.049
ercise+0.043
iaries+0.043
agy+0.042
 launchers+0.042
Neg logit contributions
nown-0.052
 smear-0.052
 undercover-0.047
 rival-0.044
 informants-0.043
Tokenle
Token ID293
Feature activation-1.39e-01

Pos logit contributions
 smear+0.064
nown+0.064
 undercover+0.057
 rival+0.053
 informants+0.052
Neg logit contributions
rek-0.064
ercise-0.056
iaries-0.055
agy-0.054
 launchers-0.054
Token (
Token ID357
Feature activation-1.08e-01

Pos logit contributions
 smear+0.115
nown+0.115
 undercover+0.103
 rival+0.097
 informants+0.095
Neg logit contributions
rek-0.107
ercise-0.094
iaries-0.092
agy-0.091
 Views-0.090
Tokenbelow
Token ID35993
Feature activation-5.70e-01

Pos logit contributions
 smear+0.084
nown+0.083
 undercover+0.074
 rival+0.069
 informants+0.068
Neg logit contributions
rek-0.089
ercise-0.079
iaries-0.078
agy-0.077
 launchers-0.076
Token),
Token ID828
Feature activation+3.21e-02

Pos logit contributions
 smear+0.451
nown+0.450
 undercover+0.402
 rival+0.376
 informants+0.367
Neg logit contributions
rek-0.461
ercise-0.409
iaries-0.404
agy-0.396
 launchers-0.395
Token the
Token ID262
Feature activation+1.34e-03

Pos logit contributions
rek+0.025
ercise+0.022
iaries+0.021
agy+0.021
 Views+0.021
Neg logit contributions
 smear-0.027
nown-0.027
 undercover-0.024
 rival-0.023
 informants-0.022
Token sk
Token ID1341
Feature activation+1.83e-01

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
nown-0.001
 smear-0.001
 undercover-0.001
 rival-0.001
 informants-0.001
Tokenipper
Token ID14710
Feature activation+7.87e-02

Pos logit contributions
rek+0.122
ercise+0.104
iaries+0.103
agy+0.100
 launchers+0.099
Neg logit contributions
 smear-0.172
nown-0.171
 undercover-0.156
 rival-0.148
 informants-0.145
Token and
Token ID290
Feature activation+4.21e-03

Pos logit contributions
rek+0.060
ercise+0.053
iaries+0.052
agy+0.051
 launchers+0.051
Neg logit contributions
 smear-0.066
nown-0.065
 undercover-0.058
 rival-0.055
 informants-0.054
Token important
Token ID1593
Feature activation+5.12e-02

Pos logit contributions
nown+0.037
 smear+0.037
 undercover+0.033
 rival+0.031
 informants+0.031
Neg logit contributions
rek-0.032
ercise-0.028
iaries-0.028
 launchers-0.027
agy-0.027
Token victories
Token ID19017
Feature activation-1.33e-01

Pos logit contributions
rek+0.045
ercise+0.040
iaries+0.040
 launchers+0.039
agy+0.039
Neg logit contributions
nown-0.037
 smear-0.037
 undercover-0.032
 rival-0.030
below-0.029
Token at
Token ID379
Feature activation-3.56e-02

Pos logit contributions
nown+0.074
 smear+0.073
 undercover+0.060
 informants+0.054
 rival+0.053
Neg logit contributions
rek-0.140
ercise-0.127
iaries-0.125
agy-0.125
 launchers-0.124
Token West
Token ID2688
Feature activation-2.82e-01

Pos logit contributions
nown+0.026
 smear+0.026
 undercover+0.022
 informants+0.021
 rival+0.020
Neg logit contributions
rek-0.031
ercise-0.028
iaries-0.027
 Views-0.027
 launchers-0.027
Token Brom
Token ID31455
Feature activation-3.52e-01

Pos logit contributions
nown+0.166
 smear+0.165
 undercover+0.141
 informants+0.126
 rival+0.121
Neg logit contributions
rek-0.292
ercise-0.263
iaries-0.259
 Views-0.258
agy-0.255
Tokenwich
Token ID11451
Feature activation-5.66e-01

Pos logit contributions
nown+0.205
 smear+0.205
 undercover+0.172
 informants+0.155
 rival+0.153
Neg logit contributions
rek-0.359
ercise-0.329
iaries-0.321
agy-0.319
 launchers-0.318
Token Albion
Token ID47995
Feature activation-3.03e-01

Pos logit contributions
nown+0.304
 smear+0.297
 undercover+0.246
 informants+0.218
 rival+0.212
Neg logit contributions
rek-0.614
ercise-0.562
 launchers-0.546
 Views-0.545
iaries-0.541
Token and
Token ID290
Feature activation+1.47e-02

Pos logit contributions
nown+0.266
 smear+0.265
 undercover+0.237
 informants+0.223
 rival+0.220
Neg logit contributions
rek-0.221
ercise-0.193
iaries-0.186
 launchers-0.185
 Views-0.185
Token Stoke
Token ID36178
Feature activation-1.67e-01

Pos logit contributions
rek+0.013
ercise+0.012
iaries+0.012
 Views+0.012
 launchers+0.012
Neg logit contributions
nown-0.010
 smear-0.010
 undercover-0.009
 informants-0.008
 rival-0.008
Token City
Token ID2254
Feature activation-1.96e-01

Pos logit contributions
nown+0.102
 smear+0.102
 undercover+0.087
 rival+0.078
 informants+0.078
Neg logit contributions
rek-0.165
ercise-0.150
iaries-0.147
 launchers-0.146
 Views-0.146
Token achieved
Token ID8793
Feature activation-2.01e-01

Pos logit contributions
nown+0.170
 smear+0.170
 undercover+0.151
 informants+0.141
 rival+0.140
Neg logit contributions
rek-0.144
ercise-0.126
iaries-0.122
 launchers-0.122
 Views-0.121
Token even
Token ID772
Feature activation-1.66e-02

Pos logit contributions
rek+0.007
ercise+0.006
iaries+0.006
 launchers+0.006
agy+0.006
Neg logit contributions
nown-0.007
 smear-0.007
 undercover-0.007
 rival-0.006
 informants-0.006
Token as
Token ID355
Feature activation-6.84e-02

Pos logit contributions
 smear+0.016
nown+0.016
 undercover+0.015
 rival+0.014
 informants+0.014
Neg logit contributions
rek-0.011
ercise-0.009
iaries-0.009
agy-0.009
 launchers-0.009
Token its
Token ID663
Feature activation+2.26e-02

Pos logit contributions
 smear+0.054
nown+0.054
 undercover+0.048
 rival+0.045
 informants+0.044
Neg logit contributions
rek-0.056
ercise-0.049
iaries-0.049
agy-0.048
 launchers-0.048
Token bottom
Token ID4220
Feature activation-1.06e-01

Pos logit contributions
rek+0.019
ercise+0.016
iaries+0.016
 launchers+0.016
agy+0.016
Neg logit contributions
nown-0.018
 smear-0.017
 undercover-0.015
 rival-0.014
 Blackwell-0.014
Token (
Token ID357
Feature activation-1.06e-01

Pos logit contributions
nown+0.083
 smear+0.083
 undercover+0.074
 rival+0.069
 informants+0.068
Neg logit contributions
rek-0.087
ercise-0.077
iaries-0.076
agy-0.074
 launchers-0.074
Tokenbelow
Token ID35993
Feature activation-5.66e-01

Pos logit contributions
 smear+0.026
nown+0.025
 undercover+0.017
 rival+0.011
 informants+0.010
Neg logit contributions
rek-0.144
ercise-0.134
iaries-0.133
agy-0.132
 launchers-0.131
Token water
Token ID1660
Feature activation-1.37e-02

Pos logit contributions
nown+0.439
 smear+0.438
 undercover+0.390
 rival+0.364
 informants+0.357
Neg logit contributions
rek-0.466
ercise-0.414
iaries-0.409
agy-0.401
 launchers-0.400
Token)
Token ID8
Feature activation-1.22e-01

Pos logit contributions
 smear+0.010
nown+0.010
 undercover+0.009
 rival+0.008
 informants+0.008
Neg logit contributions
rek-0.012
ercise-0.011
iaries-0.011
agy-0.011
 launchers-0.011
Token rises
Token ID16736
Feature activation-1.60e-02

Pos logit contributions
nown+0.103
 smear+0.103
 undercover+0.093
 rival+0.087
 informants+0.085
Neg logit contributions
rek-0.093
ercise-0.081
iaries-0.080
agy-0.078
 launchers-0.078
Token up
Token ID510
Feature activation+7.69e-02

Pos logit contributions
 smear+0.013
nown+0.013
 undercover+0.012
 rival+0.011
 informants+0.011
Neg logit contributions
rek-0.012
ercise-0.011
iaries-0.011
agy-0.010
 launchers-0.010
Token to
Token ID284
Feature activation+8.56e-03

Pos logit contributions
rek+0.059
ercise+0.052
iaries+0.052
agy+0.051
 launchers+0.051
Neg logit contributions
 smear-0.063
nown-0.063
 undercover-0.057
 rival-0.053
 informants-0.052
Token specific
Token ID2176
Feature activation+2.87e-02

Pos logit contributions
rek+0.013
ercise+0.011
iaries+0.011
agy+0.011
 launchers+0.011
Neg logit contributions
nown-0.014
 smear-0.014
 undercover-0.013
 rival-0.012
 informants-0.012
Token relationships
Token ID6958
Feature activation-1.79e-01

Pos logit contributions
rek+0.020
ercise+0.018
iaries+0.018
 launchers+0.017
agy+0.017
Neg logit contributions
nown-0.026
 smear-0.025
 undercover-0.023
 rival-0.022
below-0.021
Token like
Token ID588
Feature activation-7.11e-02

Pos logit contributions
 smear+0.150
nown+0.149
 undercover+0.133
 rival+0.125
 Blackwell+0.123
Neg logit contributions
rek-0.137
ercise-0.121
iaries-0.118
agy-0.117
 launchers-0.117
Token above
Token ID2029
Feature activation-2.16e-01

Pos logit contributions
nown+0.059
 smear+0.059
 undercover+0.053
 rival+0.049
below+0.048
Neg logit contributions
rek-0.055
ercise-0.048
iaries-0.047
 launchers-0.047
agy-0.046
Token/
Token ID14
Feature activation-1.53e-01

Pos logit contributions
 smear+0.181
nown+0.180
 undercover+0.162
 rival+0.152
 informants+0.149
Neg logit contributions
rek-0.165
ercise-0.145
iaries-0.144
agy-0.140
 launchers-0.140
Tokenbelow
Token ID35993
Feature activation-5.65e-01

Pos logit contributions
 smear+0.034
nown+0.031
 undercover+0.019
 rival+0.012
 informants+0.011
Neg logit contributions
rek-0.213
ercise-0.198
iaries-0.196
agy-0.194
 Views-0.194
Token,
Token ID11
Feature activation+1.22e-02

Pos logit contributions
 smear+0.471
nown+0.470
 undercover+0.422
 rival+0.396
 informants+0.388
Neg logit contributions
rek-0.433
ercise-0.381
iaries-0.377
agy-0.369
 launchers-0.368
Token or
Token ID393
Feature activation+1.97e-01

Pos logit contributions
rek+0.010
ercise+0.009
iaries+0.008
agy+0.008
 launchers+0.008
Neg logit contributions
 smear-0.010
nown-0.010
 undercover-0.009
 rival-0.008
 informants-0.008
Token left
Token ID1364
Feature activation-2.96e-02

Pos logit contributions
rek+0.159
ercise+0.140
iaries+0.139
 launchers+0.137
agy+0.136
Neg logit contributions
nown-0.156
 smear-0.156
 undercover-0.138
 rival-0.129
 informants-0.127
Token/
Token ID14
Feature activation-1.57e-01

Pos logit contributions
nown+0.021
 smear+0.021
 undercover+0.019
 rival+0.017
 informants+0.017
Neg logit contributions
rek-0.026
ercise-0.023
iaries-0.023
agy-0.023
 launchers-0.023
Tokenright
Token ID3506
Feature activation-1.26e-01

Pos logit contributions
 smear+0.109
nown+0.109
 undercover+0.096
 rival+0.089
below+0.087
Neg logit contributions
rek-0.142
ercise-0.128
iaries-0.127
agy-0.124
 launchers-0.124
Token Luc
Token ID7598
Feature activation+1.30e-01

Pos logit contributions
nown+0.042
 smear+0.042
 undercover+0.038
 rival+0.035
 informants+0.034
Neg logit contributions
rek-0.044
ercise-0.038
iaries-0.038
 Views-0.038
agy-0.037
Tokenio
Token ID952
Feature activation-4.49e-02

Pos logit contributions
rek+0.102
ercise+0.090
iaries+0.089
agy+0.087
 launchers+0.086
Neg logit contributions
 smear-0.106
nown-0.106
 undercover-0.095
 rival-0.089
 informants-0.087
Token,
Token ID11
Feature activation+1.46e-03

Pos logit contributions
 smear+0.038
nown+0.038
 undercover+0.034
 rival+0.032
 informants+0.031
Neg logit contributions
rek-0.034
ercise-0.030
iaries-0.029
agy-0.029
 launchers-0.029
Token a
Token ID257
Feature activation-2.25e-02

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
 smear-0.001
nown-0.001
 undercover-0.001
 rival-0.001
 informants-0.001
Token Browns
Token ID17671
Feature activation+1.57e-01

Pos logit contributions
 smear+0.020
nown+0.020
 undercover+0.018
 rival+0.017
 informants+0.016
Neg logit contributions
rek-0.016
ercise-0.014
iaries-0.014
agy-0.014
 launchers-0.014
Tokenville
Token ID4244
Feature activation-5.65e-01

Pos logit contributions
rek+0.214
ercise+0.198
iaries+0.197
agy+0.195
 Views+0.195
Neg logit contributions
nown-0.039
 smear-0.038
 undercover-0.025
 rival-0.016
 informants-0.015
Token Democrat
Token ID9755
Feature activation-1.19e-01

Pos logit contributions
nown+0.457
 smear+0.456
 undercover+0.406
 rival+0.377
below+0.373
Neg logit contributions
rek-0.446
ercise-0.394
iaries-0.389
 launchers-0.381
agy-0.381
Token who
Token ID508
Feature activation-7.28e-03

Pos logit contributions
 smear+0.103
nown+0.102
 undercover+0.092
 rival+0.086
 informants+0.085
Neg logit contributions
rek-0.089
ercise-0.077
iaries-0.076
agy-0.075
 launchers-0.074
Token announced
Token ID3414
Feature activation+2.05e-02

Pos logit contributions
nown+0.006
 smear+0.006
 undercover+0.005
 rival+0.005
below+0.005
Neg logit contributions
rek-0.006
ercise-0.005
iaries-0.005
agy-0.005
 launchers-0.005
Token his
Token ID465
Feature activation-1.82e-02

Pos logit contributions
rek+0.016
ercise+0.014
iaries+0.014
agy+0.014
 launchers+0.013
Neg logit contributions
nown-0.017
 smear-0.017
 undercover-0.015
 rival-0.014
below-0.014
Token support
Token ID1104
Feature activation-1.03e-01

Pos logit contributions
nown+0.017
 smear+0.017
 undercover+0.015
 rival+0.014
 informants+0.014
Neg logit contributions
rek-0.012
ercise-0.010
iaries-0.010
agy-0.010
 launchers-0.010
Token of
Token ID286
Feature activation-1.04e-02

Pos logit contributions
rek+0.035
ercise+0.031
iaries+0.030
agy+0.030
 launchers+0.030
Neg logit contributions
 smear-0.040
nown-0.040
 undercover-0.036
 rival-0.033
 informants-0.033
Token M
Token ID337
Feature activation-3.64e-02

Pos logit contributions
 smear+0.008
nown+0.008
 undercover+0.007
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.008
ercise-0.007
iaries-0.007
agy-0.007
 launchers-0.007
Token.
Token ID13
Feature activation-1.92e-02

Pos logit contributions
 smear+0.030
nown+0.030
 undercover+0.027
 rival+0.025
 informants+0.025
Neg logit contributions
rek-0.028
ercise-0.025
iaries-0.025
agy-0.024
 launchers-0.024
Token de
Token ID390
Feature activation+4.21e-02

Pos logit contributions
nown+0.016
 smear+0.016
 undercover+0.014
 rival+0.013
 informants+0.013
Neg logit contributions
rek-0.015
ercise-0.013
iaries-0.013
agy-0.013
 launchers-0.013
Token Tre
Token ID4700
Feature activation+1.26e-02

Pos logit contributions
rek+0.034
ercise+0.030
iaries+0.030
agy+0.030
 launchers+0.029
Neg logit contributions
 smear-0.033
nown-0.033
 undercover-0.029
 rival-0.027
 informants-0.027
Tokenville
Token ID4244
Feature activation-5.64e-01

Pos logit contributions
rek+0.015
ercise+0.014
iaries+0.014
agy+0.014
 launchers+0.014
Neg logit contributions
nown-0.005
 smear-0.005
 undercover-0.004
 rival-0.003
 informants-0.003
Token's
Token ID338
Feature activation-3.38e-02

Pos logit contributions
 smear+0.461
nown+0.460
 undercover+0.412
 rival+0.386
 informants+0.378
Neg logit contributions
rek-0.443
ercise-0.390
iaries-0.386
agy-0.377
 launchers-0.376
Token house
Token ID2156
Feature activation+7.21e-02

Pos logit contributions
nown+0.027
 smear+0.027
 undercover+0.025
 rival+0.023
below+0.022
Neg logit contributions
rek-0.027
ercise-0.024
iaries-0.023
agy-0.023
 launchers-0.023
Token on
Token ID319
Feature activation-1.89e-02

Pos logit contributions
rek+0.054
ercise+0.047
iaries+0.047
agy+0.046
 launchers+0.046
Neg logit contributions
nown-0.061
 smear-0.061
 undercover-0.055
 rival-0.052
 informants-0.051
Token the
Token ID262
Feature activation-6.54e-03

Pos logit contributions
 smear+0.015
nown+0.015
 undercover+0.014
 rival+0.013
 informants+0.013
Neg logit contributions
rek-0.015
ercise-0.013
iaries-0.013
agy-0.013
 launchers-0.013
Token r
Token ID374
Feature activation+1.05e-02

Pos logit contributions
nown+0.005
 smear+0.005
 undercover+0.005
 rival+0.004
below+0.004
Neg logit contributions
rek-0.005
ercise-0.005
iaries-0.005
 launchers-0.005
 Views-0.005
Token year
Token ID614
Feature activation-4.69e-02

Pos logit contributions
nown+0.067
 smear+0.067
 undercover+0.060
 rival+0.056
below+0.055
Neg logit contributions
rek-0.062
ercise-0.055
iaries-0.054
 launchers-0.053
agy-0.053
Token,
Token ID11
Feature activation+3.13e-03

Pos logit contributions
 smear+0.040
nown+0.040
 undercover+0.036
 rival+0.034
below+0.034
Neg logit contributions
rek-0.035
ercise-0.030
iaries-0.030
agy-0.029
 launchers-0.029
Token split
Token ID6626
Feature activation-1.11e-01

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
nown-0.003
 smear-0.003
 undercover-0.002
 rival-0.002
below-0.002
Token into
Token ID656
Feature activation+3.33e-02

Pos logit contributions
 smear+0.094
nown+0.093
 undercover+0.085
 rival+0.080
 informants+0.078
Neg logit contributions
rek-0.084
ercise-0.074
iaries-0.073
agy-0.071
 launchers-0.071
Token two
Token ID734
Feature activation-2.63e-03

Pos logit contributions
rek+0.024
ercise+0.021
iaries+0.021
 launchers+0.021
agy+0.021
Neg logit contributions
nown-0.029
 smear-0.029
 undercover-0.026
 rival-0.024
below-0.024
Token rival
Token ID8976
Feature activation-5.64e-01

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.002
 rival+0.002
 informants+0.002
Neg logit contributions
rek-0.002
ercise-0.002
iaries-0.002
agy-0.002
 launchers-0.002
Token groups
Token ID2628
Feature activation-1.74e-02

Pos logit contributions
nown+0.450
 smear+0.450
 undercover+0.402
 rival+0.375
below+0.367
Neg logit contributions
rek-0.452
ercise-0.400
iaries-0.396
agy-0.388
 launchers-0.387
Token in
Token ID287
Feature activation+2.39e-03

Pos logit contributions
 smear+0.015
nown+0.015
 undercover+0.013
 rival+0.012
 informants+0.012
Neg logit contributions
rek-0.013
ercise-0.011
iaries-0.011
agy-0.011
 launchers-0.011
Token September
Token ID2693
Feature activation+1.37e-01

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
 launchers+0.002
agy+0.002
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.002
below-0.002
Token.
Token ID13
Feature activation-2.11e-02

Pos logit contributions
rek+0.108
ercise+0.095
iaries+0.094
 launchers+0.092
agy+0.092
Neg logit contributions
nown-0.111
 smear-0.111
 undercover-0.098
 rival-0.092
below-0.091
Token Police
Token ID4287
Feature activation-2.42e-01

Pos logit contributions
 smear+0.017
nown+0.017
 undercover+0.016
 rival+0.014
 informants+0.014
Neg logit contributions
rek-0.016
ercise-0.014
iaries-0.014
 Views-0.014
 launchers-0.014
Token specific
Token ID2176
Feature activation+3.41e-02

Pos logit contributions
nown+0.008
 smear+0.008
 undercover+0.007
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.007
ercise-0.006
iaries-0.006
 launchers-0.006
agy-0.006
Token relationship
Token ID2776
Feature activation-1.57e-01

Pos logit contributions
rek+0.024
ercise+0.021
iaries+0.020
 launchers+0.020
agy+0.020
Neg logit contributions
nown-0.031
 smear-0.031
 undercover-0.028
 rival-0.026
below-0.026
Token like
Token ID588
Feature activation-6.57e-02

Pos logit contributions
 smear+0.134
nown+0.134
 undercover+0.120
 rival+0.112
 informants+0.111
Neg logit contributions
rek-0.116
ercise-0.102
iaries-0.100
agy-0.099
 launchers-0.098
Token above
Token ID2029
Feature activation-2.09e-01

Pos logit contributions
nown+0.053
 smear+0.053
 undercover+0.047
 rival+0.043
 informants+0.043
Neg logit contributions
rek-0.053
ercise-0.046
iaries-0.046
 launchers-0.045
agy-0.045
Token/
Token ID14
Feature activation-1.52e-01

Pos logit contributions
 smear+0.159
nown+0.158
 undercover+0.141
 rival+0.131
 informants+0.128
Neg logit contributions
rek-0.176
ercise-0.157
iaries-0.155
agy-0.152
 launchers-0.151
Tokenbelow
Token ID35993
Feature activation-5.64e-01

Pos logit contributions
 smear+0.032
nown+0.029
 undercover+0.018
 rival+0.011
 informants+0.011
Neg logit contributions
rek-0.212
ercise-0.197
iaries-0.195
agy-0.193
 Views-0.193
Token,
Token ID11
Feature activation+1.42e-02

Pos logit contributions
 smear+0.495
nown+0.494
 undercover+0.446
 rival+0.420
 informants+0.412
Neg logit contributions
rek-0.408
ercise-0.356
iaries-0.350
agy-0.343
 launchers-0.342
Token while
Token ID981
Feature activation+1.00e-01

Pos logit contributions
rek+0.010
ercise+0.009
iaries+0.009
agy+0.009
 launchers+0.009
Neg logit contributions
 smear-0.012
nown-0.012
 undercover-0.011
 rival-0.011
 informants-0.010
Token also
Token ID635
Feature activation+1.53e-01

Pos logit contributions
rek+0.073
ercise+0.064
iaries+0.063
 launchers+0.062
agy+0.062
Neg logit contributions
 smear-0.087
nown-0.087
 undercover-0.078
 rival-0.074
 informants-0.072
Token possessing
Token ID25566
Feature activation-2.76e-02

Pos logit contributions
rek+0.111
ercise+0.097
iaries+0.095
 launchers+0.094
agy+0.093
Neg logit contributions
nown-0.133
 smear-0.133
 undercover-0.119
 rival-0.112
below-0.110
Token elements
Token ID4847
Feature activation-8.13e-02

Pos logit contributions
nown+0.023
 smear+0.023
 undercover+0.021
 rival+0.019
below+0.019
Neg logit contributions
rek-0.021
ercise-0.018
iaries-0.018
 launchers-0.018
agy-0.018
Token
Token ID198
Feature activation-7.77e-03

Pos logit contributions
nown+0.008
 smear+0.008
 undercover+0.007
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.007
ercise-0.006
iaries-0.006
agy-0.006
 Views-0.006
Token-
Token ID12
Feature activation-6.06e-03

Pos logit contributions
 smear+0.006
nown+0.006
 undercover+0.006
 rival+0.005
 informants+0.005
Neg logit contributions
rek-0.006
ercise-0.005
iaries-0.005
agy-0.005
 launchers-0.005
Token and
Token ID290
Feature activation+1.08e-03

Pos logit contributions
 smear+0.005
nown+0.005
 undercover+0.004
 rival+0.004
 informants+0.004
Neg logit contributions
rek-0.005
ercise-0.004
iaries-0.004
agy-0.004
 launchers-0.004
Token Herman
Token ID25028
Feature activation-1.06e-01

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
 smear-0.001
nown-0.001
 undercover-0.001
 rival-0.001
 informants-0.001
Token Mel
Token ID5616
Feature activation-5.15e-02

Pos logit contributions
nown+0.087
 smear+0.087
 undercover+0.078
 rival+0.073
 informants+0.071
Neg logit contributions
rek-0.083
ercise-0.073
iaries-0.072
agy-0.071
 launchers-0.071
Tokenville
Token ID4244
Feature activation-5.63e-01

Pos logit contributions
 smear+0.011
nown+0.010
 undercover+0.006
 rival+0.004
 informants+0.003
Neg logit contributions
rek-0.072
ercise-0.067
iaries-0.067
agy-0.066
 launchers-0.066
Token.
Token ID764
Feature activation-2.51e-02

Pos logit contributions
 smear+0.470
nown+0.469
 undercover+0.422
 rival+0.397
 informants+0.387
Neg logit contributions
rek-0.430
ercise-0.378
iaries-0.374
agy-0.366
 launchers-0.364
Token.
Token ID764
Feature activation-1.97e-02

Pos logit contributions
 smear+0.021
nown+0.021
 undercover+0.019
 rival+0.017
 informants+0.017
Neg logit contributions
rek-0.020
ercise-0.017
iaries-0.017
agy-0.017
 Views-0.017
Token.
Token ID764
Feature activation-2.49e-02

Pos logit contributions
 smear+0.016
nown+0.016
 undercover+0.014
 rival+0.013
 informants+0.013
Neg logit contributions
rek-0.016
ercise-0.014
iaries-0.014
agy-0.013
 launchers-0.013
Token
Token ID198
Feature activation-1.25e-02

Pos logit contributions
 smear+0.021
nown+0.021
 undercover+0.018
 rival+0.017
 informants+0.017
Neg logit contributions
rek-0.019
ercise-0.017
iaries-0.017
agy-0.016
 Views-0.016
Token
Token ID198
Feature activation-1.07e-02

Pos logit contributions
nown+0.011
 smear+0.011
 undercover+0.010
 rival+0.009
 informants+0.009
Neg logit contributions
rek-0.009
ercise-0.008
iaries-0.008
agy-0.008
 Views-0.008
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
 smear+0.040
nown+0.040
 undercover+0.036
 rival+0.033
 informants+0.033
Neg logit contributions
rek-0.038
ercise-0.033
iaries-0.033
agy-0.032
 launchers-0.032
Token Sanders
Token ID5831
Feature activation+2.18e-02

Pos logit contributions
 smear+0.013
nown+0.013
 undercover+0.011
 rival+0.011
 informants+0.010
Neg logit contributions
rek-0.011
ercise-0.010
iaries-0.010
agy-0.010
 launchers-0.010
Token out
Token ID503
Feature activation+2.93e-01

Pos logit contributions
rek+0.016
ercise+0.014
iaries+0.014
 launchers+0.014
agy+0.014
Neg logit contributions
nown-0.019
 smear-0.019
 undercover-0.017
 rival-0.016
 informants-0.015
Token-
Token ID12
Feature activation+2.95e-03

Pos logit contributions
rek+0.220
ercise+0.193
iaries+0.191
agy+0.186
 launchers+0.186
Neg logit contributions
 smear-0.249
nown-0.249
 undercover-0.224
 rival-0.211
 informants-0.206
Tokenraised
Token ID49309
Feature activation-1.63e-02

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.002
nown-0.002
 undercover-0.002
 rival-0.002
below-0.002
Token rival
Token ID8976
Feature activation-5.62e-01

Pos logit contributions
nown+0.013
 smear+0.012
 undercover+0.011
below+0.010
 informants+0.010
Neg logit contributions
rek-0.013
ercise-0.012
iaries-0.012
 Views-0.012
agy-0.012
Token Hillary
Token ID5073
Feature activation-1.77e-01

Pos logit contributions
nown+0.365
 smear+0.361
 undercover+0.315
 rival+0.281
 informants+0.280
Neg logit contributions
rek-0.534
ercise-0.482
iaries-0.480
agy-0.473
 Views-0.472
Token Clinton
Token ID2605
Feature activation+5.04e-03

Pos logit contributions
nown+0.156
 smear+0.154
 undercover+0.140
 informants+0.129
below+0.129
Neg logit contributions
rek-0.127
ercise-0.111
iaries-0.110
 Views-0.109
agy-0.107
Token for
Token ID329
Feature activation-9.28e-03

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
agy+0.003
 launchers+0.003
Neg logit contributions
nown-0.005
 smear-0.005
 undercover-0.004
 rival-0.004
 informants-0.004
Token the
Token ID262
Feature activation-2.31e-03

Pos logit contributions
nown+0.008
 smear+0.008
 undercover+0.007
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.007
ercise-0.006
iaries-0.006
 Views-0.006
agy-0.006
Token fourth
Token ID5544
Feature activation+1.62e-01

Pos logit contributions
nown+0.002
 smear+0.002
 undercover+0.002
 rival+0.002
below+0.002
Neg logit contributions
rek-0.001
iaries-0.001
ercise-0.001
 Views-0.001
 launchers-0.001
Token Road
Token ID5567
Feature activation-1.61e-01

Pos logit contributions
rek+0.026
ercise+0.023
iaries+0.023
 Views+0.022
 launchers+0.022
Neg logit contributions
nown-0.024
 smear-0.024
 undercover-0.021
 rival-0.020
 informants-0.019
Token,
Token ID11
Feature activation+1.06e-02

Pos logit contributions
 smear+0.137
nown+0.136
 undercover+0.122
 rival+0.115
 informants+0.113
Neg logit contributions
rek-0.122
ercise-0.107
iaries-0.105
agy-0.103
 Views-0.103
Token in
Token ID287
Feature activation+9.52e-03

Pos logit contributions
rek+0.009
ercise+0.008
iaries+0.008
agy+0.007
 Views+0.007
Neg logit contributions
nown-0.008
 smear-0.008
 undercover-0.007
 rival-0.007
 informants-0.007
Token North
Token ID2258
Feature activation-8.17e-02

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 Views+0.007
Neg logit contributions
nown-0.007
 smear-0.007
 undercover-0.006
 rival-0.006
 informants-0.006
Token Ridge
Token ID20614
Feature activation-1.10e-01

Pos logit contributions
 smear+0.063
nown+0.063
 undercover+0.056
 rival+0.052
 informants+0.051
Neg logit contributions
rek-0.068
ercise-0.060
iaries-0.060
agy-0.058
 Views-0.058
Tokenville
Token ID4244
Feature activation-5.60e-01

Pos logit contributions
 smear+0.092
nown+0.091
 undercover+0.081
 rival+0.076
 informants+0.075
Neg logit contributions
rek-0.085
ercise-0.074
iaries-0.073
 Views-0.072
agy-0.071
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
 smear+0.484
nown+0.483
 undercover+0.433
 rival+0.407
 informants+0.401
Neg logit contributions
rek-0.414
ercise-0.360
iaries-0.356
agy-0.348
 Views-0.348
Token It
Token ID632
Feature activation-5.24e-02

Pos logit contributions
 smear+0.014
nown+0.014
 undercover+0.012
 rival+0.011
 informants+0.011
Neg logit contributions
rek-0.012
ercise-0.011
iaries-0.011
 Views-0.011
agy-0.011
Token has
Token ID468
Feature activation+8.58e-02

Pos logit contributions
nown+0.044
 smear+0.043
 undercover+0.039
 rival+0.036
 informants+0.036
Neg logit contributions
rek-0.040
ercise-0.035
iaries-0.035
agy-0.034
 launchers-0.034
Token stayed
Token ID9658
Feature activation+2.27e-01

Pos logit contributions
rek+0.066
ercise+0.058
iaries+0.057
agy+0.056
 launchers+0.056
Neg logit contributions
nown-0.072
 smear-0.072
 undercover-0.064
 rival-0.060
below-0.059
Token in
Token ID287
Feature activation+9.69e-03

Pos logit contributions
rek+0.164
ercise+0.143
iaries+0.141
agy+0.138
 launchers+0.138
Neg logit contributions
 smear-0.199
nown-0.199
 undercover-0.179
 rival-0.169
 informants-0.165
Token the
Token ID262
Feature activation+4.23e-03

Pos logit contributions
rek+0.047
ercise+0.041
iaries+0.040
 Views+0.039
 launchers+0.039
Neg logit contributions
nown-0.057
 smear-0.056
 undercover-0.050
 informants-0.047
 rival-0.047
Token game
Token ID983
Feature activation-1.75e-02

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
 launchers+0.003
 Views+0.003
Neg logit contributions
nown-0.003
 smear-0.003
 undercover-0.003
 rival-0.003
 informants-0.003
Token against
Token ID1028
Feature activation-2.31e-01

Pos logit contributions
nown+0.012
 smear+0.012
 undercover+0.010
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.016
ercise-0.014
iaries-0.014
 launchers-0.014
 Views-0.014
Token West
Token ID2688
Feature activation-2.82e-01

Pos logit contributions
nown+0.164
 smear+0.161
 undercover+0.140
 informants+0.128
 rival+0.127
Neg logit contributions
rek-0.207
ercise-0.186
iaries-0.183
 Views-0.182
 launchers-0.181
Token Brom
Token ID31455
Feature activation-3.55e-01

Pos logit contributions
nown+0.175
 smear+0.174
 undercover+0.149
 informants+0.134
 rival+0.131
Neg logit contributions
rek-0.281
ercise-0.251
iaries-0.249
 Views-0.248
 launchers-0.246
Tokenwich
Token ID11451
Feature activation-5.59e-01

Pos logit contributions
 smear+0.296
nown+0.295
 undercover+0.263
 rival+0.245
 informants+0.244
Neg logit contributions
rek-0.274
ercise-0.241
iaries-0.234
 Views-0.233
 launchers-0.232
Token Albion
Token ID47995
Feature activation-3.03e-01

Pos logit contributions
nown+0.294
 smear+0.290
 undercover+0.239
 informants+0.211
 rival+0.208
Neg logit contributions
rek-0.607
ercise-0.559
 Views-0.544
 launchers-0.544
iaries-0.537
Token at
Token ID379
Feature activation-3.75e-02

Pos logit contributions
 smear+0.258
nown+0.258
 undercover+0.229
 informants+0.215
 rival+0.214
Neg logit contributions
rek-0.228
ercise-0.199
 Views-0.194
iaries-0.193
 launchers-0.192
Token Anfield
Token ID44303
Feature activation+8.86e-02

Pos logit contributions
nown+0.032
 smear+0.032
 undercover+0.028
 rival+0.026
 informants+0.026
Neg logit contributions
rek-0.028
ercise-0.025
iaries-0.024
 Views-0.024
 launchers-0.024
Token in
Token ID287
Feature activation+1.38e-02

Pos logit contributions
rek+0.066
ercise+0.058
 Views+0.057
iaries+0.057
 launchers+0.056
Neg logit contributions
nown-0.076
 smear-0.076
 undercover-0.067
 rival-0.063
 informants-0.063
Token October
Token ID3267
Feature activation+4.39e-02

Pos logit contributions
rek+0.010
ercise+0.008
iaries+0.008
 Views+0.008
 launchers+0.008
Neg logit contributions
nown-0.012
 smear-0.012
 undercover-0.011
 rival-0.010
 informants-0.010
Token Two
Token ID4930
Feature activation-8.18e-02

Pos logit contributions
 smear+0.010
nown+0.010
 undercover+0.009
 rival+0.009
below+0.008
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.008
 Views-0.008
agy-0.008
Token nights
Token ID12513
Feature activation+3.25e-02

Pos logit contributions
nown+0.064
 smear+0.064
 undercover+0.056
 rival+0.053
below+0.052
Neg logit contributions
rek-0.067
ercise-0.059
iaries-0.059
 launchers-0.058
agy-0.057
Token later
Token ID1568
Feature activation+1.67e-02

Pos logit contributions
rek+0.025
ercise+0.022
iaries+0.021
agy+0.021
 launchers+0.021
Neg logit contributions
 smear-0.027
nown-0.027
 undercover-0.025
 rival-0.023
 informants-0.023
Token,
Token ID11
Feature activation+1.49e-02

Pos logit contributions
rek+0.012
ercise+0.011
iaries+0.011
agy+0.010
 launchers+0.010
Neg logit contributions
 smear-0.014
nown-0.014
 undercover-0.013
 rival-0.012
below-0.012
Token a
Token ID257
Feature activation-1.26e-02

Pos logit contributions
rek+0.012
ercise+0.010
iaries+0.010
 launchers+0.010
agy+0.010
Neg logit contributions
nown-0.012
 smear-0.012
 undercover-0.011
 rival-0.010
below-0.010
Token rival
Token ID8976
Feature activation-5.59e-01

Pos logit contributions
nown+0.010
 smear+0.010
 undercover+0.009
 rival+0.008
below+0.008
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.009
 launchers-0.008
agy-0.008
Token group
Token ID1448
Feature activation+6.66e-02

Pos logit contributions
nown+0.476
 smear+0.474
 undercover+0.424
 rival+0.396
below+0.394
Neg logit contributions
rek-0.418
ercise-0.368
iaries-0.361
 launchers-0.355
agy-0.355
Token did
Token ID750
Feature activation+1.22e-01

Pos logit contributions
rek+0.053
ercise+0.046
iaries+0.046
 launchers+0.045
agy+0.045
Neg logit contributions
nown-0.054
 smear-0.054
 undercover-0.048
 rival-0.045
 informants-0.044
Token the
Token ID262
Feature activation+3.51e-03

Pos logit contributions
rek+0.093
ercise+0.082
iaries+0.081
 launchers+0.079
agy+0.079
Neg logit contributions
nown-0.103
 smear-0.102
 undercover-0.091
 rival-0.085
below-0.085
Token same
Token ID976
Feature activation+1.50e-02

Pos logit contributions
rek+0.003
ercise+0.002
iaries+0.002
 launchers+0.002
agy+0.002
Neg logit contributions
nown-0.003
 smear-0.003
 undercover-0.003
 rival-0.002
 informants-0.002
Token nearby
Token ID6716
Feature activation-4.12e-02

Pos logit contributions
rek+0.011
ercise+0.010
iaries+0.010
agy+0.010
 launchers+0.010
Neg logit contributions
nown-0.013
 smear-0.013
 undercover-0.011
 rival-0.011
 informants-0.011
Token Mr
Token ID1770
Feature activation-5.69e-02

Pos logit contributions
rek+0.003
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.003
nown-0.003
 undercover-0.003
 rival-0.003
 informants-0.002
Token Cameron
Token ID10821
Feature activation-1.24e-01

Pos logit contributions
 smear+0.038
nown+0.038
 undercover+0.033
 rival+0.031
 informants+0.030
Neg logit contributions
rek-0.053
ercise-0.048
iaries-0.047
agy-0.047
 launchers-0.046
Token said
Token ID531
Feature activation-2.62e-03

Pos logit contributions
 smear+0.099
nown+0.099
 undercover+0.088
 rival+0.082
 informants+0.081
Neg logit contributions
rek-0.100
ercise-0.088
iaries-0.087
agy-0.086
 launchers-0.085
Token Britain
Token ID5491
Feature activation-1.18e-01

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.002
 rival+0.002
below+0.002
Neg logit contributions
rek-0.002
ercise-0.002
iaries-0.002
agy-0.002
 launchers-0.002
Token should
Token ID815
Feature activation+1.97e-02

Pos logit contributions
 smear+0.092
nown+0.091
 undercover+0.081
 rival+0.076
 informants+0.074
Neg logit contributions
rek-0.097
ercise-0.086
iaries-0.085
agy-0.083
 launchers-0.083
Token rival
Token ID8976
Feature activation-5.59e-01

Pos logit contributions
rek+0.016
ercise+0.014
iaries+0.014
agy+0.013
 launchers+0.013
Neg logit contributions
nown-0.016
 smear-0.016
 undercover-0.014
 rival-0.013
 informants-0.013
Token Dubai
Token ID24520
Feature activation-1.03e-02

Pos logit contributions
nown+0.490
 smear+0.489
 undercover+0.441
 rival+0.413
 informants+0.407
Neg logit contributions
rek-0.404
ercise-0.351
iaries-0.347
agy-0.340
 launchers-0.339
Token as
Token ID355
Feature activation-5.98e-02

Pos logit contributions
 smear+0.009
nown+0.009
 undercover+0.008
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.008
ercise-0.007
iaries-0.007
agy-0.007
 launchers-0.007
Token one
Token ID530
Feature activation+1.18e-01

Pos logit contributions
 smear+0.050
nown+0.050
 undercover+0.045
 rival+0.042
 informants+0.041
Neg logit contributions
rek-0.046
ercise-0.040
iaries-0.040
agy-0.039
 launchers-0.039
Token of
Token ID286
Feature activation-3.19e-04

Pos logit contributions
rek+0.094
ercise+0.083
iaries+0.082
agy+0.080
 launchers+0.080
Neg logit contributions
 smear-0.095
nown-0.095
 undercover-0.085
 rival-0.080
 informants-0.078
Token the
Token ID262
Feature activation+7.48e-03

Pos logit contributions
 smear+0.000
nown+0.000
 undercover+0.000
 rival+0.000
 informants+0.000
Neg logit contributions
rek-0.000
ercise-0.000
iaries-0.000
agy-0.000
 launchers-0.000
Token by
Token ID416
Feature activation+8.57e-02

Pos logit contributions
rek+0.108
ercise+0.093
iaries+0.092
agy+0.089
 launchers+0.089
Neg logit contributions
 smear-0.151
nown-0.151
 undercover-0.137
 rival-0.130
 informants-0.127
Token state
Token ID1181
Feature activation+1.64e-02

Pos logit contributions
rek+0.068
ercise+0.060
iaries+0.059
 launchers+0.058
agy+0.058
Neg logit contributions
nown-0.069
 smear-0.069
 undercover-0.061
 rival-0.057
below-0.056
Token-
Token ID12
Feature activation+5.07e-03

Pos logit contributions
rek+0.012
ercise+0.011
iaries+0.011
agy+0.011
 launchers+0.011
Neg logit contributions
 smear-0.014
nown-0.014
 undercover-0.012
 rival-0.012
 informants-0.011
Tokenowned
Token ID11990
Feature activation+2.23e-01

Pos logit contributions
rek+0.003
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.005
nown-0.005
 undercover-0.005
 rival-0.005
 informants-0.005
Token Guang
Token ID36980
Feature activation-3.12e-01

Pos logit contributions
rek+0.181
ercise+0.160
iaries+0.159
 launchers+0.156
agy+0.156
Neg logit contributions
nown-0.176
 smear-0.175
 undercover-0.156
 rival-0.145
below-0.142
Tokend
Token ID67
Feature activation+4.14e-01

Pos logit contributions
 smear+0.401
nown+0.400
 undercover+0.374
 rival+0.360
 informants+0.355
Neg logit contributions
rek-0.099
ercise-0.069
iaries-0.067
agy-0.063
 launchers-0.062
Tokenong
Token ID506
Feature activation-1.29e-01

Pos logit contributions
rek+0.371
ercise+0.329
iaries+0.325
agy+0.321
 launchers+0.314
Neg logit contributions
 smear-0.297
nown-0.293
 undercover-0.261
 rival-0.238
 informants-0.237
Token D
Token ID360
Feature activation+8.20e-02

Pos logit contributions
 smear+0.107
nown+0.107
 undercover+0.096
 rival+0.090
 informants+0.088
Neg logit contributions
rek-0.100
ercise-0.087
iaries-0.086
agy-0.085
 launchers-0.084
Tokenaba
Token ID15498
Feature activation+1.25e-01

Pos logit contributions
rek+0.066
ercise+0.057
iaries+0.057
agy+0.056
 launchers+0.055
Neg logit contributions
 smear-0.066
nown-0.066
 undercover-0.059
 rival-0.055
 informants-0.054
Tokenosh
Token ID3768
Feature activation+3.86e-02

Pos logit contributions
rek+0.099
ercise+0.087
iaries+0.086
agy+0.084
 launchers+0.084
Neg logit contributions
 smear-0.102
nown-0.101
 undercover-0.091
 rival-0.085
 informants-0.083
Tokenan
Token ID272
Feature activation-1.70e-03

Pos logit contributions
rek+0.030
ercise+0.027
iaries+0.026
agy+0.026
 launchers+0.026
Neg logit contributions
 smear-0.031
nown-0.031
 undercover-0.028
 rival-0.026
 informants-0.026
TokenRegarding
Token ID39424
Feature activation+5.61e-02

Pos logit contributions
 smear+0.003
nown+0.003
 undercover+0.002
 rival+0.002
 informants+0.002
Neg logit contributions
rek-0.003
ercise-0.003
iaries-0.003
agy-0.002
 launchers-0.002
Token Arduino
Token ID27634
Feature activation-5.93e-02

Pos logit contributions
rek+0.044
ercise+0.039
iaries+0.039
 launchers+0.038
agy+0.038
Neg logit contributions
 smear-0.045
nown-0.045
 undercover-0.041
 rival-0.038
 informants-0.037
Token compatibility
Token ID17764
Feature activation-3.25e-02

Pos logit contributions
 smear+0.050
nown+0.050
 undercover+0.045
 rival+0.042
 informants+0.041
Neg logit contributions
rek-0.045
ercise-0.039
iaries-0.039
 launchers-0.038
 Views-0.038
Token itself
Token ID2346
Feature activation+4.14e-02

Pos logit contributions
 smear+0.028
nown+0.028
 undercover+0.025
 rival+0.024
 informants+0.023
Neg logit contributions
rek-0.024
ercise-0.021
iaries-0.021
agy-0.020
 launchers-0.020
Token,
Token ID11
Feature activation+7.72e-03

Pos logit contributions
rek+0.031
ercise+0.027
iaries+0.027
agy+0.026
 launchers+0.026
Neg logit contributions
 smear-0.036
nown-0.036
 undercover-0.032
 rival-0.030
 informants-0.030
Token doing
Token ID1804
Feature activation+3.05e-01

Pos logit contributions
rek+0.006
ercise+0.005
iaries+0.005
agy+0.005
 launchers+0.005
Neg logit contributions
 smear-0.006
nown-0.006
 undercover-0.006
 rival-0.005
 informants-0.005
Token it
Token ID340
Feature activation-1.05e-01

Pos logit contributions
rek+0.243
ercise+0.215
iaries+0.213
 launchers+0.210
 Views+0.209
Neg logit contributions
nown-0.245
 smear-0.243
 undercover-0.215
 rival-0.202
below-0.199
Token well
Token ID880
Feature activation-7.27e-02

Pos logit contributions
 smear+0.088
nown+0.088
 undercover+0.079
 rival+0.074
 informants+0.073
Neg logit contributions
rek-0.080
ercise-0.070
iaries-0.069
agy-0.068
 launchers-0.068
Token on
Token ID319
Feature activation-1.74e-02

Pos logit contributions
 smear+0.061
nown+0.061
 undercover+0.055
 rival+0.051
 informants+0.051
Neg logit contributions
rek-0.055
ercise-0.048
iaries-0.047
 launchers-0.047
 Views-0.047
Token anything
Token ID1997
Feature activation+5.61e-02

Pos logit contributions
nown+0.014
 smear+0.014
 undercover+0.013
 rival+0.012
 informants+0.012
Neg logit contributions
rek-0.013
ercise-0.012
iaries-0.012
 launchers-0.012
agy-0.011
Token other
Token ID584
Feature activation+5.04e-02

Pos logit contributions
rek+0.041
ercise+0.036
iaries+0.035
 launchers+0.035
agy+0.034
Neg logit contributions
nown-0.049
 smear-0.049
 undercover-0.044
 rival-0.041
 informants-0.041
Token
Token ID250
Feature activation+1.72e-02

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.001
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.001
ercise-0.001
iaries-0.001
 Views-0.001
agy-0.001
TokenThey
Token ID2990
Feature activation+4.53e-03

Pos logit contributions
rek+0.013
ercise+0.012
iaries+0.011
agy+0.011
 launchers+0.011
Neg logit contributions
 smear-0.014
nown-0.014
 undercover-0.013
 rival-0.012
 informants-0.012
Token got
Token ID1392
Feature activation-2.13e-03

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
agy+0.003
 launchers+0.003
Neg logit contributions
 smear-0.004
nown-0.004
 undercover-0.004
 rival-0.003
 informants-0.003
Token Bill
Token ID3941
Feature activation-2.66e-01

Pos logit contributions
nown+0.002
 smear+0.002
 undercover+0.002
 rival+0.001
 informants+0.001
Neg logit contributions
rek-0.002
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Token Ward
Token ID12150
Feature activation-1.40e-01

Pos logit contributions
 smear+0.195
nown+0.194
 undercover+0.172
 rival+0.160
 informants+0.156
Neg logit contributions
rek-0.232
ercise-0.207
iaries-0.205
agy-0.201
 launchers-0.200
Token out
Token ID503
Feature activation+2.99e-01

Pos logit contributions
 smear+0.116
nown+0.116
 undercover+0.104
 rival+0.097
 informants+0.095
Neg logit contributions
rek-0.108
ercise-0.095
iaries-0.093
agy-0.092
 launchers-0.091
Token of
Token ID286
Feature activation-1.46e-02

Pos logit contributions
rek+0.228
ercise+0.200
iaries+0.198
agy+0.193
 launchers+0.193
Neg logit contributions
 smear-0.251
nown-0.250
 undercover-0.225
 rival-0.211
 informants-0.207
Token the
Token ID262
Feature activation+2.99e-03

Pos logit contributions
nown+0.012
 smear+0.012
 undercover+0.010
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.012
ercise-0.010
iaries-0.010
agy-0.010
 launchers-0.010
Token asylum
Token ID13142
Feature activation+1.24e-01

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
 launchers+0.002
agy+0.002
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.002
 informants-0.002
Token to
Token ID284
Feature activation+6.53e-03

Pos logit contributions
rek+0.095
ercise+0.084
iaries+0.083
agy+0.081
 launchers+0.081
Neg logit contributions
 smear-0.102
nown-0.102
 undercover-0.092
 rival-0.086
 informants-0.084
Token play
Token ID711
Feature activation+2.94e-01

Pos logit contributions
rek+0.005
ercise+0.004
iaries+0.004
agy+0.004
 launchers+0.004
Neg logit contributions
nown-0.006
 smear-0.006
 undercover-0.005
 rival-0.005
 informants-0.005
Tokenesp
Token ID9774
Feature activation+2.71e-01

Pos logit contributions
 smear+0.006
nown+0.006
 undercover+0.006
 rival+0.005
 informants+0.005
Neg logit contributions
rek-0.005
ercise-0.004
iaries-0.004
agy-0.004
 launchers-0.004
Tokenrit
Token ID799
Feature activation-5.46e-02

Pos logit contributions
rek+0.218
ercise+0.193
iaries+0.191
agy+0.187
 launchers+0.186
Neg logit contributions
 smear-0.217
nown-0.216
 undercover-0.194
 rival-0.181
 informants-0.177
Token origin
Token ID8159
Feature activation-3.18e-02

Pos logit contributions
 smear+0.045
nown+0.045
 undercover+0.040
 rival+0.038
 informants+0.037
Neg logit contributions
rek-0.043
ercise-0.038
iaries-0.037
agy-0.036
 launchers-0.036
Tokenel
Token ID417
Feature activation+3.62e-01

Pos logit contributions
 smear+0.029
nown+0.029
 undercover+0.026
 rival+0.024
 informants+0.024
Neg logit contributions
rek-0.022
ercise-0.019
iaries-0.019
agy-0.019
 launchers-0.019
Token des
Token ID748
Feature activation+5.36e-02

Pos logit contributions
rek+0.280
ercise+0.246
iaries+0.244
agy+0.239
 launchers+0.238
Neg logit contributions
 smear-0.300
nown-0.299
 undercover-0.269
 rival-0.252
below-0.246
Token Cors
Token ID26978
Feature activation+3.33e-01

Pos logit contributions
rek+0.042
ercise+0.037
iaries+0.037
agy+0.036
 launchers+0.036
Neg logit contributions
 smear-0.044
nown-0.044
 undercover-0.039
 rival-0.037
 informants-0.036
Tokenaires
Token ID17693
Feature activation+1.11e-01

Pos logit contributions
rek+0.208
ercise+0.177
iaries+0.175
agy+0.170
 launchers+0.169
Neg logit contributions
 smear-0.326
nown-0.325
 undercover-0.297
 rival-0.282
 informants-0.276
Token [...]
Token ID26894
Feature activation-5.91e-02

Pos logit contributions
rek+0.088
ercise+0.077
iaries+0.077
agy+0.075
 launchers+0.075
Neg logit contributions
nown-0.090
 smear-0.090
 undercover-0.080
 rival-0.075
below-0.074
Token En
Token ID2039
Feature activation+1.45e-01

Pos logit contributions
 smear+0.047
nown+0.047
 undercover+0.042
 rival+0.039
below+0.038
Neg logit contributions
rek-0.047
ercise-0.042
iaries-0.041
agy-0.041
 launchers-0.040
Token cas
Token ID6124
Feature activation+1.88e-02

Pos logit contributions
rek+0.116
ercise+0.102
iaries+0.101
agy+0.099
 launchers+0.099
Neg logit contributions
 smear-0.116
nown-0.115
 undercover-0.103
 rival-0.097
 informants-0.094
Token de
Token ID390
Feature activation+5.10e-02

Pos logit contributions
rek+0.015
ercise+0.013
iaries+0.013
agy+0.013
 launchers+0.013
Neg logit contributions
 smear-0.015
nown-0.015
 undercover-0.013
 rival-0.012
below-0.012
Token Catalonia
Token ID33859
Feature activation+1.53e-01

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 launchers+0.007
Neg logit contributions
 smear-0.012
nown-0.012
 undercover-0.011
 rival-0.010
 informants-0.010
Token could
Token ID714
Feature activation-3.86e-02

Pos logit contributions
rek+0.119
ercise+0.105
iaries+0.102
 launchers+0.101
agy+0.100
Neg logit contributions
nown-0.125
 smear-0.125
 undercover-0.112
 rival-0.104
 Blackwell-0.103
Token be
Token ID307
Feature activation+1.15e-02

Pos logit contributions
nown+0.030
 smear+0.030
 undercover+0.027
 rival+0.025
 informants+0.024
Neg logit contributions
rek-0.032
ercise-0.028
iaries-0.028
agy-0.027
 launchers-0.027
Token a
Token ID257
Feature activation-1.30e-02

Pos logit contributions
rek+0.009
ercise+0.008
iaries+0.008
agy+0.008
 launchers+0.008
Neg logit contributions
nown-0.009
 smear-0.009
 undercover-0.008
 rival-0.008
 informants-0.008
Token way
Token ID835
Feature activation+1.84e-02

Pos logit contributions
nown+0.011
 smear+0.010
 undercover+0.009
 rival+0.009
 informants+0.009
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.009
 launchers-0.009
agy-0.009
Token out
Token ID503
Feature activation+2.97e-01

Pos logit contributions
rek+0.014
ercise+0.012
iaries+0.012
agy+0.012
 launchers+0.012
Neg logit contributions
 smear-0.016
nown-0.016
 undercover-0.014
 rival-0.013
 informants-0.013
Token of
Token ID286
Feature activation-9.40e-03

Pos logit contributions
rek+0.227
ercise+0.200
iaries+0.197
agy+0.193
 launchers+0.192
Neg logit contributions
 smear-0.248
nown-0.247
 undercover-0.222
 rival-0.209
 informants-0.204
Token the
Token ID262
Feature activation+3.93e-03

Pos logit contributions
nown+0.008
 smear+0.008
 undercover+0.007
 rival+0.006
 informants+0.006
Neg logit contributions
rek-0.007
ercise-0.006
iaries-0.006
agy-0.006
 launchers-0.006
Token present
Token ID1944
Feature activation-1.31e-01

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
 launchers+0.003
agy+0.003
Neg logit contributions
nown-0.003
 smear-0.003
 undercover-0.003
 rival-0.003
 informants-0.003
Token dead
Token ID2636
Feature activation-6.34e-02

Pos logit contributions
nown+0.105
 smear+0.105
 undercover+0.094
 rival+0.088
 informants+0.086
Neg logit contributions
rek-0.104
ercise-0.092
iaries-0.091
agy-0.089
 launchers-0.089
Tokenlock
Token ID5354
Feature activation+3.31e-03

Pos logit contributions
 smear+0.053
nown+0.053
 undercover+0.047
 rival+0.044
 informants+0.043
Neg logit contributions
rek-0.049
ercise-0.043
iaries-0.043
agy-0.042
 launchers-0.041
Token are
Token ID389
Feature activation+7.19e-03

Pos logit contributions
rek+0.050
ercise+0.044
iaries+0.043
 launchers+0.043
agy+0.043
Neg logit contributions
nown-0.053
 smear-0.053
 undercover-0.047
 rival-0.044
 informants-0.044
Token ways
Token ID2842
Feature activation+7.70e-02

Pos logit contributions
rek+0.006
ercise+0.005
iaries+0.005
 launchers+0.005
agy+0.005
Neg logit contributions
nown-0.006
 smear-0.006
 undercover-0.005
 rival-0.005
below-0.005
Token this
Token ID428
Feature activation-6.06e-02

Pos logit contributions
rek+0.057
ercise+0.050
iaries+0.049
agy+0.048
 launchers+0.048
Neg logit contributions
nown-0.066
 smear-0.066
 undercover-0.059
 rival-0.056
below-0.054
Token could
Token ID714
Feature activation-2.94e-02

Pos logit contributions
nown+0.052
 smear+0.051
 undercover+0.045
 rival+0.043
below+0.042
Neg logit contributions
rek-0.046
ercise-0.040
iaries-0.039
 launchers-0.039
agy-0.039
Token have
Token ID423
Feature activation+6.14e-02

Pos logit contributions
nown+0.026
 smear+0.026
 undercover+0.023
 rival+0.022
 informants+0.022
Neg logit contributions
rek-0.021
ercise-0.018
iaries-0.018
agy-0.018
 launchers-0.018
Token been
Token ID587
Feature activation+7.72e-03

Pos logit contributions
rek+0.051
ercise+0.045
iaries+0.044
 launchers+0.044
agy+0.044
Neg logit contributions
nown-0.048
 smear-0.047
 undercover-0.042
 rival-0.039
below-0.039
Token handled
Token ID12118
Feature activation+5.54e-02

Pos logit contributions
rek+0.006
ercise+0.005
iaries+0.005
agy+0.005
 launchers+0.005
Neg logit contributions
nown-0.007
 smear-0.007
 undercover-0.006
 rival-0.006
 informants-0.005
Token without
Token ID1231
Feature activation+6.84e-03

Pos logit contributions
rek+0.043
ercise+0.038
iaries+0.038
agy+0.037
 launchers+0.037
Neg logit contributions
 smear-0.046
nown-0.046
 undercover-0.041
 rival-0.038
 informants-0.037
Token striking
Token ID8871
Feature activation+8.84e-02

Pos logit contributions
rek+0.005
ercise+0.005
iaries+0.005
 launchers+0.004
agy+0.004
Neg logit contributions
nown-0.006
 smear-0.006
 undercover-0.005
 rival-0.005
below-0.005
Token her
Token ID607
Feature activation+1.15e-01

Pos logit contributions
rek+0.061
ercise+0.053
iaries+0.052
agy+0.051
 launchers+0.051
Neg logit contributions
nown-0.081
 smear-0.081
 undercover-0.073
 rival-0.069
 informants-0.067
Token,"
Token ID553
Feature activation+1.74e-01

Pos logit contributions
rek+0.080
ercise+0.069
iaries+0.069
agy+0.067
 launchers+0.066
Neg logit contributions
 smear-0.105
nown-0.104
 undercover-0.095
 rival-0.090
 informants-0.088
Token and
Token ID290
Feature activation+4.06e-03

Pos logit contributions
rek+0.005
ercise+0.004
iaries+0.004
 launchers+0.004
agy+0.004
Neg logit contributions
nown-0.005
 smear-0.005
 undercover-0.004
 rival-0.004
below-0.004
Token silk
Token ID23938
Feature activation-9.53e-02

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
 launchers+0.003
agy+0.003
Neg logit contributions
nown-0.003
 smear-0.003
 undercover-0.003
 rival-0.003
below-0.003
Token weaving
Token ID44889
Feature activation+1.10e-02

Pos logit contributions
nown+0.076
 smear+0.075
 undercover+0.068
 rival+0.063
below+0.062
Neg logit contributions
rek-0.077
ercise-0.068
iaries-0.067
 launchers-0.066
agy-0.066
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
 launchers+0.007
agy+0.007
Neg logit contributions
nown-0.009
 smear-0.009
 undercover-0.008
 rival-0.008
 Blackwell-0.008
Token Today
Token ID6288
Feature activation-7.48e-02

Pos logit contributions
nown+0.014
 smear+0.014
 undercover+0.013
 rival+0.012
 informants+0.012
Neg logit contributions
rek-0.013
ercise-0.011
iaries-0.011
 Views-0.011
agy-0.011
Token,
Token ID11
Feature activation+6.07e-03

Pos logit contributions
 smear+0.062
nown+0.062
 undercover+0.055
 rival+0.052
 informants+0.051
Neg logit contributions
rek-0.058
ercise-0.051
iaries-0.050
agy-0.049
 launchers-0.049
Token the
Token ID262
Feature activation-2.19e-04

Pos logit contributions
rek+0.005
ercise+0.004
iaries+0.004
agy+0.004
 launchers+0.004
Neg logit contributions
nown-0.005
 smear-0.005
 undercover-0.004
 rival-0.004
below-0.004
Token same
Token ID976
Feature activation+1.04e-02

Pos logit contributions
nown+0.000
 smear+0.000
 undercover+0.000
 rival+0.000
below+0.000
Neg logit contributions
rek-0.000
ercise-0.000
iaries-0.000
agy-0.000
 launchers-0.000
Token types
Token ID3858
Feature activation+4.02e-02

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 launchers+0.007
Neg logit contributions
nown-0.008
 smear-0.008
 undercover-0.007
 rival-0.007
below-0.007
Token of
Token ID286
Feature activation-1.43e-02

Pos logit contributions
rek+0.031
ercise+0.027
iaries+0.027
agy+0.027
 launchers+0.026
Neg logit contributions
 smear-0.033
nown-0.033
 undercover-0.030
 rival-0.028
 informants-0.027
Token looms
Token ID46234
Feature activation-2.26e-01

Pos logit contributions
nown+0.011
 smear+0.011
 undercover+0.010
 rival+0.009
below+0.009
Neg logit contributions
rek-0.012
iaries-0.010
ercise-0.010
 launchers-0.010
agy-0.010
Token was
Token ID373
Feature activation+2.89e-03

Pos logit contributions
rek+0.002
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.002
below-0.002
Token built
Token ID3170
Feature activation-5.99e-02

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.002
nown-0.002
 undercover-0.002
 rival-0.002
 informants-0.002
Token on
Token ID319
Feature activation-6.99e-03

Pos logit contributions
 smear+0.051
nown+0.051
 undercover+0.045
 rival+0.043
 informants+0.042
Neg logit contributions
rek-0.045
ercise-0.039
iaries-0.039
agy-0.038
 launchers-0.038
Token farmland
Token ID45723
Feature activation+1.42e-01

Pos logit contributions
nown+0.006
 smear+0.006
 undercover+0.005
 rival+0.005
 informants+0.005
Neg logit contributions
rek-0.005
ercise-0.005
iaries-0.005
 launchers-0.005
agy-0.005
Token owned
Token ID6898
Feature activation+1.72e-01

Pos logit contributions
rek+0.110
ercise+0.096
iaries+0.095
agy+0.094
 launchers+0.094
Neg logit contributions
nown-0.117
 smear-0.117
 undercover-0.105
 rival-0.098
 informants-0.096
Token by
Token ID416
Feature activation+8.81e-02

Pos logit contributions
rek+0.114
ercise+0.098
iaries+0.097
agy+0.094
 launchers+0.094
Neg logit contributions
 smear-0.161
nown-0.161
 undercover-0.147
 rival-0.139
 informants-0.136
Token the
Token ID262
Feature activation+1.37e-02

Pos logit contributions
rek+0.068
ercise+0.060
iaries+0.059
agy+0.058
 launchers+0.058
Neg logit contributions
nown-0.073
 smear-0.072
 undercover-0.065
 rival-0.060
below-0.059
Token Sherman
Token ID23198
Feature activation+8.13e-02

Pos logit contributions
rek+0.011
ercise+0.010
iaries+0.010
 launchers+0.009
agy+0.009
Neg logit contributions
nown-0.011
 smear-0.011
 undercover-0.010
 rival-0.009
 informants-0.009
Token family
Token ID1641
Feature activation-4.92e-02

Pos logit contributions
rek+0.066
ercise+0.059
iaries+0.058
agy+0.057
 launchers+0.057
Neg logit contributions
nown-0.064
 smear-0.064
 undercover-0.057
 rival-0.053
 informants-0.052
Token.
Token ID13
Feature activation-6.47e-03

Pos logit contributions
nown+0.041
 smear+0.041
 undercover+0.037
 rival+0.035
 informants+0.034
Neg logit contributions
rek-0.037
ercise-0.033
iaries-0.032
 launchers-0.032
agy-0.032
Token
Token ID198
Feature activation+7.99e-03

Pos logit contributions
nown+0.005
 smear+0.005
 undercover+0.005
 rival+0.005
 informants+0.004
Neg logit contributions
rek-0.005
ercise-0.004
iaries-0.004
 Views-0.004
agy-0.004
Token Wife
Token ID34188
Feature activation-7.75e-02

Pos logit contributions
nown+0.025
 smear+0.024
 undercover+0.022
 rival+0.020
 informants+0.020
Neg logit contributions
rek-0.026
ercise-0.023
iaries-0.022
agy-0.022
 Views-0.022
Token CBS
Token ID11133
Feature activation+9.79e-02

Pos logit contributions
nown+0.063
 smear+0.062
 undercover+0.056
 rival+0.052
 informants+0.051
Neg logit contributions
rek-0.062
ercise-0.054
iaries-0.053
 Views-0.053
agy-0.053
Token Tat
Token ID29070
Feature activation+1.21e-01

Pos logit contributions
rek+0.078
ercise+0.069
iaries+0.068
 Views+0.067
agy+0.067
Neg logit contributions
nown-0.079
 smear-0.079
 undercover-0.070
 rival-0.065
 informants-0.065
Tokeniana
Token ID7484
Feature activation-1.72e-02

Pos logit contributions
rek+0.098
ercise+0.086
iaries+0.086
agy+0.084
 launchers+0.083
Neg logit contributions
 smear-0.097
nown-0.096
 undercover-0.086
 rival-0.081
 informants-0.079
Token Mas
Token ID11066
Feature activation+6.68e-02

Pos logit contributions
 smear+0.015
nown+0.015
 undercover+0.013
 rival+0.013
 informants+0.012
Neg logit contributions
rek-0.013
ercise-0.011
iaries-0.011
agy-0.011
 launchers-0.011
Tokenl
Token ID75
Feature activation+6.75e-02

Pos logit contributions
rek+0.046
ercise+0.040
iaries+0.039
agy+0.038
 launchers+0.038
Neg logit contributions
 smear-0.061
nown-0.061
 undercover-0.056
 rival-0.052
 informants-0.051
Tokenany
Token ID1092
Feature activation-3.26e-02

Pos logit contributions
rek+0.052
ercise+0.045
agy+0.045
iaries+0.045
 Views+0.044
Neg logit contributions
 smear-0.057
nown-0.056
 undercover-0.050
 rival-0.047
 informants-0.047
Token Or
Token ID1471
Feature activation+1.23e-01

Pos logit contributions
nown+0.026
 smear+0.026
 undercover+0.023
 rival+0.022
 informants+0.021
Neg logit contributions
rek-0.026
ercise-0.023
iaries-0.023
 Views-0.022
agy-0.022
Tokenphan
Token ID19080
Feature activation+2.13e-01

Pos logit contributions
rek+0.067
ercise+0.055
iaries+0.054
agy+0.052
 Views+0.052
Neg logit contributions
 smear-0.131
nown-0.130
 undercover-0.120
 rival-0.114
 informants-0.113
Token Black
Token ID2619
Feature activation-2.98e-02

Pos logit contributions
rek+0.193
ercise+0.174
iaries+0.172
 launchers+0.168
agy+0.167
Neg logit contributions
 smear-0.148
nown-0.147
 undercover-0.131
 rival-0.122
 Blackwell-0.118
Token BBC
Token ID7823
Feature activation+1.20e-01

Pos logit contributions
nown+0.024
 smear+0.024
 undercover+0.022
 rival+0.020
 informants+0.020
Neg logit contributions
rek-0.024
ercise-0.021
iaries-0.021
 Views-0.020
agy-0.020
Token and
Token ID290
Feature activation+4.06e-03

Pos logit contributions
 smear+0.016
nown+0.016
 undercover+0.014
 rival+0.013
 informants+0.013
Neg logit contributions
rek-0.013
ercise-0.012
iaries-0.012
agy-0.011
 launchers-0.011
Token the
Token ID262
Feature activation+2.72e-03

Pos logit contributions
rek+0.003
ercise+0.003
iaries+0.003
agy+0.003
 launchers+0.003
Neg logit contributions
nown-0.003
 smear-0.003
 undercover-0.003
 rival-0.003
 informants-0.003
Token lighting
Token ID12019
Feature activation-3.98e-02

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
 launchers+0.002
 Views+0.002
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.002
 Blackwell-0.002
Token wasn
Token ID2492
Feature activation-4.91e-02

Pos logit contributions
nown+0.033
 smear+0.032
 undercover+0.029
 rival+0.027
 informants+0.027
Neg logit contributions
rek-0.031
ercise-0.027
iaries-0.027
 launchers-0.027
 Views-0.026
Token
Token ID447
Feature activation-1.44e-02

Pos logit contributions
 smear+0.041
nown+0.041
 undercover+0.037
 rival+0.034
 informants+0.034
Neg logit contributions
rek-0.038
ercise-0.033
iaries-0.033
agy-0.032
 Views-0.032
Token
Token ID247
Feature activation-2.21e-02

Pos logit contributions
nown+0.012
 smear+0.012
 undercover+0.011
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.011
ercise-0.010
iaries-0.010
agy-0.010
 Views-0.010
Tokent
Token ID83
Feature activation+2.99e-02

Pos logit contributions
 smear+0.019
nown+0.019
 undercover+0.017
 rival+0.016
 informants+0.016
Neg logit contributions
rek-0.017
ercise-0.014
iaries-0.014
agy-0.014
 Views-0.014
Token ideal
Token ID7306
Feature activation-2.30e-01

Pos logit contributions
rek+0.024
ercise+0.021
iaries+0.021
 Views+0.021
agy+0.021
Neg logit contributions
nown-0.024
 smear-0.024
 undercover-0.021
 rival-0.020
 informants-0.019
Token,
Token ID11
Feature activation+1.06e-02

Pos logit contributions
 smear+0.195
nown+0.194
 undercover+0.175
 rival+0.164
 informants+0.161
Neg logit contributions
rek-0.174
ercise-0.152
iaries-0.150
agy-0.147
 launchers-0.147
Token either
Token ID2035
Feature activation+6.48e-02

Pos logit contributions
rek+0.008
ercise+0.007
iaries+0.007
agy+0.007
 launchers+0.007
Neg logit contributions
nown-0.009
 smear-0.009
 undercover-0.008
 rival-0.007
 informants-0.007
Token.
Token ID13
Feature activation-1.67e-02

Pos logit contributions
rek+0.049
ercise+0.043
iaries+0.042
agy+0.041
 launchers+0.041
Neg logit contributions
 smear-0.055
nown-0.055
 undercover-0.049
 rival-0.046
 informants-0.045
Tokenojure
Token ID32511
Feature activation+8.98e-02

Pos logit contributions
 smear+0.007
nown+0.007
 undercover+0.007
 rival+0.006
 informants+0.006
Neg logit contributions
rek-0.005
ercise-0.004
iaries-0.004
agy-0.004
 launchers-0.004
Token /
Token ID1220
Feature activation-4.29e-02

Pos logit contributions
rek+0.069
ercise+0.061
iaries+0.060
 launchers+0.059
 Views+0.059
Neg logit contributions
 smear-0.075
nown-0.075
 undercover-0.067
 rival-0.062
 informants-0.062
Token tools
Token ID4899
Feature activation-2.55e-01

Pos logit contributions
nown+0.035
 smear+0.035
 undercover+0.031
 rival+0.029
below+0.029
Neg logit contributions
rek-0.034
ercise-0.030
iaries-0.029
 launchers-0.029
agy-0.029
Token.
Token ID764
Feature activation-1.86e-02

Pos logit contributions
 smear+0.206
nown+0.206
 undercover+0.184
 rival+0.173
 informants+0.169
Neg logit contributions
rek-0.202
ercise-0.179
iaries-0.177
agy-0.173
 launchers-0.173
Token n
Token ID299
Feature activation-8.29e-02

Pos logit contributions
 smear+0.016
nown+0.016
 undercover+0.014
 rival+0.014
 informants+0.013
Neg logit contributions
rek-0.014
ercise-0.012
iaries-0.012
agy-0.012
 launchers-0.012
Tokenrepl
Token ID35666
Feature activation-9.93e-02

Pos logit contributions
 smear+0.071
nown+0.071
 undercover+0.064
 rival+0.060
 informants+0.060
Neg logit contributions
rek-0.061
ercise-0.054
iaries-0.053
agy-0.052
 launchers-0.052
Token |
Token ID930
Feature activation-2.40e-03

Pos logit contributions
 smear+0.083
nown+0.082
 undercover+0.074
 rival+0.069
 informants+0.068
Neg logit contributions
rek-0.076
ercise-0.067
iaries-0.067
agy-0.065
 launchers-0.065
Token 12
Token ID1105
Feature activation+2.00e-02

Pos logit contributions
 smear+0.002
nown+0.002
 undercover+0.002
 rival+0.002
 informants+0.002
Neg logit contributions
rek-0.001
ercise-0.001
iaries-0.001
agy-0.001
 launchers-0.001
Token44
Token ID2598
Feature activation+1.29e-01

Pos logit contributions
rek+0.013
ercise+0.011
iaries+0.011
agy+0.011
 launchers+0.011
Neg logit contributions
 smear-0.019
nown-0.019
 undercover-0.017
 rival-0.016
 informants-0.016
Token |
Token ID930
Feature activation-4.76e-04

Pos logit contributions
rek+0.098
ercise+0.086
iaries+0.085
 Views+0.083
agy+0.083
Neg logit contributions
nown-0.109
 smear-0.109
 undercover-0.098
 rival-0.092
 informants-0.090
Token |
Token ID930
Feature activation-7.88e-03

Pos logit contributions
 smear+0.000
nown+0.000
 undercover+0.000
 rival+0.000
 informants+0.000
Neg logit contributions
rek-0.000
ercise-0.000
iaries-0.000
agy-0.000
 launchers-0.000
Token number
Token ID1271
Feature activation+7.32e-02

Pos logit contributions
rek+0.005
ercise+0.005
iaries+0.004
 launchers+0.004
 Views+0.004
Neg logit contributions
nown-0.005
 smear-0.005
 undercover-0.004
 rival-0.004
 informants-0.004
Token of
Token ID286
Feature activation-4.74e-03

Pos logit contributions
rek+0.057
ercise+0.050
iaries+0.050
agy+0.049
 launchers+0.049
Neg logit contributions
 smear-0.060
nown-0.060
 undercover-0.054
 rival-0.050
 informants-0.049
Token journeys
Token ID35724
Feature activation+6.51e-02

Pos logit contributions
nown+0.004
 smear+0.004
 undercover+0.003
 rival+0.003
 informants+0.003
Neg logit contributions
rek-0.004
ercise-0.003
iaries-0.003
 launchers-0.003
 Views-0.003
Token on
Token ID319
Feature activation-1.63e-02

Pos logit contributions
rek+0.049
ercise+0.043
iaries+0.043
 launchers+0.042
 Views+0.042
Neg logit contributions
nown-0.055
 smear-0.055
 undercover-0.049
 rival-0.046
 informants-0.045
Token the
Token ID262
Feature activation+6.21e-03

Pos logit contributions
 smear+0.013
nown+0.013
 undercover+0.012
 rival+0.011
 informants+0.011
Neg logit contributions
rek-0.013
ercise-0.011
iaries-0.011
 launchers-0.011
 Views-0.011
Token Tube
Token ID34510
Feature activation-1.77e-01

Pos logit contributions
rek+0.005
ercise+0.005
iaries+0.005
 launchers+0.005
 Views+0.004
Neg logit contributions
nown-0.005
 smear-0.005
 undercover-0.004
 informants-0.004
 rival-0.004
Token has
Token ID468
Feature activation+9.43e-02

Pos logit contributions
nown+0.166
 smear+0.165
 undercover+0.150
 rival+0.140
 informants+0.140
Neg logit contributions
rek-0.117
ercise-0.101
iaries-0.099
 launchers-0.097
 Views-0.096
Token increased
Token ID3220
Feature activation+2.55e-02

Pos logit contributions
rek+0.080
ercise+0.071
iaries+0.071
agy+0.069
 launchers+0.069
Neg logit contributions
nown-0.071
 smear-0.071
 undercover-0.063
 rival-0.058
 informants-0.057
Token by
Token ID416
Feature activation+8.47e-02

Pos logit contributions
rek+0.017
ercise+0.015
iaries+0.014
agy+0.014
 launchers+0.014
Neg logit contributions
 smear-0.024
nown-0.024
 undercover-0.022
 rival-0.020
 informants-0.020
Token 30
Token ID1542
Feature activation+1.03e-01

Pos logit contributions
rek+0.057
ercise+0.050
iaries+0.049
 launchers+0.048
agy+0.048
Neg logit contributions
nown-0.078
 smear-0.078
 undercover-0.070
 rival-0.066
below-0.065
Token%;
Token ID26525
Feature activation+2.78e-01

Pos logit contributions
rek+0.071
ercise+0.061
iaries+0.060
agy+0.059
 launchers+0.059
Neg logit contributions
 smear-0.095
nown-0.095
 undercover-0.086
 rival-0.081
 informants-0.080
Token any
Token ID597
Feature activation+5.34e-02

Pos logit contributions
rek+0.072
ercise+0.063
iaries+0.063
agy+0.061
 launchers+0.061
Neg logit contributions
 smear-0.080
nown-0.080
 undercover-0.072
 rival-0.067
 informants-0.066
Token Mercenary
Token ID49969
Feature activation+2.01e-02

Pos logit contributions
rek+0.041
ercise+0.036
iaries+0.036
agy+0.035
 launchers+0.035
Neg logit contributions
 smear-0.044
nown-0.044
 undercover-0.040
 rival-0.037
 informants-0.037
Token war
Token ID1175
Feature activation-1.17e-01

Pos logit contributions
rek+0.016
ercise+0.015
iaries+0.014
agy+0.014
 launchers+0.014
Neg logit contributions
 smear-0.016
nown-0.016
 undercover-0.014
 rival-0.013
 informants-0.013
Tokencaster
Token ID17970
Feature activation-1.72e-01

Pos logit contributions
 smear+0.092
nown+0.092
 undercover+0.082
 rival+0.077
 informants+0.075
Neg logit contributions
rek-0.095
ercise-0.084
iaries-0.083
agy-0.082
 launchers-0.082
Token and
Token ID290
Feature activation+4.69e-03

Pos logit contributions
 smear+0.141
nown+0.141
 undercover+0.126
 rival+0.118
 informants+0.116
Neg logit contributions
rek-0.135
ercise-0.119
iaries-0.117
agy-0.115
 launchers-0.114
Token non
Token ID1729
Feature activation-1.19e-01

Pos logit contributions
rek+0.004
ercise+0.003
iaries+0.003
 launchers+0.003
agy+0.003
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.003
 rival-0.003
 informants-0.003
Token-
Token ID12
Feature activation+5.26e-03

Pos logit contributions
 smear+0.101
nown+0.101
 undercover+0.091
 rival+0.085
 informants+0.083
Neg logit contributions
rek-0.090
ercise-0.079
iaries-0.078
agy-0.076
 launchers-0.076
Tokencharacter
Token ID22769
Feature activation+9.06e-02

Pos logit contributions
rek+0.004
ercise+0.003
iaries+0.003
agy+0.003
 launchers+0.003
Neg logit contributions
 smear-0.005
nown-0.005
 undercover-0.004
 rival-0.004
 informants-0.004
Token war
Token ID1175
Feature activation-1.14e-01

Pos logit contributions
rek+0.073
ercise+0.064
iaries+0.064
 launchers+0.062
agy+0.062
Neg logit contributions
nown-0.073
 smear-0.072
 undercover-0.064
 rival-0.060
 informants-0.059
Tokenj
Token ID73
Feature activation+1.71e-01

Pos logit contributions
nown+0.087
 smear+0.087
 undercover+0.078
 rival+0.072
 informants+0.071
Neg logit contributions
rek-0.095
ercise-0.084
iaries-0.083
agy-0.082
 launchers-0.082
Tokenacks
Token ID4595
Feature activation+3.62e-01

Pos logit contributions
rek+0.117
ercise+0.101
iaries+0.100
agy+0.097
 launchers+0.097
Neg logit contributions
 smear-0.157
nown-0.157
 undercover-0.143
 rival-0.135
 informants-0.132
Token colleague
Token ID16008
Feature activation-1.49e-01

Pos logit contributions
nown+0.008
 smear+0.008
 undercover+0.007
 rival+0.006
below+0.006
Neg logit contributions
rek-0.009
ercise-0.008
iaries-0.008
agy-0.008
 launchers-0.008
Token Nicole
Token ID25176
Feature activation-4.80e-02

Pos logit contributions
 smear+0.120
nown+0.120
 undercover+0.107
 rival+0.100
 informants+0.098
Neg logit contributions
rek-0.119
ercise-0.105
iaries-0.104
agy-0.102
 launchers-0.101
Token O
Token ID440
Feature activation-1.10e-01

Pos logit contributions
nown+0.038
 smear+0.037
 undercover+0.033
 rival+0.031
 informants+0.030
Neg logit contributions
rek-0.039
ercise-0.035
iaries-0.034
 Views-0.034
agy-0.034
Tokenzer
Token ID9107
Feature activation+2.94e-02

Pos logit contributions
 smear+0.091
nown+0.091
 undercover+0.082
 rival+0.077
 informants+0.075
Neg logit contributions
rek-0.084
ercise-0.074
iaries-0.073
agy-0.072
 launchers-0.071
Token has
Token ID468
Feature activation+9.30e-02

Pos logit contributions
rek+0.022
ercise+0.019
iaries+0.019
agy+0.019
 Views+0.019
Neg logit contributions
 smear-0.025
nown-0.025
 undercover-0.022
 rival-0.021
 informants-0.021
Token discussed
Token ID6693
Feature activation-5.34e-02

Pos logit contributions
rek+0.072
ercise+0.063
iaries+0.062
agy+0.061
 launchers+0.061
Neg logit contributions
nown-0.077
 smear-0.077
 undercover-0.069
 rival-0.065
 Blackwell-0.063
Token,
Token ID11
Feature activation+1.45e-02

Pos logit contributions
 smear+0.045
nown+0.045
 undercover+0.040
 rival+0.038
 Blackwell+0.037
Neg logit contributions
rek-0.040
ercise-0.035
iaries-0.035
agy-0.034
 launchers-0.034
Token there
Token ID612
Feature activation+6.18e-02

Pos logit contributions
rek+0.011
ercise+0.010
iaries+0.009
agy+0.009
 launchers+0.009
Neg logit contributions
 smear-0.012
nown-0.012
 undercover-0.011
 rival-0.010
 informants-0.010
Token is
Token ID318
Feature activation-1.35e-02

Pos logit contributions
rek+0.047
ercise+0.041
iaries+0.040
agy+0.039
 launchers+0.039
Neg logit contributions
 smear-0.052
nown-0.052
 undercover-0.047
 rival-0.044
 Blackwell-0.043
Token a
Token ID257
Feature activation-9.95e-03

Pos logit contributions
nown+0.011
 smear+0.011
 undercover+0.010
 rival+0.009
below+0.009
Neg logit contributions
rek-0.011
ercise-0.009
iaries-0.009
 launchers-0.009
agy-0.009
Token long
Token ID890
Feature activation+2.08e-01

Pos logit contributions
 smear+0.009
nown+0.009
 undercover+0.008
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.007
ercise-0.006
iaries-0.006
agy-0.006
 launchers-0.006
Token and
Token ID290
Feature activation+8.68e-03

Pos logit contributions
rek+0.005
ercise+0.005
iaries+0.005
 launchers+0.005
agy+0.005
Neg logit contributions
nown-0.006
 smear-0.006
 undercover-0.005
 rival-0.005
 informants-0.005
Token took
Token ID1718
Feature activation+7.53e-02

Pos logit contributions
rek+0.007
ercise+0.006
iaries+0.006
 launchers+0.006
agy+0.006
Neg logit contributions
nown-0.007
 smear-0.007
 undercover-0.006
 rival-0.006
 informants-0.006
Token images
Token ID4263
Feature activation-6.44e-02

Pos logit contributions
rek+0.057
ercise+0.050
iaries+0.050
 launchers+0.048
 Views+0.048
Neg logit contributions
nown-0.063
 smear-0.063
 undercover-0.057
 rival-0.053
 informants-0.052
Token of
Token ID286
Feature activation-1.04e-02

Pos logit contributions
 smear+0.054
nown+0.053
 undercover+0.048
 rival+0.045
 informants+0.044
Neg logit contributions
rek-0.049
ercise-0.043
iaries-0.043
agy-0.042
 launchers-0.042
Token the
Token ID262
Feature activation+5.31e-03

Pos logit contributions
nown+0.009
 smear+0.009
 undercover+0.008
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.008
ercise-0.007
iaries-0.007
 launchers-0.007
 Views-0.007
Token pin
Token ID6757
Feature activation-6.14e-02

Pos logit contributions
rek+0.004
ercise+0.004
iaries+0.004
 launchers+0.004
 Views+0.004
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.004
 rival-0.003
 Blackwell-0.003
Tokenhole
Token ID13207
Feature activation+6.58e-02

Pos logit contributions
 smear+0.056
nown+0.055
 undercover+0.050
 rival+0.048
 informants+0.047
Neg logit contributions
rek-0.043
ercise-0.037
iaries-0.037
agy-0.036
 launchers-0.036
Token at
Token ID379
Feature activation-4.22e-02

Pos logit contributions
rek+0.050
ercise+0.044
iaries+0.044
 launchers+0.043
 Views+0.043
Neg logit contributions
nown-0.055
 smear-0.054
 undercover-0.049
 rival-0.046
 Blackwell-0.045
Token a
Token ID257
Feature activation-1.53e-02

Pos logit contributions
nown+0.035
 smear+0.035
 undercover+0.031
 rival+0.029
 informants+0.029
Neg logit contributions
rek-0.032
ercise-0.029
iaries-0.028
 launchers-0.028
agy-0.028
Token 40
Token ID2319
Feature activation+1.65e-01

Pos logit contributions
nown+0.013
 smear+0.013
 undercover+0.012
 rival+0.011
 informants+0.011
Neg logit contributions
rek-0.011
ercise-0.010
iaries-0.010
 launchers-0.009
agy-0.009
Token degree
Token ID4922
Feature activation+1.18e-01

Pos logit contributions
rek+0.126
ercise+0.111
iaries+0.110
agy+0.107
 launchers+0.107
Neg logit contributions
 smear-0.138
nown-0.137
 undercover-0.123
 rival-0.116
 informants-0.113
Token $
Token ID720
Feature activation+5.74e-02

Pos logit contributions
nown+0.193
 smear+0.193
 undercover+0.174
 rival+0.164
 informants+0.160
Neg logit contributions
rek-0.165
ercise-0.144
iaries-0.142
agy-0.139
 launchers-0.139
Tokenart
Token ID433
Feature activation+2.39e-01

Pos logit contributions
rek+0.045
ercise+0.039
iaries+0.039
agy+0.038
 launchers+0.038
Neg logit contributions
 smear-0.047
nown-0.047
 undercover-0.042
 rival-0.040
 informants-0.039
Tokenext
Token ID2302
Feature activation+1.74e-01

Pos logit contributions
rek+0.215
ercise+0.193
iaries+0.191
agy+0.187
 launchers+0.186
Neg logit contributions
 smear-0.168
nown-0.168
 undercover-0.148
 rival-0.137
 informants-0.133
Token =
Token ID796
Feature activation-2.04e-01

Pos logit contributions
rek+0.170
ercise+0.153
iaries+0.152
agy+0.150
 launchers+0.149
Neg logit contributions
 smear-0.110
nown-0.109
 undercover-0.095
 rival-0.087
 informants-0.084
Token ($
Token ID7198
Feature activation-9.58e-02

Pos logit contributions
nown+0.159
 smear+0.158
 undercover+0.142
 rival+0.132
 informants+0.130
Neg logit contributions
rek-0.166
ercise-0.147
iaries-0.146
 Views-0.143
 launchers-0.143
Tokentext
Token ID5239
Feature activation-4.66e-01

Pos logit contributions
 smear+0.079
nown+0.079
 undercover+0.071
 rival+0.066
 informants+0.065
Neg logit contributions
rek-0.075
ercise-0.066
iaries-0.065
agy-0.064
 launchers-0.063
Token -
Token ID532
Feature activation-6.30e-02

Pos logit contributions
 smear+0.378
nown+0.377
 undercover+0.338
 rival+0.316
 informants+0.309
Neg logit contributions
rek-0.369
ercise-0.326
iaries-0.322
agy-0.315
 launchers-0.314
Tokensplit
Token ID35312
Feature activation-8.39e-02

Pos logit contributions
 smear+0.047
nown+0.047
 undercover+0.042
 rival+0.039
 informants+0.038
Neg logit contributions
rek-0.054
ercise-0.048
iaries-0.047
 Views-0.046
 launchers-0.046
Token "\
Token ID37082
Feature activation+3.35e-02

Pos logit contributions
 smear+0.065
nown+0.065
 undercover+0.058
 rival+0.054
 informants+0.053
Neg logit contributions
rek-0.069
ercise-0.061
iaries-0.061
agy-0.060
 Views-0.059
Tokenr
Token ID81
Feature activation+3.85e-01

Pos logit contributions
rek+0.025
ercise+0.021
iaries+0.021
agy+0.021
 launchers+0.020
Neg logit contributions
 smear-0.029
nown-0.029
 undercover-0.027
 rival-0.025
 informants-0.024
Token
Token ID198
Feature activation-8.96e-03

Pos logit contributions
rek+0.290
ercise+0.254
agy+0.246
iaries+0.246
 launchers+0.243
Neg logit contributions
 smear-0.328
nown-0.325
 undercover-0.298
 rival-0.275
 informants-0.274
Token AT
Token ID5161
Feature activation-8.14e-02

Pos logit contributions
rek+0.056
ercise+0.050
iaries+0.049
agy+0.048
 launchers+0.048
Neg logit contributions
 smear-0.044
nown-0.044
 undercover-0.039
 rival-0.036
 informants-0.035
Token M
Token ID337
Feature activation-3.10e-02

Pos logit contributions
nown+0.060
 smear+0.059
 undercover+0.053
 rival+0.048
 informants+0.048
Neg logit contributions
rek-0.071
ercise-0.063
iaries-0.063
 launchers-0.062
 Views-0.062
TokenCC
Token ID4093
Feature activation-9.96e-03

Pos logit contributions
 smear+0.024
nown+0.023
 undercover+0.021
 rival+0.019
 informants+0.019
Neg logit contributions
rek-0.026
ercise-0.023
iaries-0.023
agy-0.023
 launchers-0.022
TokenON
Token ID1340
Feature activation-1.62e-02

Pos logit contributions
 smear+0.008
nown+0.008
 undercover+0.007
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.008
ercise-0.007
iaries-0.007
agy-0.007
 launchers-0.007
TokenNE
Token ID12161
Feature activation-2.22e-01

Pos logit contributions
 smear+0.010
nown+0.010
 undercover+0.009
 rival+0.008
 informants+0.008
Neg logit contributions
rek-0.016
ercise-0.014
iaries-0.014
agy-0.014
 launchers-0.014
TokenLL
Token ID3069
Feature activation-4.45e-01

Pos logit contributions
nown+0.079
 smear+0.078
 undercover+0.059
 rival+0.046
 informants+0.046
Neg logit contributions
rek-0.279
 launchers-0.255
ercise-0.254
 Views-0.253
agy-0.253
Token
Token ID198
Feature activation-3.97e-03

Pos logit contributions
nown+0.364
 smear+0.363
 undercover+0.326
 rival+0.304
 informants+0.298
Neg logit contributions
rek-0.348
ercise-0.307
iaries-0.304
agy-0.298
 launchers-0.298
Token
Token ID198
Feature activation-6.69e-04

Pos logit contributions
nown+0.003
 smear+0.003
 undercover+0.003
 rival+0.003
 informants+0.003
Neg logit contributions
rek-0.003
ercise-0.003
iaries-0.003
agy-0.003
 launchers-0.003
TokenTrump
Token ID6170
Feature activation+2.11e-01

Pos logit contributions
 smear+0.001
nown+0.001
 undercover+0.001
 rival+0.000
 informants+0.000
Neg logit contributions
rek-0.000
ercise-0.000
iaries-0.000
agy-0.000
 launchers-0.000
Token has
Token ID468
Feature activation+8.88e-02

Pos logit contributions
rek+0.159
ercise+0.139
iaries+0.137
agy+0.135
 launchers+0.134
Neg logit contributions
nown-0.179
 smear-0.179
 undercover-0.161
 rival-0.149
 informants-0.148
Token often
Token ID1690
Feature activation+9.66e-02

Pos logit contributions
rek+0.071
ercise+0.063
iaries+0.062
agy+0.061
 launchers+0.061
Neg logit contributions
nown-0.071
 smear-0.071
 undercover-0.063
 rival-0.059
below-0.058
Token HBO
Token ID18804
Feature activation+5.01e-03

Pos logit contributions
rek+0.200
ercise+0.176
iaries+0.173
 Views+0.170
agy+0.170
Neg logit contributions
nown-0.215
 smear-0.215
 undercover-0.193
 rival-0.180
 informants-0.177
Token Jim
Token ID5395
Feature activation-1.30e-01

Pos logit contributions
rek+0.004
ercise+0.003
iaries+0.003
 Views+0.003
agy+0.003
Neg logit contributions
nown-0.004
 smear-0.004
 undercover-0.004
 rival-0.003
 informants-0.003
Token Parsons
Token ID35925
Feature activation-2.71e-01

Pos logit contributions
 smear+0.098
nown+0.097
 undercover+0.087
 rival+0.081
 Blackwell+0.079
Neg logit contributions
rek-0.110
ercise-0.098
iaries-0.097
 launchers-0.095
agy-0.095
Token The
Token ID383
Feature activation-1.51e-02

Pos logit contributions
nown+0.218
 smear+0.217
 undercover+0.194
 rival+0.181
 informants+0.178
Neg logit contributions
rek-0.216
ercise-0.191
iaries-0.188
 Views-0.185
agy-0.185
Token Big
Token ID4403
Feature activation+6.36e-02

Pos logit contributions
nown+0.012
 smear+0.012
 undercover+0.011
 rival+0.010
 informants+0.010
Neg logit contributions
rek-0.012
ercise-0.011
iaries-0.011
 Views-0.010
 launchers-0.010
Token Bang
Token ID9801
Feature activation-3.66e-01

Pos logit contributions
rek+0.076
ercise+0.070
iaries+0.070
agy+0.069
 launchers+0.069
Neg logit contributions
 smear-0.026
nown-0.025
 undercover-0.020
 rival-0.017
 Blackwell-0.016
Token Theory
Token ID17003
Feature activation-1.16e-01

Pos logit contributions
 smear+0.237
nown+0.235
 undercover+0.205
 rival+0.189
 informants+0.183
Neg logit contributions
rek-0.349
ercise-0.315
iaries-0.312
agy-0.307
 launchers-0.305
Token CBS
Token ID11133
Feature activation+9.58e-02

Pos logit contributions
nown+0.097
 smear+0.096
 undercover+0.086
 rival+0.080
 informants+0.079
Neg logit contributions
rek-0.090
ercise-0.079
iaries-0.078
 Views-0.077
agy-0.076
Token Amy
Token ID14235
Feature activation-1.62e-01

Pos logit contributions
rek+0.076
ercise+0.067
iaries+0.066
 Views+0.065
agy+0.065
Neg logit contributions
nown-0.078
 smear-0.077
 undercover-0.069
 rival-0.064
 informants-0.064
Token Poe
Token ID34815
Feature activation+4.52e-02

Pos logit contributions
 smear+0.134
nown+0.134
 undercover+0.120
 rival+0.113
 informants+0.110
Neg logit contributions
rek-0.125
ercise-0.110
iaries-0.109
agy-0.106
 launchers-0.106
Tokenhler
Token ID49737
Feature activation-2.52e-01

Pos logit contributions
rek+0.050
ercise+0.046
iaries+0.046
agy+0.045
 launchers+0.045
Neg logit contributions
 smear-0.022
nown-0.022
 undercover-0.018
 rival-0.016
 informants-0.015
Token make
Token ID787
Feature activation-1.18e-02

Pos logit contributions
nown+0.025
 smear+0.025
 undercover+0.023
 rival+0.021
 informants+0.021
Neg logit contributions
rek-0.017
ercise-0.015
iaries-0.015
agy-0.014
 launchers-0.014
Token up
Token ID510
Feature activation+7.65e-02

Pos logit contributions
nown+0.010
 smear+0.010
 undercover+0.009
 rival+0.008
below+0.008
Neg logit contributions
rek-0.009
ercise-0.008
iaries-0.008
 launchers-0.007
agy-0.007
Token the
Token ID262
Feature activation+2.83e-03

Pos logit contributions
rek+0.057
ercise+0.050
iaries+0.049
 launchers+0.048
agy+0.048
Neg logit contributions
nown-0.065
 smear-0.065
 undercover-0.058
 rival-0.055
 informants-0.054
Token majority
Token ID3741
Feature activation+2.71e-03

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
 launchers+0.002
agy+0.002
Neg logit contributions
nown-0.002
 smear-0.002
 undercover-0.002
 rival-0.002
 informants-0.002
Token of
Token ID286
Feature activation-1.34e-02

Pos logit contributions
rek+0.002
ercise+0.002
iaries+0.002
agy+0.002
 launchers+0.002
Neg logit contributions
 smear-0.002
nown-0.002
 undercover-0.002
 rival-0.002
 informants-0.002
Token customers
Token ID4297
Feature activation-4.13e-01

Pos logit contributions
nown+0.011
 smear+0.011
 undercover+0.010
 rival+0.009
below+0.009
Neg logit contributions
rek-0.010
ercise-0.009
iaries-0.009
 launchers-0.009
 Views-0.009
Token,
Token ID11
Feature activation+1.27e-03

Pos logit contributions
 smear+0.344
nown+0.343
 undercover+0.308
 rival+0.289
 informants+0.283
Neg logit contributions
rek-0.318
ercise-0.280
iaries-0.276
agy-0.270
 launchers-0.269
Token she
Token ID673
Feature activation+4.54e-02

Pos logit contributions
rek+0.001
ercise+0.001
iaries+0.001
agy+0.001
 launchers+0.001
Neg logit contributions
nown-0.001
 smear-0.001
 undercover-0.001
 rival-0.001
below-0.001
Token said
Token ID531
Feature activation-1.06e-02

Pos logit contributions
rek+0.037
ercise+0.033
iaries+0.032
agy+0.032
 launchers+0.032
Neg logit contributions
 smear-0.036
nown-0.036
 undercover-0.032
 rival-0.030
 informants-0.029
Token.
Token ID13
Feature activation-1.80e-02

Pos logit contributions
 smear+0.009
nown+0.009
 undercover+0.008
 rival+0.007
 informants+0.007
Neg logit contributions
rek-0.008
ercise-0.007
iaries-0.007
agy-0.007
 launchers-0.007
Token
Token ID198
Feature activation-1.84e-03

Pos logit contributions
 smear+0.015
nown+0.015
 undercover+0.014
 rival+0.013
 informants+0.012
Neg logit contributions
rek-0.014
ercise-0.012
iaries-0.012
agy-0.012
 Views-0.012
Token,
Token ID11
Feature activation+5.71e-03

Pos logit contributions
 smear+0.021
nown+0.021
 undercover+0.019
 rival+0.018
below+0.018
Neg logit contributions
rek-0.020
ercise-0.017
iaries-0.017
agy-0.017
 launchers-0.016
Token Ying
Token ID38833
Feature activation-2.18e-01

Pos logit contributions
rek+0.005
ercise+0.004
iaries+0.004
agy+0.004
 launchers+0.004
Neg logit contributions
nown-0.005
 smear-0.005
 undercover-0.004
 rival-0.004
below-0.004
Token Chen
Token ID12555
Feature activation-1.14e-01

Pos logit contributions
 smear+0.170
nown+0.170
 undercover+0.152
 rival+0.142
 informants+0.138
Neg logit contributions
rek-0.179
ercise-0.158
iaries-0.156
agy-0.153
 launchers-0.152
Token,
Token ID11
Feature activation+4.99e-03

Pos logit contributions
 smear+0.097
nown+0.096
 undercover+0.087
 rival+0.082
 informants+0.080
Neg logit contributions
rek-0.086
ercise-0.076
iaries-0.075
agy-0.073
 launchers-0.073
Token were
Token ID547
Feature activation+6.98e-02

Pos logit contributions
rek+0.004
ercise+0.003
iaries+0.003
agy+0.003
 launchers+0.003
Neg logit contributions
 smear-0.004
nown-0.004
 undercover-0.004
 rival-0.004
below-0.003
Token thru
Token ID33834
Feature activation-3.88e-01

Pos logit contributions
rek+0.052
ercise+0.046
iaries+0.046
 launchers+0.045
agy+0.045
Neg logit contributions
nown-0.059
 smear-0.059
 undercover-0.052
 rival-0.049
below-0.048
Token-
Token ID12
Feature activation-4.15e-03

Pos logit contributions
 smear+0.325
nown+0.324
 undercover+0.292
 rival+0.274
 informants+0.268
Neg logit contributions
rek-0.296
ercise-0.260
iaries-0.257
agy-0.251
 launchers-0.250
Tokenh
Token ID71
Feature activation+1.92e-01

Pos logit contributions
 smear+0.004
nown+0.004
 undercover+0.004
 rival+0.004
 informants+0.004
Neg logit contributions
rek-0.002
ercise-0.002
iaries-0.002
agy-0.002
 launchers-0.002
Tokeniking
Token ID14132
Feature activation+2.23e-02

Pos logit contributions
rek+0.137
ercise+0.119
iaries+0.117
agy+0.115
 launchers+0.113
Neg logit contributions
 smear-0.172
nown-0.171
 undercover-0.156
 rival-0.146
 informants-0.144
Token the
Token ID262
Feature activation-4.08e-03

Pos logit contributions
rek+0.017
ercise+0.015
iaries+0.015
 launchers+0.015
agy+0.015
Neg logit contributions
nown-0.018
 smear-0.018
 undercover-0.016
 rival-0.015
below-0.015
Token 211
Token ID28714
Feature activation-3.50e-04

Pos logit contributions
nown+0.003
 smear+0.003
 undercover+0.003
 rival+0.003
below+0.003
Neg logit contributions
rek-0.003
ercise-0.003
iaries-0.003
 launchers-0.003
 Views-0.003