INDEX
Explanations
words and phrases related to authority and presence
New Auto-Interp
Negative Logits
compass
-0.17
arna
-0.16
ames
-0.16
ammad
-0.15
mes
-0.15
mess
-0.15
ær
-0.14
صات
-0.14
amac
-0.14
adr
-0.14
POSITIVE LOGITS
§
0.17
_ios
0.17
ungi
0.16
ouch
0.16
akh
0.15
ļ
0.15
nte
0.14
MENT
0.14
reeNode
0.14
bie
0.14
Activations Density 0.036%