INDEX
Explanations
names of individuals associated with various contexts
New Auto-Interp
Negative Logits
ice
-0.15
486
-0.15
pers
-0.14
599
-0.14
front
-0.14
488
-0.14
oser
-0.13
å¾Ĵ
-0.13
eso
-0.13
ific
-0.13
POSITIVE LOGITS
adam
0.17
Ľ
0.16
sov
0.16
ombok
0.14
tü
0.14
onas
0.14
callee
0.14
adb
0.14
ckill
0.14
odash
0.14
Activations Density 0.017%