INDEX
Explanations
the word "Blair"
the name "Blair."
New Auto-Interp
Negative Logits
Magikarp
-0.91
Temperature
-0.74
ymes
-0.74
uality
-0.72
igators
-0.70
ensing
-0.70
Ģ
-0.69
ãĤº
-0.69
entric
-0.68
Trend
-0.68
POSITIVE LOGITS
Blair
1.08
anke
0.80
ite
0.80
oleon
0.79
ites
0.79
ufact
0.75
umenthal
0.75
anche
0.72
anches
0.71
ock
0.70
Activations Density 0.003%