INDEX
Explanations
This neuron detects mentions of individuals “alone,” particularly in the phrase describing someone living alone.
New Auto-Interp
Negative Logits
xFB
-0.07
snippet
-0.07
.member
-0.07
HIGH
-0.07
Parade
-0.06
FAILED
-0.06
destac
-0.06
نیروی
-0.06
+:
-0.06
_week
-0.06
POSITIVE LOGITS
일반
0.08
减
0.06
اساسی
0.06
일반
0.06
sound
0.06
Vision
0.06
따
0.06
cerr
0.06
################################################
0.06
tel
0.06
Activations Density 0.000%