INDEX
Explanations
learning
The neuron activates on occurrences of the phrase “machine learning” (and its close variants).
New Auto-Interp
Negative Logits
Emperor
-0.07
ギ
-0.07
\a
-0.07
スカ
-0.07
Paz
-0.07
"a
-0.07
Parker
-0.07
hobby
-0.06
Hyde
-0.06
discussing
-0.06
POSITIVE LOGITS
=L
0.08
ThanOrEqualTo
0.07
atural
0.07
lending
0.07
mainBundle
0.07
ml
0.07
-click
0.07
Rol
0.07
_JS
0.07
rell
0.06
Activations Density 0.014%