Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "of" preceded or followed by nouns referring to units or components of a whole.

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HasFactory
    -1.02
    SequentialGroup
    -0.94
     Efq
    -0.80
     autorytatywna
    -0.79
    LookAnd
    -0.78
     IBOutlet
    -0.73
    AndEndTag
    -0.73
     jadx
    -0.72
    semantics
    -0.71
     صوتيه
    -0.70
    POSITIVE LOGITS
     τέ
    0.45
    hle
    0.45
    '
    0.44
     blevet
    0.43
     pure
    0.42
    ظيم
    0.42
     The
    0.42
     an
    0.41
    lained
    0.41
    )$_
    0.41
    Act Density 1.343%

    No Known Activations