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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code-related syntaxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acock
    -0.15
    ÎķÎ¥
    -0.15
    ait
    -0.15
    .sponge
    -0.15
    azı
    -0.14
    abbix
    -0.14
    tat
    -0.14
    aginator
    -0.14
    inka
    -0.14
    pras
    -0.14
    POSITIVE LOGITS
    weg
    0.16
    å®ĺ
    0.15
    501
    0.14
    売
    0.14
    HELL
    0.14
    mong
    0.14
    _ONCE
    0.14
    Passed
    0.14
    nde
    0.13
    iston
    0.13
    Act Density 0.316%

    No Known Activations