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

    Neuronpedia

    INDEX
    Explanations

    suggestive language and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     immemorial
    -0.74
    Biografía
    -0.72
    fortawesome
    -0.71
    STEIN
    -0.71
    Wal
    -0.69
    parfum
    -0.69
    MathML
    -0.68
     Wal
    -0.68
     dalamnya
    -0.68
    forName
    -0.68
    POSITIVE LOGITS
     suggestions
    1.44
     SUGGEST
    1.43
     suggested
    1.35
     suggest
    1.33
    ugges
    1.33
     Sugges
    1.31
    Suggest
    1.31
    SUGGEST
    1.30
     suggests
    1.29
     Suggestions
    1.29
    Act Density 0.078%

    No Known Activations