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

    Neuronpedia

    INDEX
    Explanations

    words that indicate correctness or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McKinnon
    -1.06
    Hauptartikel
    -0.99
    WireFormatLite
    -0.94
    __":
    -0.93
    CMYK
    -0.91
    matchCondition
    -0.90
    NameInMap
    -0.90
     okuyayım
    -0.88
    OSSARY
    -0.88
    MigrationBuilder
    -0.86
    POSITIVE LOGITS
    right
    1.29
     RIGHT
    1.29
     Right
    1.25
     right
    1.25
    Right
    1.21
    RIGHT
    1.18
    setRight
    1.08
    getRight
    1.00
     righ
    0.97
     Righ
    0.89
    Act Density 0.091%

    No Known Activations