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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and abbreviations of company or organizational names

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cca
    -0.64
    tons
    -0.63
    chuk
    -0.63
    gie
    -0.62
    private
    -0.61
     Franks
    -0.60
    unia
    -0.59
    ordering
    -0.58
     Vaugh
    -0.58
    rum
    -0.56
    POSITIVE LOGITS
    WORK
    1.25
    OLOGY
    1.24
    MENT
    1.24
    ODE
    1.21
    ING
    1.18
    ATA
    1.17
    FIELD
    1.15
    LEY
    1.15
    ON
    1.14
    IFIED
    1.14
    Act Density 0.196%

    No Known Activations