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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transitions, beginnings, or changes in context or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dst
    -0.15
    ActionCreators
    -0.15
    abbo
    -0.14
     mechan
    -0.14
    STS
    -0.14
    otts
    -0.14
    صب
    -0.14
    .must
    -0.14
    CharArray
    -0.14
    getto
    -0.14
    POSITIVE LOGITS
    ÙĦÙģ
    0.16
    ARAM
    0.16
    itty
    0.15
    igy
    0.15
    essen
    0.15
    ald
    0.14
    aldi
    0.14
    indr
    0.14
     Threads
    0.14
    Threads
    0.14
    Act Density 0.200%

    No Known Activations