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

    Neuronpedia

    INDEX
    Explanations

    verbs related to decision making and determination

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to decision-making and determination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.70
    ECD
    -0.64
    ACT
    -0.61
    inqu
    -0.61
    Sah
    -0.60
    vind
    -0.60
    AMY
    -0.59
    iva
    -0.59
    ľ
    -0.58
    GRE
    -0.58
    POSITIVE LOGITS
     which
    1.37
     Which
    1.35
     whether
    1.32
    Which
    1.32
     whom
    1.25
     where
    1.15
     whence
    1.14
     who
    1.13
     how
    1.10
     what
    1.08
    Act Density 0.485%

    No Known Activations