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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "use" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "use" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inas
    -0.77
    alos
    -0.71
    yip
    -0.70
    ccording
    -0.70
    arious
    -0.69
    apult
    -0.66
    doms
    -0.65
    ilater
    -0.65
    inosaur
    -0.64
    ighth
    -0.64
    POSITIVE LOGITS
    ppe
    0.86
    ibility
    0.83
    fully
    0.77
    llo
    0.75
    ãĥ¯
    0.70
    mble
    0.69
    fulness
    0.66
    package
    0.65
    UID
    0.64
    Ùĩ
    0.63
    Act Density 0.034%

    No Known Activations