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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating excess or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¸ģ
    -0.17
    ÑĤеÑģÑĮ
    -0.16
    /her
    -0.15
    emas
    -0.15
    erv
    -0.15
    ustr
    -0.15
    sets
    -0.15
    sh
    -0.14
    ErrorException
    -0.14
    erva
    -0.14
    POSITIVE LOGITS
    edList
    0.19
    lying
    0.17
    /down
    0.17
    ture
    0.16
    heard
    0.16
    -the
    0.16
    enga
    0.15
    took
    0.15
    hang
    0.15
    /in
    0.15
    Act Density 0.145%

    No Known Activations