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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptions of large quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.64
     Skies
    -0.55
    rame
    -0.54
    ovies
    -0.50
    ebus
    -0.50
    ots
    -0.48
    abad
    -0.47
    wolves
    -0.46
    ĻĤ
    -0.46
    asted
    -0.46
    POSITIVE LOGITS
     of
    1.12
    Of
    0.79
     OF
    0.79
     Of
    0.77
     thereof
    0.75
     (>
    0.70
    OF
    0.66
    of
    0.64
    enance
    0.63
    lust
    0.60
    Act Density 0.179%

    No Known Activations