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

    Neuronpedia

    INDEX
    Explanations

    words related to size or quantity, particularly emphasizing that something is 'large enough'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sufficient size or capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guth
    -0.79
    Brow
    -0.71
    amily
    -0.70
    bull
    -0.70
    misc
    -0.66
    zl
    -0.65
    analysis
    -0.64
    cot
    -0.63
    anton
    -0.63
    tell
    -0.63
    POSITIVE LOGITS
    hots
    0.67
     quantities
    0.63
     ILCS
    0.62
     persuasive
    0.61
    andem
    0.61
     sidx
    0.61
     doses
    0.59
    rehend
    0.59
    -+-+
    0.58
     detectable
    0.58
    Act Density 0.021%

    No Known Activations