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

    Neuronpedia

    INDEX
    Explanations

    words related to exceeding, passing, or overtaking certain values or quantities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surpassing or exceeding thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     loc
    -0.74
    atto
    -0.69
    abet
    -0.67
    iott
    -0.64
    pring
    -0.61
    ogy
    -0.61
    orm
    -0.59
    endale
    -0.59
    Premium
    -0.59
     Relief
    -0.58
    POSITIVE LOGITS
    peak
    0.76
    =>
    0.71
    Beat
    0.68
    frog
    0.67
    stood
    0.66
    İĭ
    0.63
     Hugo
    0.63
    Ń·
    0.63
     hers
    0.62
    beat
    0.62
    Act Density 0.092%

    No Known Activations