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

    Neuronpedia

    INDEX
    Explanations

    phrases related to borders, limits, or extremes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to boundaries or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quel
    -0.87
    SourceFile
    -0.74
    externalActionCode
    -0.69
    reau
    -0.69
    apest
    -0.68
    lead
    -0.68
     istg
    -0.67
    ily
    -0.67
    BILL
    -0.65
     Cosponsors
    -0.65
    POSITIVE LOGITS
     humanity
    0.80
     civilisation
    0.79
     civilization
    0.78
     sanity
    0.76
     legality
    0.72
     imagination
    0.72
     decency
    0.69
     humankind
    0.69
     academia
    0.69
     Appalach
    0.69
    Act Density 0.200%

    No Known Activations