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

    Neuronpedia

    INDEX
    Explanations

    terms related to categorization or classification processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to categorization and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.76
    perty
    -0.72
    elin
    -0.72
    orah
    -0.68
     homeland
    -0.67
     Tah
    -0.67
     ful
    -0.67
    rentice
    -0.66
     vig
    -0.65
    athi
    -0.63
    POSITIVE LOGITS
    anguage
    0.89
     classify
    0.86
    REDACTED
    0.83
    ifications
    0.83
    ostic
    0.82
    ifier
    0.82
     categor
    0.81
    ically
    0.81
    ourgeois
    0.80
    rill
    0.79
    Act Density 0.038%

    No Known Activations