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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific measure or quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "half."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reilly
    -0.70
    ayn
    -0.69
     Kimmel
    -0.67
    PLA
    -0.66
     Sweeney
    -0.63
    Marginal
    -0.61
     appropri
    -0.61
    ãĤ¡
    -0.59
    INGTON
    -0.58
    atively
    -0.57
    POSITIVE LOGITS
     dozen
    1.36
    dozen
    1.32
     thousand
    0.87
     handful
    0.85
     decade
    0.84
     century
    0.84
     hundred
    0.83
     million
    0.83
     continent
    0.79
     bunch
    0.79
    Act Density 0.025%

    No Known Activations