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

    Neuronpedia

    INDEX
    Explanations

    quotations that start with the word "one."

    oai_token-act-pair · gpt-3.5-turbo

    the word "one" in various contexts related to individuals and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fighters
    -0.67
    ooks
    -0.66
    folk
    -0.63
     probabilities
    -0.63
    hips
    -0.61
    ãĤµ
    -0.61
    inders
    -0.60
     pathogens
    -0.60
     patterns
    -0.59
     lifestyles
    -0.59
    POSITIVE LOGITS
     hundred
    0.94
     Hundred
    0.89
     thousand
    0.76
     million
    0.75
    Ħ¢
    0.75
    idas
    0.74
     hour
    0.73
     Thousand
    0.71
    Shot
    0.70
    India
    0.69
    Act Density 0.133%

    No Known Activations