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

    Neuronpedia

    INDEX
    Explanations

    the number "dozen" occurring as part of a count

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities, specifically the word "dozen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estine
    -0.78
    bro
    -0.76
    ICO
    -0.73
    usher
    -0.71
    ainer
    -0.71
    earch
    -0.69
    iner
    -0.68
    claimed
    -0.65
    hra
    -0.65
    inth
    -0.63
    POSITIVE LOGITS
     thousand
    1.12
     dozen
    0.97
    uously
    0.91
     hundred
    0.90
     Thousand
    0.89
     consecutive
    0.87
    uous
    0.85
    acity
    0.84
    fold
    0.82
     different
    0.80
    Act Density 0.043%

    No Known Activations