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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "dozen"

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities around a dozen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hra
    -0.75
    uria
    -0.67
    î
    -0.67
    ppers
    -0.65
    estine
    -0.63
     mathemat
    -0.63
    ICO
    -0.62
    otto
    -0.62
    Reviewer
    -0.62
    claimed
    -0.61
    POSITIVE LOGITS
    uously
    1.01
     thousand
    1.00
     Thousand
    0.96
     dozen
    0.96
    dozen
    0.92
    uous
    0.88
     consecutive
    0.84
    acity
    0.81
     iterations
    0.80
    aciously
    0.78
    Act Density 0.015%

    No Known Activations