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

    Neuronpedia

    INDEX
    Explanations

    instances of the number "ten"

    oai_token-act-pair · gpt-3.5-turbo

    the word "ten" and phrases related to quantities or measurements of ten

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.75
    ller
    -0.70
    HY
    -0.69
    btn
    -0.65
    uberty
    -0.64
    hammad
    -0.63
    Reviewed
    -0.61
    LCS
    -0.60
    ramid
    -0.59
    igslist
    -0.59
    POSITIVE LOGITS
    aciously
    1.27
    acious
    1.19
    acity
    1.12
    uous
    1.10
    fold
    1.04
     thousand
    1.02
    uously
    1.01
    ieth
    0.95
    ured
    0.94
    eenth
    0.91
    Act Density 0.008%

    No Known Activations