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

    Neuronpedia

    INDEX
    Explanations

    the number 10 or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ten"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.72
     Indust
    -0.69
     jerk
    -0.63
    à¼
    -0.62
    Downloadha
    -0.62
     Bind
    -0.59
    hammad
    -0.58
    ****************
    -0.58
    ARDS
    -0.57
    igslist
    -0.57
    POSITIVE LOGITS
    aciously
    1.36
    acious
    1.29
    acity
    1.20
    uous
    1.17
    ured
    1.14
    fold
    1.07
    uously
    1.07
     thousand
    1.06
    eenth
    0.97
    ieth
    0.96
    Act Density 0.027%

    No Known Activations