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

    Neuronpedia

    INDEX
    Explanations

    references to the number "eight"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "eight."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hammad
    -0.71
    UGE
    -0.69
     srf
    -0.69
     Rica
    -0.64
    Fed
    -0.64
     Palestin
    -0.62
    rison
    -0.62
    itivity
    -0.61
    atem
    -0.60
     depended
    -0.60
    POSITIVE LOGITS
    een
    1.57
    eenth
    1.54
    teen
    1.26
    teenth
    1.14
    ieth
    1.07
     hundred
    0.99
     months
    0.97
    fif
    0.93
    aciously
    0.90
    fold
    0.87
    Act Density 0.017%

    No Known Activations