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

    Neuronpedia

    INDEX
    Explanations

    the number "four" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "four"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idence
    -0.68
     Happ
    -0.66
    Fed
    -0.66
    UGE
    -0.65
     Rica
    -0.64
    isky
    -0.63
    UTION
    -0.63
    ller
    -0.61
    reference
    -0.61
    LER
    -0.60
    POSITIVE LOGITS
    teenth
    1.87
    teen
    1.86
     hundred
    1.12
    eenth
    1.11
    some
    1.10
    een
    1.06
    aciously
    1.03
    square
    1.00
    acious
    0.92
    fif
    0.92
    Act Density 0.049%

    No Known Activations