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

    Neuronpedia

    INDEX
    Explanations

    global rankings or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical rankings and comparisons across various categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avez
    -0.67
    erent
    -0.67
    ypes
    -0.64
    arten
    -0.63
    amples
    -0.63
    tsy
    -0.63
    Submit
    -0.63
    ries
    -0.62
    obyl
    -0.62
    idy
    -0.62
    POSITIVE LOGITS
     surpass
    1.26
     trailing
    1.21
     boasting
    1.17
    behind
    1.09
     eclips
    1.08
     surpassed
    1.07
     averaging
    1.05
     beating
    1.05
     topping
    1.03
     comprising
    0.97
    Act Density 0.237%

    No Known Activations