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

    Neuronpedia

    INDEX
    Explanations

    words related to "visibility" or similar concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to visual appearance or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.81
    ãĥ¤
    -0.75
     Malaysian
    -0.68
    Ö¼
    -0.65
    riage
    -0.64
     Buffett
    -0.62
    avanaugh
    -0.61
     Cosponsors
    -0.61
    rera
    -0.59
    dfx
    -0.59
    POSITIVE LOGITS
     vis
    1.15
     challeng
    1.06
     versa
    0.95
    ially
    0.80
    iors
    0.80
    uo
    0.79
    ibilities
    0.78
    cer
    0.78
    vim
    0.75
    ets
    0.74
    Act Density 0.006%

    No Known Activations