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

    Neuronpedia

    INDEX
    Explanations

    words related to files or documents

    oai_token-act-pair · gpt-3.5-turbo

    words related to recyclable materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.00
    aido
    -0.86
    akening
    -0.83
    raviolet
    -0.79
    iversal
    -0.78
    icrobial
    -0.78
    keyes
    -0.73
    pai
    -0.72
    erion
    -0.71
    govtrack
    -0.71
    POSITIVE LOGITS
    mma
    0.82
    tto
    0.79
     Cheong
    0.73
     Nadu
    0.71
    ile
    0.70
     erection
    0.69
     paths
    0.66
    ILE
    0.65
     FTP
    0.63
     Oval
    0.62
    Act Density 0.007%

    No Known Activations