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

    Neuronpedia

    INDEX
    Explanations

    websites or internet URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs or website links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.80
     Prohibition
    -0.66
     ageing
    -0.64
     conclud
    -0.61
     eleph
    -0.60
    ailability
    -0.58
     Lowell
    -0.57
     aging
    -0.57
    oreAnd
    -0.56
     Revolutionary
    -0.55
    POSITIVE LOGITS
    /_
    0.80
    ffee
    0.78
    //
    0.76
    /)
    0.76
    /#
    0.75
    cdn
    0.75
    \/
    0.73
    /,
    0.72
    verage
    0.71
    à
    0.70
    Act Density 0.006%

    No Known Activations