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

    Neuronpedia

    INDEX
    Explanations

    words related to academic, scholarly, or research fields

    oai_token-act-pair · gpt-3.5-turbo

    references to various domains of study or disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.83
    bian
    -0.74
    iggle
    -0.69
    CRIP
    -0.69
    ILA
    -0.67
     Fas
    -0.66
     nodd
    -0.63
    ramid
    -0.62
    gements
    -0.62
    export
    -0.62
    POSITIVE LOGITS
     fields
    0.84
    field
    0.79
    onet
    0.78
     field
    0.75
    naires
    0.74
    fields
    0.72
    ftime
    0.70
    orer
    0.69
    ula
    0.69
    ouri
    0.68
    Act Density 0.020%

    No Known Activations