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

    Neuronpedia

    INDEX
    Explanations

    names of people and their positions or titles

    oai_token-act-pair · gpt-3.5-turbo

    non-zero numerical values or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    course
    -0.70
     endeav
    -0.68
     intending
    -0.67
    xual
    -0.66
     sacrificing
    -0.64
     Penny
    -0.60
     dissu
    -0.60
     altogether
    -0.58
    cycles
    -0.57
    tt
    -0.57
    POSITIVE LOGITS
    WASHINGTON
    0.92
    ³³³³³³³³
    0.86
    ³³³
    0.86
    ccording
    0.86
    Published
    0.78
    Filename
    0.78
    Washington
    0.77
    posted
    0.77
    ramid
    0.77
    TOR
    0.76
    Act Density 0.348%

    No Known Activations