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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.87
    </i>
    -0.84
    ه
    -0.84
    Marlene
    -0.77
    iastical
    -0.77
    rouvez
    -0.76
    </b>
    -0.75
    rrrr
    -0.75
     UITableView
    -0.75
     inder
    -0.74
    POSITIVE LOGITS
    tic
    1.09
    ANTIC
    0.99
     Brito
    0.93
    ic
    0.92
    IC
    0.91
    gic
    0.90
    thique
    0.90
    monic
    0.89
    lic
    0.87
     tonic
    0.86
    Act Density 0.148%

    No Known Activations