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

    Neuronpedia

    INDEX
    Explanations

    statistical significance indicators in research results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.83
     Theſe
    -0.82
     betweenstory
    -0.82
     itſelf
    -0.81
    ंदीखरीदारी
    -0.80
     Réponses
    -0.79
    Skocz
    -0.77
    новниш
    -0.77
    abestanden
    -0.77
     ―――――
    -0.77
    POSITIVE LOGITS
     “
    0.49
    posedge
    0.46
    op
    0.45
    ırken
    0.42
     giac
    0.41
     cabo
    0.40
    opf
    0.40
    ాని
    0.40
    bilecek
    0.38
     getopt
    0.38
    Act Density 0.037%

    No Known Activations