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

    Neuronpedia

    INDEX
    Explanations

    references to statistical peaks in data distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jo
    -0.63
    rath
    -0.63
     '
    -0.62
    ordano
    -0.60
     try
    -0.58
    .........
    -0.57
    仕
    -0.57
    Kot
    -0.56
    ...
    -0.56
     Granger
    -0.55
    POSITIVE LOGITS
     peak
    2.78
     peaks
    2.61
     Peak
    2.60
    Peak
    2.57
    peak
    2.48
     PEAK
    2.40
     Peaks
    2.28
     peaking
    2.12
    peaks
    2.11
     peaked
    1.96
    Act Density 0.102%

    No Known Activations