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

    Neuronpedia

    INDEX
    Explanations

    significant changes in status or levels over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADIUS
    -0.15
    iji
    -0.15
    unger
    -0.15
    aders
    -0.14
     Advisors
    -0.14
    ityEngine
    -0.14
     Spieler
    -0.14
    antor
    -0.14
     Rug
    -0.13
    uib
    -0.13
    POSITIVE LOGITS
     peak
    0.88
    peak
    0.71
     Peak
    0.70
    Peak
    0.70
     peaks
    0.66
    _peak
    0.57
     peaked
    0.54
     Peaks
    0.51
     height
    0.44
    /Peak
    0.43
    Act Density 0.166%

    No Known Activations