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

    Neuronpedia

    INDEX
    Explanations

    negative emotional responses and unfortunate events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uche
    -0.17
    ô
    -0.17
    浩
    -0.15
    raquo
    -0.14
    icao
    -0.14
    vasion
    -0.14
    /umd
    -0.14
    uchs
    -0.14
    umi
    -0.13
    respect
    -0.13
    POSITIVE LOGITS
     Mig
    0.15
    uide
    0.14
    ncia
    0.14
    indsight
    0.14
    anton
    0.14
     Shirley
    0.13
    laden
    0.13
    arde
    0.13
    adin
    0.13
    باش
    0.13
    Act Density 0.261%

    No Known Activations