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

    Neuronpedia

    INDEX
    Explanations

    instances of menu item additions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antee
    -0.15
    izon
    -0.14
     Rash
    -0.14
    oppable
    -0.14
    amarin
    -0.14
    hee
    -0.14
    EST
    -0.14
    stants
    -0.14
    ulen
    -0.14
    θÎŃ
    -0.14
    POSITIVE LOGITS
    actionDate
    0.17
    rou
    0.16
    ITIVE
    0.15
    timeofday
    0.15
     Vader
    0.14
    /comment
    0.14
    ac
    0.14
     Spr
    0.14
    ÃŁ
    0.13
    rouch
    0.13
    Act Density 0.015%

    No Known Activations