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

    Neuronpedia

    INDEX
    Explanations

    references to gender and variations of existence or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ispers
    -0.14
    arena
    -0.14
    æľŁ
    -0.14
    onica
    -0.14
    reib
    -0.14
     Cure
    -0.14
    erb
    -0.13
    Ñģли
    -0.13
    ellular
    -0.13
    Äįan
    -0.13
    POSITIVE LOGITS
    /AFP
    0.15
     alike
    0.15
    itaire
    0.15
     Millenn
    0.14
    ulously
    0.14
    chair
    0.14
    GES
    0.14
    ngör
    0.14
    bette
    0.14
     Sho
    0.14
    Act Density 0.080%

    No Known Activations