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

    Neuronpedia

    INDEX
    Explanations

    numerical values and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡tÃŃ
    -0.15
    ucas
    -0.15
     Hunger
    -0.14
    uyết
    -0.14
    esor
    -0.14
    FRING
    -0.14
    ifar
    -0.14
    SOR
    -0.13
    yles
    -0.13
     COPYRIGHT
    -0.13
    POSITIVE LOGITS
    OTS
    0.15
     Wen
    0.15
     Paz
    0.15
    rej
    0.14
    oden
    0.14
     rit
    0.14
    endale
    0.14
    reich
    0.14
    ereum
    0.13
    lassian
    0.13
    Act Density 0.044%

    No Known Activations