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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to violations of laws or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolled
    -0.15
    ollapsed
    -0.15
    iao
    -0.15
    ropp
    -0.14
    Úĺ
    -0.14
    azen
    -0.14
    iá»ģn
    -0.13
    ji
    -0.13
    FlatButton
    -0.13
     yetiÅŁ
    -0.13
    POSITIVE LOGITS
     Buckley
    0.18
    ease
    0.17
     conv
    0.17
    ustin
    0.15
    emy
    0.14
    Å¡ek
    0.14
    asmus
    0.14
     utter
    0.14
    Ring
    0.14
    feas
    0.14
    Act Density 0.008%

    No Known Activations