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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal standards and conditions of liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.94
     becauſe
    -0.94
    Autoritní
    -0.86
     виправивши
    -0.86
     pleaſure
    -0.84
     مشين
    -0.84
     ſeveral
    -0.83
     Monfieur
    -0.82
     myſelf
    -0.82
     uſed
    -0.82
    POSITIVE LOGITS
     could
    0.58
     warrant
    0.56
     de
    0.55
     enough
    0.53
    足以
    0.52
     war
    0.52
     des
    0.52
     пор
    0.51
     actually
    0.51
    geno
    0.50
    Act Density 0.249%

    No Known Activations