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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal claims and liabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.49
     GenerationType
    -0.47
    :✨
    -0.43
    featureID
    -0.40
     guer
    -0.40
     ویکی‌پدی
    -0.39
     Empires
    -0.39
     jsPsych
    -0.39
    SerializedName
    -0.38
    sidemargin
    -0.38
    POSITIVE LOGITS
     reasonably
    1.06
    reasonably
    0.92
     reasonable
    0.89
    Reasonable
    0.79
     Reasonable
    0.79
     raisonnable
    0.78
    reasonable
    0.78
     REASON
    0.71
     substantially
    0.71
     substantial
    0.68
    Act Density 2.962%

    No Known Activations