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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate legal proceedings or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sud
    -0.52
    غي
    -0.50
     strict
    -0.50
    væ
    -0.48
     var
    -0.48
    iers
    -0.47
     read
    -0.46
    ob
    -0.46
    iores
    -0.45
     set
    -0.44
    POSITIVE LOGITS
     שוליים
    0.80
     فريبيس
    0.80
     esternos
    0.79
     onBind
    0.78
     مرئيه
    0.75
    StoryboardSegue
    0.74
     ब्रेकडाउन
    0.74
    kuuta
    0.74
     препратки
    0.74
    hopped
    0.70
    Act Density 1.334%

    No Known Activations