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

    Neuronpedia

    INDEX
    Explanations

    mentions of financial implications and risks associated with public projects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Danke
    -0.55
     المعيارى
    -0.53
    Nguyên
    -0.52
    FunctionFlags
    -0.48
     forme
    -0.46
     radiate
    -0.46
    Enlaces
    -0.46
     invokingState
    -0.46
    tained
    -0.46
    Obrázky
    -0.45
    POSITIVE LOGITS
    HtmlAttribute
    0.66
     préfé
    0.59
    ModelAttribute
    0.59
     muligt
    0.59
    batore
    0.57
    Tail
    0.57
     mourut
    0.57
    évaluateur
    0.56
     słucha
    0.56
    بوابة
    0.56
    Act Density 0.097%

    No Known Activations