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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and safety issues

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.87
     ModelExpression
    -0.83
     initComponents
    -0.73
     noqa
    -0.71
     مشين
    -0.71
    InjectAttribute
    -0.69
    awtextra
    -0.67
    urlpatterns
    -0.67
    Begriffsklä
    -0.66
     שוליים
    -0.66
    POSITIVE LOGITS
    pubmed
    0.57
     research
    0.56
     health
    0.54
     scientific
    0.54
     scientifically
    0.52
     sauter
    0.52
     studies
    0.51
    νώ
    0.51
    Scientific
    0.49
    乱
    0.48
    Act Density 0.247%

    No Known Activations