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

    Neuronpedia

    INDEX
    Explanations

    references to legal arguments and justifications regarding behavior and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words indicating justification and legitimacy

    np_acts-logits-general · gemini-2.0-flash

    justification or legitimacy of actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peggio
    -0.44
     radical
    -0.42
    epam
    -0.41
     principal
    -0.40
     jLabel
    -0.39
    innerHTML
    -0.38
    парта
    -0.38
     \
    -0.38
     H
    -0.37
     &
    -0.37
    POSITIVE LOGITS
     harmless
    1.15
     innocently
    1.07
     legitimate
    0.95
    Билгалдахарш
    0.88
    GEBURTSDATUM
    0.86
     jspb
    0.86
     justifiable
    0.85
     justified
    0.85
     InputDecoration
    0.85
     مشين
    0.84
    Act Density 0.573%

    No Known Activations