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

    Neuronpedia

    INDEX
    Explanations

    statements of opinion or critique related to governance and policy issues

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

    Sentences starting with a quotation mark

    np_acts-logits-general · gemini-2.0-flash

    criticism or questions about actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kadang
    -0.63
     occasionally
    -0.62
     Occasionally
    -0.61
     Sometimes
    -0.60
    Sometimes
    -0.60
     sometimes
    -0.59
    Portail
    -0.59
     ibland
    -0.58
    sometimes
    -0.57
     déterminé
    -0.55
    POSITIVE LOGITS
     why
    0.87
     neither
    0.86
     seharusnya
    0.85
     Зачем
    0.81
     Shouldn
    0.81
    shame
    0.79
    Shouldn
    0.79
     Shame
    0.79
     shame
    0.78
     taxpayers
    0.78
    Act Density 0.451%

    No Known Activations