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

    Neuronpedia

    INDEX
    Explanations

    strong opinions on social issues, particularly in political contexts.

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

    discussion regarding literature and politics.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    names of authors or experts being cited, particularly when followed by verbs like "says", "writes", "argues", or "concludes".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Statements or opinions

    np_acts-logits-general · gemini-2.0-flash

    authors making statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.79
    RectangleBorder
    -0.78
     وتسجيلات
    -0.76
    BufferException
    -0.76
    CodeAttribute
    -0.75
    Према
    -0.72
    AnimationsModule
    -0.72
    GEBURTSDATUM
    -0.71
    protoc
    -0.70
     ModelExpression
    -0.69
    POSITIVE LOGITS
     writes
    0.88
     wrote
    0.83
     pointed
    0.81
     points
    0.71
     write
    0.69
     writing
    0.68
     argues
    0.68
     argued
    0.66
     rightly
    0.66
     cites
    0.65
    Act Density 0.428%

    No Known Activations