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

    Neuronpedia

    INDEX
    Explanations

    discourse about social judgments and expectations

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

    people expressing opinions or actions

    np_acts-logits-general · gemini-2.5-flash-lite

    statements of opinion, judgment, or reported speech—language about what people think, say, or know, often in evaluative or argumentative contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Accept
    -0.44
    accept
    -0.44
     accept
    -0.43
    IContainer
    -0.39
     accepting
    -0.39
     Accept
    -0.39
     acep
    -0.37
     Accepting
    -0.36
     accep
    -0.36
     accepts
    -0.35
    POSITIVE LOGITS
    HasBeenSet
    0.57
    0.54
    BufferException
    0.54
    ArrowToggle
    0.54
    yntaxException
    0.53
    httphttps
    0.53
    InSection
    0.52
     okuyayım
    0.52
     يتيمه
    0.50
    Autoritní
    0.50
    Act Density 0.120%

    No Known Activations