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

    Neuronpedia

    INDEX
    Explanations

    messages about personal feelings and relationships

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

    Darroti

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

    spots first- and second-person pronouns and other self-/addressee-focused words (e.g., "I", "you", "we", "do") indicating speaker-directed or conversational language.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.59
    liferay
    -0.54
    findpost
    -0.52
     useAppContext
    -0.47
    richTextPanel
    -0.46
    complexContent
    -0.45
    LookAnd
    -0.44
     NSCoder
    -0.44
     oč
    -0.44
    AntiForgeryToken
    -0.43
    POSITIVE LOGITS
     Taktlose
    0.42
    DoubleQuotes
    0.37
    deselect
    0.36
     angel
    0.36
     анге
    0.35
     ComVisible
    0.35
    angel
    0.35
    nan
    0.35
     igång
    0.34
     MonoBehaviour
    0.34
    Act Density 0.248%

    No Known Activations