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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and expressions of personal experience

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

    "I" followed by a past-tense verb

    np_acts-logits-general · gemini-2.0-flash

    I followed by a communicative action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.97
     المعيارى
    -0.76
     وتسجيلات
    -0.71
    AutoresizingMask
    -0.65
     الحره
    -0.65
    InputBorder
    -0.57
     protoimpl
    -0.56
    ActionCreators
    -0.54
     MutableLiveData
    -0.53
    énario
    -0.53
    POSITIVE LOGITS
     wrote
    0.64
     mentioned
    0.62
     Wrote
    0.60
     asked
    0.57
     interviewed
    0.57
     contacted
    0.56
     talked
    0.56
    agers
    0.55
     alluded
    0.53
     spoke
    0.53
    Act Density 0.315%

    No Known Activations