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

    Neuronpedia

    INDEX
    Explanations

    phrases that express user choices and experiences

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

    "can I" or "you" followed by a verb

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

    Finds first- and second-person expressions of agency (I/you), especially words indicating requests, intent, ability or actions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    UnitTesting
    -0.40
     consumers
    -0.39
    fotografía
    -0.38
     consommateurs
    -0.36
     Öffentlichkeit
    -0.35
     consumidor
    -0.35
     lección
    -0.35
     Zuschauer
    -0.35
     Consumers
    -0.35
     peringkat
    -0.34
    POSITIVE LOGITS
    mybatisplus
    0.63
     Мексичка
    0.56
    ModelAdmin
    0.49
    enterOuterAlt
    0.49
    aarrggbb
    0.49
    setVerticalGroup
    0.46
    tagHelperRunner
    0.44
    AutoModerator
    0.44
    Демографія
    0.44
     tong
    0.44
    Act Density 0.809%

    No Known Activations