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

    Neuronpedia

    INDEX
    Explanations

    references to the speaker's personal experiences and emotions

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

    first-person singular pronouns

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

    Instances of first-person self-reference — tokens that mark the speaker referring to themselves (personal perspective/possession).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     transfieras
    -0.70
     ویکی‌پدیا
    -0.68
     kasarigan
    -0.65
     surla
    -0.65
     autorytatywna
    -0.64
    Kjelder
    -0.64
     JpaRepository
    -0.62
     Wiktionnaire
    -0.60
    
    -0.58
    AnimationsModule
    -0.58
    POSITIVE LOGITS
    kasse
    0.42
    blad
    0.37
    PAG
    0.35
     cabra
    0.35
    è
    0.34
     مختلف
    0.34
     Wittenberg
    0.33
    isk
    0.33
     בו
    0.33
     Abend
    0.33
    Act Density 0.237%

    No Known Activations