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

    Neuronpedia

    INDEX
    Explanations

    descriptions of arrogance and inflated self-importance

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

    arrogance and ego

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JpaRepository
    -0.48
    verwijspagina
    -0.46
     disambiguazione
    -0.44
    참고
    -0.43
     useDispatch
    -0.42
    ungszeit
    -0.41
    illerato
    -0.40
    ngths
    -0.39
    Derbyniad
    -0.39
     Wochenende
    -0.38
    POSITIVE LOGITS
     arrogant
    0.68
     cocky
    0.63
     arrog
    0.62
     haughty
    0.60
     arrogance
    0.58
     ego
    0.57
     narciss
    0.56
     proud
    0.54
    proud
    0.54
     egos
    0.53
    Act Density 0.152%

    No Known Activations