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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to assertiveness and dominance in behavior

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

    aggressive, assertive, intrusive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.53
    ✨:
    -0.45
     mxArray
    -0.43
     Weeknd
    -0.43
     smtplib
    -0.43
     OnInit
    -0.42
    Erfolge
    -0.41
    curacies
    -0.41
     Erhaltung
    -0.41
    hmig
    -0.41
    POSITIVE LOGITS
     aggressive
    0.91
    Aggressive
    0.85
     Aggressive
    0.84
     aggressively
    0.77
     aggres
    0.77
    aggressive
    0.75
     obnoxious
    0.73
     aggressiveness
    0.71
     assertive
    0.70
     intrusive
    0.69
    Act Density 0.041%

    No Known Activations