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

    Neuronpedia

    INDEX
    Explanations

    tones of humor and charm in interactions and descriptions

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

    Positive personality traits

    np_acts-logits-general · gemini-2.0-flash

    positive personality traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    felves
    -0.69
    WithIOException
    -0.60
    ArgumentParser
    -0.56
    Mistake
    -0.53
    regierung
    -0.52
    aarrggbb
    -0.52
     mahdollis
    -0.51
     subgoal
    -0.50
     paž
    -0.50
    IBOutlet
    -0.49
    POSITIVE LOGITS
     charisma
    0.96
     personality
    0.94
     charm
    0.93
     warmth
    0.82
     infectious
    0.81
     presence
    0.78
     wit
    0.77
    personality
    0.76
     personnalité
    0.75
     personalidad
    0.75
    Act Density 0.153%

    No Known Activations