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

    Neuronpedia

    INDEX
    Explanations

    terms related to arrogance and inflated self-importance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ">//
    -0.60
    DockStyle
    -0.59
    .*")]
    -0.59
    __(/*!
    -0.55
    mogorov
    -0.53
    orteur
    -0.52
    idopsis
    -0.51
     joindre
    -0.50
    prepareStatement
    -0.50
    ']}
    -0.49
    POSITIVE LOGITS
     bragging
    1.10
     arrogant
    1.04
     cocky
    1.03
     arrogance
    0.94
    Ego
    0.91
     ego
    0.90
     brag
    0.90
     pride
    0.90
     Pride
    0.86
     Ego
    0.86
    Act Density 0.029%

    No Known Activations