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

    Neuronpedia

    INDEX
    Explanations

    expressions of arrogance and inflated self-image in individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    œurs
    -0.52
     useContext
    -0.43
    دانشنامهٔ
    -0.39
    TableBody
    -0.39
     tortuga
    -0.38
     muualla
    -0.38
     CommonModule
    -0.38
     utafitiHapana
    -0.37
    conexao
    -0.37
     разобра
    -0.36
    POSITIVE LOGITS
     pride
    0.86
     proudly
    0.82
     bragging
    0.80
     brag
    0.80
     proud
    0.79
     boast
    0.77
    pride
    0.77
     claim
    0.76
     arrog
    0.75
    proud
    0.73
    Act Density 0.315%

    No Known Activations