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

    Neuronpedia

    INDEX
    Explanations

    expressions and behavior related to social manipulation and attempting to impress others

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

    impressing or pleasing others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.47
    клопе
    -0.39
     sababu
    -0.38
    ContentAsync
    -0.35
    IGraphics
    -0.34
    Datuak
    -0.34
    ]$}
    -0.33
    writeFieldEnd
    -0.33
    IntoConstraints
    -0.33
     cause
    -0.32
    POSITIVE LOGITS
    urbo
    0.50
    centiles
    0.48
    formance
    0.48
    Pyx
    0.47
     pleasing
    0.46
    mobileqq
    0.44
    quisites
    0.44
    Trick
    0.43
    ouille
    0.43
    ✭✭
    0.43
    Act Density 0.062%

    No Known Activations