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

    Neuronpedia

    INDEX
    Explanations

    terms related to discrimination in employment based on various protected characteristics

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

    demographic characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inSlope
    -0.49
    ApiOperation
    -0.48
     للاسماء
    -0.48
     <<<<<<<<<<<<<<
    -0.48
    ScopeManager
    -0.46
    -0.46
    elemField
    -0.45
    はじめに
    -0.44
     المعيارى
    -0.44
    DockStyle
    -0.43
    POSITIVE LOGITS
    sams
    0.40
    insatz
    0.38
    Искәрмәләр
    0.36
    trui
    0.36
     Module
    0.35
    ágenes
    0.35
    iconque
    0.34
     propOrder
    0.34
     vixion
    0.34
    这就是
    0.33
    Act Density 0.080%

    No Known Activations