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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of political or social divisions and their implications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.81
    MLLoader
    -0.73
    [])
    -0.71
    DoubleQuotes
    -0.69
    interopRequire
    -0.68
    Билгалдахарш
    -0.67
     propOrder
    -0.66
    цездатний
    -0.65
    ChildScrollView
    -0.63
     '>=
    -0.58
    POSITIVE LOGITS
     segregation
    0.50
    แตก
    0.50
     разли
    0.50
     écl
    0.48
     static
    0.46
     demarcation
    0.45
     separation
    0.45
     制
    0.45
     forskj
    0.44
     Static
    0.42
    Act Density 0.339%

    No Known Activations