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

    Neuronpedia

    INDEX
    Explanations

    references to political ideology and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __*/
    -0.84
     kasarigan
    -0.70
     betweenstory
    -0.69
    ParallelGroup
    -0.65
     المعيارى
    -0.63
    Демографія
    -0.62
    ArrowToggle
    -0.61
     Audiodateien
    -0.60
    RegressionTest
    -0.60
    DotNetBar
    -0.60
    POSITIVE LOGITS
     NSCoder
    0.60
     inderdaad
    0.55
     ligiloj
    0.49
    WriteAttribute
    0.48
    LEncoder
    0.48
    //</
    0.47
    긴
    0.46
    translator
    0.46
    UnknownFields
    0.46
    وزن
    0.45
    Act Density 0.546%

    No Known Activations