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

    Neuronpedia

    INDEX
    Explanations

    prominent names and influential figures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yarış
    -0.52
     bosco
    -0.49
    IsContent
    -0.48
     Murillo
    -0.48
     escolar
    -0.47
     unfinished
    -0.47
    ↘
    -0.46
     universitario
    -0.46
     engelsk
    -0.46
     knihy
    -0.45
    POSITIVE LOGITS
     figures
    0.81
     stalwart
    0.75
     figure
    0.74
    figures
    0.72
    stays
    0.71
     Figures
    0.70
    icône
    0.68
    ReusableCell
    0.68
    pulumi
    0.67
     figuras
    0.67
    Act Density 0.256%

    No Known Activations