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

    Neuronpedia

    INDEX
    Explanations

    terms related to accuracy and error in diagnostics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     motivadoras
    -0.78
     decorativos
    -0.77
     artísticas
    -0.69
     decorativas
    -0.64
     médicaux
    -0.64
     financières
    -0.63
     acrylique
    -0.62
     graciosas
    -0.60
     navideñas
    -0.60
     educativas
    -0.59
    POSITIVE LOGITS
     twos
    0.76
     Silvers
    0.73
     yellows
    0.73
     whites
    0.72
     thirds
    0.69
     threes
    0.69
     reds
    0.68
     greens
    0.68
    CppMethod
    0.67
     longs
    0.67
    Act Density 0.765%

    No Known Activations