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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal beliefs and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.79
    writeFieldEnd
    -0.70
    frameCount
    -0.69
     AppColors
    -0.69
     >=",
    -0.67
     NSCoder
    -0.67
    MLLoader
    -0.66
    Portale
    -0.65
    ConfigureAwait
    -0.65
     ModelExpression
    -0.65
    POSITIVE LOGITS
    Because
    0.90
     because
    0.83
     Because
    0.83
     Perché
    0.76
    是因为
    0.75
    because
    0.74
     weil
    0.73
     Porque
    0.73
     porque
    0.72
     BECAUSE
    0.71
    Act Density 0.171%

    No Known Activations