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

    Neuronpedia

    INDEX
    Explanations

    elements that emphasize suggestions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NDEBUG
    -0.76
     متعلقه
    -0.73
    ValueStyle
    -0.71
     nakalista
    -0.67
     ModelExpression
    -0.66
    IndentedString
    -0.66
     unplayable
    -0.62
     Theſe
    -0.62
     ویکی‌پدیا
    -0.61
     GenerationType
    -0.60
    POSITIVE LOGITS
     good
    0.97
     common
    0.96
     excellent
    0.95
     great
    0.93
     obvious
    0.82
     easy
    0.81
     easiest
    0.80
     umum
    0.78
     sure
    0.77
     ottimo
    0.76
    Act Density 0.266%

    No Known Activations