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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and their syntax used in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.98
    +#+#
    -0.93
     الحره
    -0.76
    AndEndTag
    -0.73
     ویکی‌پدی
    -0.71
    msgSender
    -0.71
    aarrggbb
    -0.69
     ProtoMessage
    -0.66
     propOrder
    -0.66
    routeProvider
    -0.65
    POSITIVE LOGITS
     Basing
    0.56
    ')}}"
    0.53
    往
    0.52
     FX
    0.51
     "\<
    0.51
     vengeance
    0.50
    asInstanceOf
    0.49
     dress
    0.48
     visually
    0.48
     dier
    0.48
    Act Density 0.016%

    No Known Activations