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

    Neuronpedia

    INDEX
    Explanations

    numeric values and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.81
     Jefus
    -1.79
     Efq
    -1.79
     Monfieur
    -1.73
     purpoſe
    -1.69
     Reſ
    -1.69
     pleaſure
    -1.67
     Theſe
    -1.66
     myſelf
    -1.65
     uſed
    -1.62
    POSITIVE LOGITS
     of
    0.82
     in
    0.71
     I
    0.70
    <bos>
    0.70
     -
    0.69
    '
    0.68
     ma
    0.68
     E
    0.67
     /
    0.67
     "
    0.66
    Act Density 1.694%

    No Known Activations