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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities associated with measurement or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.84
     Jefus
    -1.82
     Majefty
    -1.80
     Monfieur
    -1.76
     Reſ
    -1.73
     pleaſure
    -1.72
     purpoſe
    -1.71
     uſed
    -1.69
     Anſ
    -1.68
     myſelf
    -1.67
    POSITIVE LOGITS
     I
    0.84
     /
    0.81
     of
    0.81
     -
    0.77
     e
    0.76
     )
    0.76
     (
    0.75
     )
    0.75
     "
    0.73
     ]);
    0.73
    Act Density 1.701%

    No Known Activations