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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -1.07
     Efq
    -1.05
     becauſe
    -1.03
    PerformLayout
    -0.97
     Majefty
    -0.94
     Paglinawan
    -0.93
     Theſe
    -0.92
    -0.92
     pleaſure
    -0.92
     myſelf
    -0.91
    POSITIVE LOGITS
     '
    0.89
    "
    0.83
     ‘
    0.79
    ‘
    0.76
     "
    0.73
    '
    0.69
     ’
    0.68
    s
    0.68
    ”
    0.65
    t
    0.65
    Act Density 0.196%

    No Known Activations