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

    Neuronpedia

    INDEX
    Explanations

    certain punctuation marks, especially periods and slashes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     auffi
    -1.05
     myſelf
    -1.03
    ſelf
    -1.01
     itſelf
    -0.98
     pleaſure
    -0.95
    +#+#
    -0.95
    mybatisplus
    -0.94
     فريبيس
    -0.94
    ItemBackground
    -0.93
     ſtand
    -0.91
    POSITIVE LOGITS
     
    0.91
    Portale
    0.55
     "
    0.54
     “
    0.54
     L
    0.51
     i
    0.49
     (
    0.49
     +
    0.49
     Sal
    0.49
    /
    0.49
    Act Density 0.031%

    No Known Activations