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

    Neuronpedia

    INDEX
    Explanations

    the presence of symbols or special characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    that
    -0.17
     THAT
    -0.16
    That
    -0.15
    	that
    -0.15
    thag
    -0.14
     that
    -0.14
     That
    -0.14
    _that
    -0.14
    éĤ£éĩĮ
    -0.14
    alah
    -0.13
    POSITIVE LOGITS
     different
    0.39
     various
    0.35
    different
    0.29
     Different
    0.29
     Various
    0.27
     each
    0.27
    ä¸įåIJĮ
    0.26
     these
    0.26
     this
    0.25
    Different
    0.25
    Act Density 0.030%

    No Known Activations