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

    Neuronpedia

    INDEX
    Explanations

    the sentence boundaries or sentence starting points in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "}},
    -0.63
    __(/*!
    -0.63
     
    -0.56
    topt
    -0.55
     التالي
    -0.54
    __',
    -0.54
     ?";
    -0.53
    jähriger
    -0.53
    ']],
    -0.52
    */),
    -0.52
    POSITIVE LOGITS
     Majefty
    0.74
     myſelf
    0.73
     Jefus
    0.72
     eenig
    0.72
     camicia
    0.71
     pleaſure
    0.71
     ſtate
    0.69
     fevere
    0.69
     raiſ
    0.69
     purpoſe
    0.69
    Act Density 0.160%

    No Known Activations