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

    Neuronpedia

    INDEX
    Explanations

    underscore characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رÙĬر
    -0.17
     ëĭ¤ìļ´ë°Ľê¸°
    -0.15
    undred
    -0.14
    erap
    -0.14
     zaz
    -0.14
    _charset
    -0.14
    activ
    -0.14
    ä¸įäºĨ
    -0.14
    tha
    -0.13
     Fallen
    -0.13
    POSITIVE LOGITS
    па
    0.15
     foul
    0.15
    uby
    0.14
     вÑĸÑĢ
    0.14
    letes
    0.14
    اث
    0.14
    ĺ
    0.14
    grim
    0.14
    landa
    0.14
    bies
    0.14
    Act Density 0.027%

    No Known Activations