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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating pauses or emotional emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HeaderCode
    -0.14
    âng
    -0.13
    ëĶĶìĭľ
    -0.13
    __).
    -0.13
    )(__
    -0.13
    ива
    -0.13
    (DBG
    -0.13
    IDDEN
    -0.13
    éli
    -0.13
    ĶåĽŀ
    -0.12
    POSITIVE LOGITS
     ;
    0.16
     Petersburg
    0.16
     com
    0.15
    amu
    0.15
    631
    0.14
    cke
    0.13
    ERRU
    0.13
    º
    0.13
     ag
    0.13
     gov
    0.13
    Act Density 0.018%

    No Known Activations