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

    Neuronpedia

    INDEX
    Explanations

    textual structures, particularly punctuation and formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abcdefghijklmnop
    -0.14
    绣
    -0.14
    idding
    -0.14
    è³Ģ
    -0.13
     Heller
    -0.13
    egal
    -0.13
     ins
    -0.13
    nder
    -0.13
    ìĿ´ìħĺ
    -0.13
    ÙĩÙħ
    -0.12
    POSITIVE LOGITS
     Tags
    0.16
    malink
    0.15
    iaux
    0.14
    ĶåĽŀ
    0.14
    iado
    0.14
    ignum
    0.14
     Kaynak
    0.14
    obs
    0.14
    âĨIJ
    0.14
     Peyton
    0.14
    Act Density 0.511%

    No Known Activations