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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placement within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utsch
    -0.17
    usses
    -0.15
    sted
    -0.15
    dsa
    -0.14
    onis
    -0.14
    reb
    -0.14
    fen
    -0.14
    itled
    -0.14
    rosse
    -0.14
    aben
    -0.14
    POSITIVE LOGITS
     Hull
    0.17
     Pv
    0.15
    uhl
    0.15
    ÙĤب
    0.15
     Mayer
    0.15
    icator
    0.14
    먹
    0.14
     legit
    0.14
    ãĥ¼ãĤ¹
    0.13
    alı
    0.13
    Act Density 0.006%

    No Known Activations