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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods and questions marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isch
    -0.16
    ãĥ³ãĥĸ
    -0.16
    Å¡t
    -0.15
    sert
    -0.15
    -Bar
    -0.14
    etler
    -0.14
    vation
    -0.14
    emer
    -0.14
    oty
    -0.13
     etc
    -0.13
    POSITIVE LOGITS
    marvin
    0.14
    æĭĶ
    0.14
    evin
    0.14
    ãĥ¼ãĥª
    0.14
    inton
    0.13
    Ñħодим
    0.13
    è¡Ĺ
    0.13
    rogen
    0.13
     Innoc
    0.13
    ropoda
    0.13
    Act Density 0.333%

    No Known Activations