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

    Neuronpedia

    INDEX
    Explanations

    JSON syntax elements, particularly strings and their delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »¿
    -0.17
    सल
    -0.16
    eger
    -0.15
     Abed
    -0.14
    ray
    -0.14
    rente
    -0.14
    íĥĪ
    -0.14
     trai
    -0.13
    uxe
    -0.13
    ffer
    -0.13
    POSITIVE LOGITS
    ly
    0.20
    ampo
    0.17
    ed
    0.16
    ëĭ¤
    0.15
    unta
    0.14
    ing
    0.14
    owan
    0.13
    esan
    0.13
    unting
    0.13
    n
    0.13
    Act Density 0.048%

    No Known Activations