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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and file management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regular
    -0.14
    oha
    -0.14
     whirl
    -0.14
    its
    -0.13
     balk
    -0.13
    odo
    -0.13
    amo
    -0.13
    our
    -0.13
    æĦı
    -0.13
     AN
    -0.12
    POSITIVE LOGITS
    سÙĪب
    0.17
    archives
    0.16
     ëĺIJíķľ
    0.15
    Malloc
    0.14
    ynchronously
    0.14
    icaret
    0.14
    curity
    0.14
    eldon
    0.14
    ç¿°
    0.14
    èĬĻ
    0.14
    Act Density 0.160%

    No Known Activations