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

    Neuronpedia

    INDEX
    Explanations

    mathematical statements discussing conditions and existence of certain properties or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Explicit
    -0.16
    ÃŃd
    -0.14
    uje
    -0.14
     blinds
    -0.14
     Òij
    -0.13
    etter
    -0.13
    lust
    -0.13
     explicit
    -0.13
    IDEO
    -0.13
    rollo
    -0.13
    POSITIVE LOGITS
     every
    0.31
     Every
    0.24
    every
    0.23
    enever
    0.23
     there
    0.23
     necessarily
    0.21
    Every
    0.21
     ogni
    0.20
    æ¯ı
    0.19
    rane
    0.17
    Act Density 0.182%

    No Known Activations