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

    Neuronpedia

    INDEX
    Explanations

    terms related to identification and uniqueness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wan
    -0.15
    igua
    -0.15
     Chance
    -0.14
    ç²¾ç¥ŀ
    -0.14
    outers
    -0.14
    788
    -0.14
    IfExists
    -0.13
    ongan
    -0.13
    chten
    -0.13
    798
    -0.13
    POSITIVE LOGITS
     libertin
    0.17
    анов
    0.16
     ÑģобÑĸ
    0.15
    artz
    0.14
     длÑı
    0.14
     Temporary
    0.14
     based
    0.14
    ál
    0.14
     temporary
    0.14
    dma
    0.14
    Act Density 0.747%

    No Known Activations