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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols not typically found in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hta
    -0.18
    rana
    -0.16
    ht
    -0.16
    ocking
    -0.16
    éģĵ
    -0.15
    iert
    -0.15
    cht
    -0.14
    apult
    -0.14
    ero
    -0.14
    ��
    -0.14
    POSITIVE LOGITS
    illac
    0.15
    ulence
    0.14
    TypeDef
    0.14
     seasons
    0.14
     tả
    0.14
    621
    0.14
    745
    0.13
    æŁ»
    0.13
     Season
    0.13
    ecies
    0.13
    Act Density 0.023%

    No Known Activations