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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and bibliographic details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inis
    -0.18
    ãĥ³ãĥIJãĥ¼
    -0.16
    Į
    -0.16
     ç¿
    -0.15
    ãĥ³ãĥģ
    -0.15
    ê´Ģ
    -0.15
    ilos
    -0.14
     Bates
    -0.13
    076
    -0.13
    ormal
    -0.13
    POSITIVE LOGITS
    strand
    0.17
    olland
    0.16
    orum
    0.15
    ione
    0.15
    olec
    0.14
    andes
    0.14
    æ£Ĵ
    0.14
    oksen
    0.14
    oux
    0.14
    addle
    0.14
    Act Density 0.048%

    No Known Activations