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

    Neuronpedia

    INDEX
    Explanations

    various forms of language and communication in written texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    &oacute
    -0.17
    Äĵ
    -0.16
    974
    -0.16
    Ä«
    -0.16
    úi
    -0.16
    æ¯
    -0.15
    ó
    -0.15
     al
    -0.15
    .sz
    -0.15
    ÑĢади
    -0.14
    POSITIVE LOGITS
     Ãł
    0.28
    Ãł
    0.27
    'Ãł
    0.22
     ÃĢ
    0.22
    Ãłn
    0.22
    ÃĢ
    0.21
    Ãłm
    0.20
     bÃł
    0.19
    ’Ãł
    0.19
     th
    0.18
    Act Density 0.015%

    No Known Activations