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

    Neuronpedia

    INDEX
    Explanations

    numerical values that represent years or statistics in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    200
    -0.23
    199
    -0.22
    202
    -0.21
    198
    -0.19
    ing
    -0.19
    иÑħ
    -0.16
    asu
    -0.16
    196
    -0.15
    kk
    -0.15
    ot
    -0.15
    POSITIVE LOGITS
     ÙħÛĮÙĦادÛĮ
    0.24
    âĢ³
    0.18
    Ø¡
    0.17
    âĢ²
    0.15
     Dün
    0.15
    ä¹Ī
    0.15
    uitka
    0.15
     edition
    0.15
    ÛĮÛĮÙĨ
    0.14
    atoi
    0.14
    Act Density 0.180%

    No Known Activations