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

    Neuronpedia

    INDEX
    Explanations

    references to policy changes and legal actions related to social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĺ¯ä¸Ģ个
    -0.20
    æīĢæľī
    -0.18
    çļĦä¸Ģ个
    -0.18
     모ëĵł
    -0.16
     sebuah
    -0.15
     twice
    -0.15
     vešker
    -0.15
     another
    -0.14
     tüm
    -0.14
    ä»»ä½ķ
    -0.14
    POSITIVE LOGITS
     either
    0.55
    either
    0.45
     Either
    0.43
    Either
    0.39
     various
    0.39
     varying
    0.38
     либо
    0.38
     EITHER
    0.37
     respectively
    0.36
     respective
    0.34
    Act Density 0.648%

    No Known Activations