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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures indicating quantities or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ë¨
    -0.15
    biên
    -0.15
     ifndef
    -0.15
     ëĦ¤ìĿ´íĬ¸
    -0.15
    ëĿ¼íĶ¼
    -0.14
    ëĶĶìĭľ
    -0.14
    fragistics
    -0.14
    ì§Ģëħ¸
    -0.14
    _Lean
    -0.13
    ëŁ
    -0.13
    POSITIVE LOGITS
    âĢ¦↵
    0.14
     Tr
    0.14
     Mang
    0.14
     âĢ¦↵
    0.14
     a
    0.13
     McCorm
    0.13
     an
    0.13
     sequentially
    0.13
    ocol
    0.12
     N
    0.12
    Act Density 0.015%

    No Known Activations