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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engin
    -0.14
    vid
    -0.13
    uzzi
    -0.13
     diff
    -0.13
     sparing
    -0.13
     gy
    -0.13
    rodu
    -0.13
    lass
    -0.13
     wid
    -0.13
     Hog
    -0.12
    POSITIVE LOGITS
     current
    0.18
    current
    0.18
    what
    0.16
     exactly
    0.16
     whats
    0.16
     Ø¢ÙĨÚĨÙĩ
    0.15
     currently
    0.15
    ç¿Ķ
    0.15
    ìĭ
    0.14
    currently
    0.14
    Act Density 0.012%

    No Known Activations