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

    Neuronpedia

    INDEX
    Explanations

    statistical comparisons involving quantities and ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æľį
    -0.15
    orum
    -0.15
    PLY
    -0.14
    ropa
    -0.14
     Balls
    -0.14
     Anime
    -0.14
    UBLE
    -0.13
    оÑĩки
    -0.13
    PTS
    -0.13
    ignon
    -0.13
    POSITIVE LOGITS
     every
    0.28
     Every
    0.23
    every
    0.23
    Every
    0.22
    æ¯ı
    0.21
     ogni
    0.20
    _every
    0.18
     hver
    0.17
     æ¯ı
    0.17
     ratio
    0.15
    Act Density 0.096%

    No Known Activations