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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical arrangements and placements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ür
    -0.16
    iffe
    -0.14
    ÄĽr
    -0.13
     bfd
    -0.13
    Minute
    -0.13
    CTest
    -0.13
    erif
    -0.13
    UFFIX
    -0.12
    ëĿ¼ëıĦ
    -0.12
     Faster
    -0.12
    POSITIVE LOGITS
     horizontal
    0.31
     vertically
    0.28
     vertical
    0.28
     horizontally
    0.28
     upside
    0.27
     flush
    0.26
     upright
    0.26
     next
    0.26
    horizontal
    0.26
     flat
    0.25
    Act Density 0.251%

    No Known Activations