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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to timestamps or time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sal
    -0.18
    chte
    -0.17
     Altern
    -0.16
     Down
    -0.16
     altern
    -0.15
     digit
    -0.15
     Er
    -0.14
    endez
    -0.14
    Down
    -0.14
     Bl
    -0.14
    POSITIVE LOGITS
    íĥľ
    0.17
     太
    0.16
    heit
    0.15
     geri
    0.15
    /epl
    0.15
    /autoload
    0.15
    awi
    0.14
     ков
    0.14
    .codes
    0.14
    PCODE
    0.14
    Act Density 0.012%

    No Known Activations