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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and matrix operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edException
    -0.18
    amar
    -0.16
    loe
    -0.15
     Gale
    -0.15
    agit
    -0.15
    ientes
    -0.14
    entes
    -0.14
    Ģ
    -0.14
    essel
    -0.14
     Synd
    -0.13
    POSITIVE LOGITS
    ÑĢеÑģÑĤ
    0.15
     dear
    0.15
    apore
    0.14
     Boot
    0.14
    boot
    0.14
     wrappers
    0.14
     boot
    0.14
    UNT
    0.13
    robat
    0.13
     pornstar
    0.13
    Act Density 0.007%

    No Known Activations