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

    Neuronpedia

    INDEX
    Explanations

    informal expressions of frustration or humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    룹
    -0.15
    ноп
    -0.14
    leftright
    -0.14
    ToPoint
    -0.14
    ivery
    -0.14
    vů
    -0.14
    chner
    -0.14
    ToWorld
    -0.13
    enuity
    -0.13
    tram
    -0.13
    POSITIVE LOGITS
    etheless
    0.19
    ieee
    0.18
    iii
    0.17
    oooo
    0.15
     underst
    0.15
    pecially
    0.15
    erdings
    0.15
    oooooooo
    0.14
    identally
    0.14
    ually
    0.14
    Act Density 0.354%

    No Known Activations