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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating a degree of superiority or excess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irim
    -0.15
    outu
    -0.15
    ic
    -0.15
    ESS
    -0.15
    omer
    -0.15
    uty
    -0.15
    inalg
    -0.14
    rou
    -0.14
    gun
    -0.14
    pot
    -0.14
    POSITIVE LOGITS
     usual
    0.14
     dozen
    0.14
     ever
    0.14
    rát
    0.14
    ahn
    0.13
    793
    0.13
    azor
    0.13
    á»ķ
    0.13
    ToFront
    0.13
     sinking
    0.13
    Act Density 0.041%

    No Known Activations