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

    Neuronpedia

    INDEX
    Explanations

    citations and references from academic or research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lear
    -0.16
     sud
    -0.16
    duit
    -0.15
     èĢ
    -0.14
     Bradley
    -0.14
    usher
    -0.14
     refere
    -0.14
    ãĥ©ãĥ¼
    -0.14
     Sche
    -0.13
    uby
    -0.13
    POSITIVE LOGITS
    ITA
    0.16
    adows
    0.16
    ãĥ³ãĥĨãĤ£
    0.15
    irection
    0.14
    udad
    0.14
    adies
    0.14
    uhl
    0.14
     eskort
    0.14
    ewidth
    0.14
    åłĤ
    0.14
    Act Density 0.017%

    No Known Activations