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

    Neuronpedia

    INDEX
    Explanations

    specific sequences related to AMD RYZEN processors

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'Y'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ities
    -0.85
    ciating
    -0.75
    itures
    -0.75
    icable
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.70
    entimes
    -0.69
    icably
    -0.67
     Cortana
    -0.67
    byter
    -0.66
     encryption
    -0.65
    POSITIVE LOGITS
    STEM
    1.10
    ield
    1.01
    ORK
    0.97
    EAR
    0.97
    outh
    0.96
    PE
    0.95
    ELL
    0.94
    outube
    0.93
    ARD
    0.93
    ANK
    0.92
    Act Density 0.027%

    No Known Activations