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

    Neuronpedia

    INDEX
    Explanations

    references to news sources or citation styles in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.75
    yip
    -0.72
    halla
    -0.61
     Pryor
    -0.60
     leagues
    -0.60
     Spartans
    -0.60
    onics
    -0.59
     Bones
    -0.59
     hairs
    -0.59
     cush
    -0.58
    POSITIVE LOGITS
    aido
    0.71
     withd
    0.70
    onductor
    0.69
    ilo
    0.68
    meta
    0.67
    oros
    0.67
    ATT
    0.66
    UTC
    0.66
     tremend
    0.65
    Rand
    0.64
    Act Density 0.065%

    No Known Activations