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

    Neuronpedia

    INDEX
    Explanations

    specific names related to literature

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Huxley" and variations related to his work or legacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hir
    -0.68
     relief
    -0.66
     peanuts
    -0.65
     bases
    -0.62
     Anchorage
    -0.62
     point
    -0.61
     standing
    -0.60
     footing
    -0.60
     flush
    -0.59
     credibility
    -0.59
    POSITIVE LOGITS
    ux
    4.73
    UX
    2.65
    aux
    1.43
    uxe
    1.38
    ix
    1.28
    lux
    1.25
    uc
    1.18
    udeau
    1.14
    uce
    1.14
    uf
    1.13
    Act Density 0.011%

    No Known Activations