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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing a unique or particular characteristic

    oai_token-act-pair · gpt-3.5-turbo

    statements of identity or characteristic attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peoples
    -0.69
     Cheong
    -0.69
     Deaths
    -0.68
    ffe
    -0.67
    ainers
    -0.65
    heny
    -0.64
     Saud
    -0.64
    isions
    -0.63
     Guys
    -0.63
    inav
    -0.62
    POSITIVE LOGITS
     supposed
    1.18
    nt
    1.03
     meant
    0.97
     neither
    0.96
     indistinguishable
    0.95
     otherwise
    0.94
     destined
    0.94
     compatible
    0.93
     remotely
    0.92
     supposedly
    0.90
    Act Density 0.217%

    No Known Activations