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

    Neuronpedia

    INDEX
    Explanations

    references to literary or artistic works

    oai_token-act-pair · gpt-3.5-turbo

    references to various works, particularly artistic, literary, or composed works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Adin
    -0.78
    SPONSORED
    -0.75
    antha
    -0.75
    wcs
    -0.73
     Ukrain
    -0.69
     Rohing
    -0.63
    angular
    -0.62
    pora
    -0.62
    ACP
    -0.62
    berries
    -0.62
    POSITIVE LOGITS
    hops
    1.59
    paces
    1.44
    heet
    1.18
    pace
    1.11
    flows
    1.01
    bench
    0.98
    hirt
    0.97
    icle
    0.97
    aday
    0.96
    fare
    0.95
    Act Density 0.063%

    No Known Activations