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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "ultra"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "ultra" or "high" specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilage
    -0.74
    icative
    -0.66
    ication
    -0.65
     Cosponsors
    -0.64
    icator
    -0.63
    ez
    -0.63
    cific
    -0.62
    icating
    -0.62
     Bleach
    -0.60
    Interstitial
    -0.59
    POSITIVE LOGITS
    fine
    1.03
    orthodox
    0.96
    charged
    0.90
    ples
    0.87
    ordinary
    0.87
    fast
    0.85
    Fine
    0.83
     violet
    0.81
    visor
    0.80
    mega
    0.80
    Act Density 0.034%

    No Known Activations