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

    Neuronpedia

    INDEX
    Explanations

    Japanese names and terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to names or terms in a specific cultural or linguistic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Continental
    -0.70
     Scand
    -0.68
     Cind
    -0.65
    20439
    -0.65
     Integrity
    -0.63
     Develop
    -0.63
     Equip
    -0.63
     GOODMAN
    -0.62
    ications
    -0.61
    icators
    -0.61
    POSITIVE LOGITS
    pport
    1.16
    pta
    1.14
    hei
    1.10
    jin
    1.04
    seless
    1.01
    selage
    1.01
    pling
    1.01
    pload
    0.98
    ji
    0.97
    pei
    0.96
    Act Density 0.019%

    No Known Activations