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

    Neuronpedia

    INDEX
    Explanations

    references to the creator of various works or products

    oai_token-act-pair · gpt-3.5-turbo

    references to creators and their contributions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.70
    ishops
    -0.66
     scrut
    -0.64
    olit
    -0.64
    auna
    -0.62
    UGE
    -0.61
    abb
    -0.61
    eat
    -0.61
    romy
    -0.60
    vor
    -0.59
    POSITIVE LOGITS
    ãĤº
    0.84
    creator
    0.84
     creator
    0.82
    ãĥ´
    0.81
    ãĤ´
    0.80
    ãĤ¼
    0.79
    ãĥ¼ãĥĨãĤ£
    0.77
    ãĤ½
    0.75
    ãĥķãĤ¡
    0.75
    ãĥł
    0.75
    Act Density 0.026%

    No Known Activations