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

    Neuronpedia

    INDEX
    Explanations

    terms related to dictionaries or encyclopedias

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of dictionaries and encyclopedias

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psey
    -0.86
    atem
    -0.77
    ayed
    -0.74
    rity
    -0.72
    sent
    -0.72
    ayer
    -0.72
    roach
    -0.71
    estic
    -0.69
    chell
    -0.69
    acas
    -0.69
    POSITIVE LOGITS
     Dictionary
    1.25
    ãĥĥãĤ¯
    0.97
    ãĥ¼ãĥĨãĤ£
    0.96
     dictionary
    0.93
     Encyclopedia
    0.91
     Britann
    0.80
     encyclopedia
    0.79
     Dram
    0.79
    ictionary
    0.78
    cloth
    0.72
    Act Density 0.012%

    No Known Activations