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

    Neuronpedia

    INDEX
    Explanations

    common initials used in names or titles

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns, particularly those related to people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤº
    -0.82
    264
    -0.76
    263
    -0.74
    266
    -0.73
    udic
    -0.73
    262
    -0.73
     Americ
    -0.72
     Tycoon
    -0.72
    ãĤ¦ãĤ¹
    -0.71
     Democracy
    -0.68
    POSITIVE LOGITS
    h
    1.29
    har
    1.17
    H
    1.14
    hw
    1.11
    haw
    1.08
     HL
    1.04
    HM
    1.02
    hs
    1.01
    HT
    1.01
    HK
    1.00
    Act Density 0.247%

    No Known Activations