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

    Neuronpedia

    INDEX
    Explanations

    Russian Cyrillic characters

    oai_token-act-pair · gpt-3.5-turbo

    words or characters in a non-Latin script, particularly those related to the Cyrillic alphabet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ttes
    -0.84
     Starr
    -0.81
     Doe
    -0.73
     McMaster
    -0.68
     Petraeus
    -0.67
     Dayton
    -0.66
     Roe
    -0.66
     Nike
    -0.65
     Simpson
    -0.64
     Somers
    -0.64
    POSITIVE LOGITS
    Ñģ
    1.48
    ÑĤ
    1.37
    к
    1.30
    н
    1.20
    е
    1.16
    л
    1.14
    Ñı
    1.12
    в
    1.11
    м
    1.10
    и
    1.09
    Act Density 0.005%

    No Known Activations