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

    Neuronpedia

    INDEX
    Explanations

    Russian Cyrillic characters, possibly related to text encoding

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "о" and similar Cyrillic characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clover
    -0.92
    esville
    -0.85
    hyde
    -0.79
    ologically
    -0.79
    secut
    -0.73
    ometimes
    -0.72
    raints
    -0.71
    eele
    -0.69
    irable
    -0.69
     Ada
    -0.69
    POSITIVE LOGITS
    Ñ
    1.21
    ÑĢ
    1.18
    е
    1.18
    н
    1.14
    ÑĤ
    1.13
    Ñģ
    1.11
    о
    1.09
    и
    1.04
     Ð
    1.01
    Ñı
    1.00
    Act Density 0.003%

    No Known Activations