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

    characters and symbols from a non-Latin script, possibly related to a specific language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.83
    oche
    -0.79
    issance
    -0.77
    hedral
    -0.76
    bee
    -0.76
    ench
    -0.76
    cker
    -0.76
    leground
    -0.75
    undai
    -0.74
    ndra
    -0.73
    POSITIVE LOGITS
    а
    1.28
    и
    1.27
    оÐ
    1.22
    е
    1.21
    о
    1.14
    ÑĢ
    1.09
    ÑĮ
    1.09
    Ñĭ
    1.05
    м
    1.05
    н
    1.03
    Act Density 0.010%

    No Known Activations