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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic characters and specific letter combinations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character 'Ð'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    horn
    -0.73
    gate
    -0.72
     Meadows
    -0.71
     crossover
    -0.68
     Walker
    -0.67
    illard
    -0.67
     Hawkins
    -0.65
    walking
    -0.63
    walk
    -0.63
     Baylor
    -0.63
    POSITIVE LOGITS
     Ð
    3.90
    Ð
    2.49
    о
    1.94
    Ñ
    1.91
    Ñģ
    1.86
    м
    1.84
    ÑĤ
    1.83
    в
    1.82
    д
    1.78
    оÐ
    1.76
    Act Density 0.019%

    No Known Activations