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

    Neuronpedia

    INDEX
    Explanations

    repeated patterns or sequences that involve the use of commas and numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     $#
    -0.57
    ’
    -0.55
    -
    -0.52
     Reis
    -0.52
     كومونز
    -0.51
     Mari
    -0.51
    '
    -0.51
    es
    -0.50
    Glas
    -0.49
     Tur
    -0.48
    POSITIVE LOGITS
     Roskov
    1.29
    +#+#
    1.10
    */),
    1.00
    Personendaten
    0.96
    '}),
    0.95
     صوتيه
    0.93
     >=",
    0.90
    ,:);
    0.90
    ']],
    0.90
     للاسماء
    0.88
    Act Density 0.208%

    No Known Activations