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

    Neuronpedia

    INDEX
    Explanations

    punctuations and spacing patterns in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.24
     ÑģобÑĭ
    -0.19
     Lance
    -0.16
     sooner
    -0.15
     based
    -0.15
    arty
    -0.15
     Sawyer
    -0.14
    at
    -0.14
     if
    -0.14
     индивидÑĥ
    -0.14
    POSITIVE LOGITS
     а
    0.22
     ÑĩÑĤобÑĭ
    0.22
     ÑĤо
    0.18
     бÑĥд
    0.17
     ÑĢавно
    0.17
     lesbische
    0.17
     бÑĥдÑĮ
    0.16
    اذ
    0.16
    ÑĤак
    0.16
    бÑĥдÑĮ
    0.16
    Act Density 0.018%

    No Known Activations