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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and parentheses, in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ons
    -0.16
    ings
    -0.14
    lett
    -0.14
    -ÑĤо
    -0.14
    Ñĥд
    -0.14
     respective
    -0.14
    lets
    -0.14
    -↵↵
    -0.13
    aille
    -0.13
    agan
    -0.13
    POSITIVE LOGITS
    s
    0.32
    Ùĩ
    0.21
    samp
    0.19
    y
    0.18
    sian
    0.18
    EndInit
    0.16
    ãĤĪãģĨãģª
    0.16
    i
    0.16
    a
    0.16
    à¸Ħ
    0.16
    Act Density 0.296%

    No Known Activations