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

    Neuronpedia

    INDEX
    Explanations

    instances of formal document structure or specific formatting commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.64
     (
    -0.55
     â
    -0.54
     a
    -0.53
     "
    -0.51
     /
    -0.48
    esa
    -0.48
     �
    -0.46
     ,
    -0.46
    ot
    -0.46
    POSITIVE LOGITS
    <bos>
    3.14
    '
    1.35
    ’
    1.34
     Савезне
    1.34
     المعيارى
    1.16
     فريبيس
    1.12
    ########.
    1.10
     Мексичка
    1.06
    begin
    1.04
     Paglinawan
    0.96
    Act Density 0.291%

    No Known Activations