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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence termination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.65
     a
    -0.64
     (
    -0.57
      
    -0.57
     The
    -0.52
     essentially
    -0.52
     {
    -0.52
    ↵
    -0.52
     an
    -0.51
     any
    -0.51
    POSITIVE LOGITS
    <bos>
    2.48
     виправивши
    1.02
    ’
    1.01
    Билгалдахарш
    1.01
    ########.
    1.01
     Baillargeon
    1.01
    ագրություններ
    0.99
    HomeAsUpEnabled
    0.95
    '
    0.93
     utafitiHapana
    0.92
    Act Density 0.219%

    No Known Activations