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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lenker
    -0.69
     فريبيس
    -0.67
     betweenstory
    -0.59
     <>",
    -0.59
     invokingState
    -0.54
     صوتيه
    -0.53
     poveznice
    -0.51
    ãng
    -0.50
     Karo
    -0.50
    ftagPool
    -0.50
    POSITIVE LOGITS
     .
    1.04
    (.
    0.91
     '.
    0.91
    ('.
    0.90
    //.
    0.80
    ;->
    0.76
     ".
    0.76
    ','.
    0.75
    .$.
    0.75
    <.
    0.73
    Act Density 0.032%

    No Known Activations