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

    Neuronpedia

    INDEX
    Explanations

    various types of parentheses and related punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -2.75
     Efq
    -2.71
     itſelf
    -2.63
    ^(@)
    -2.40
     himſelf
    -2.37
     Jefus
    -2.35
     Theſe
    -2.33
     Monfieur
    -2.31
     themſelves
    -2.28
     purpoſe
    -2.27
    POSITIVE LOGITS
     (
    2.58
    (
    1.41
     -
    1.37
    <eos>
    1.36
     ((
    1.32
     [
    1.29
    -(
    1.27
    ,
    1.26
    .
    1.26
    /
    1.26
    Act Density 0.644%

    No Known Activations