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

    Neuronpedia

    INDEX
    Explanations

    sentence-ending punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.64
    ↵↵
    -0.61
    "
    -0.55
     (
    -0.53
    [
    -0.50
    !
    -0.50
    (
    -0.50
     The
    -0.49
    $
    -0.48
     &
    -0.47
    POSITIVE LOGITS
    ſelves
    1.00
     itſelf
    0.99
     myſelf
    0.95
    ſelf
    0.93
     pleaſure
    0.89
     themſelves
    0.89
    Tikang
    0.85
    writeFieldEnd
    0.83
    -------------</
    0.82
    ArgsConstructor
    0.82
    Act Density 0.195%

    No Known Activations