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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks and potential sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.38
     outcome
    -0.38
    “
    -0.37
     heat
    -0.37
     Fed
    -0.35
     sorte
    -0.34
     hig
    -0.34
     Oxford
    -0.34
     rot
    -0.34
     ger
    -0.34
    POSITIVE LOGITS
    UnusedPrivate
    0.69
    docx
    0.63
    DockStyle
    0.62
    脚注の使い方
    0.60
    jpg
    0.60
    com
    0.59
    exe
    0.59
    󠁿
    0.59
    TagMode
    0.59
    org
    0.58
    Act Density 1.129%

    No Known Activations