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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "comments" and variations of it in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comment sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zet
    -0.37
     vital
    -0.37
    Disco
    -0.36
    labelledby
    -0.35
    quelize
    -0.34
     Bri
    -0.34
    principalColumn
    -0.34
    extAlignment
    -0.34
     Bot
    -0.34
     Jap
    -0.34
    POSITIVE LOGITS
    Comments
    2.45
     Comments
    2.05
    comments
    1.77
     COMMENTS
    1.63
    COMMENTS
    1.55
     Comment
    1.53
    Comment
    1.52
     comments
    1.52
     comment
    1.33
    comment
    1.32
    Act Density 0.007%

    No Known Activations