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

    Neuronpedia

    INDEX
    Explanations

    addressing the reader using the term "Dear" in a document

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize reader engagement and community involvement with the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anski
    -0.77
     Niet
    -0.70
    fman
    -0.64
     Pearce
    -0.63
     Tarant
    -0.61
     replay
    -0.61
     Atkinson
    -0.60
    ''.
    -0.59
     Hitchcock
    -0.58
    enegger
    -0.58
    POSITIVE LOGITS
     Gutenberg
    0.85
    à¤
    0.74
    Untitled
    0.69
     Reader
    0.68
    Reader
    0.67
    taboola
    0.67
     mornings
    0.66
    Daily
    0.66
     Scrolls
    0.65
    Independent
    0.64
    Act Density 0.016%

    No Known Activations