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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quoted speech or attribution

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

    attributed speech or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.44
     Manten
    -0.42
     Boven
    -0.40
     amistad
    -0.39
     Gerechtigkeit
    -0.38
     convivencia
    -0.36
     réalise
    -0.36
     démarrer
    -0.36
     Wahrheit
    -0.36
     paix
    -0.35
    POSITIVE LOGITS
     quoted
    0.61
     quotes
    0.58
     quoting
    0.57
    quoted
    0.57
     Quoted
    0.56
     quotations
    0.52
    NameInMap
    0.52
    Quotes
    0.52
    Quoted
    0.51
    Autoritní
    0.50
    Act Density 0.005%

    No Known Activations