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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "saying" and its variants, indicating discussions or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    848
    -0.16
    isphere
    -0.15
     Abu
    -0.14
    aspers
    -0.14
     sleeves
    -0.14
     Schedule
    -0.14
    ira
    -0.14
     Kont
    -0.14
    574
    -0.13
    cott
    -0.13
    POSITIVE LOGITS
    inth
    0.17
    omers
    0.16
    radu
    0.16
    atore
    0.15
    stoff
    0.15
    .Fat
    0.14
    inch
    0.14
    dbName
    0.14
    orsch
    0.14
    ÑĤоÑĢ
    0.14
    Act Density 0.045%

    No Known Activations