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

    Neuronpedia

    INDEX
    Explanations

    the word "entirely" and its variations, indicating a strong emphasis on completeness or absoluteness

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

    entirely + qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mamp
    -0.51
     PPD
    -0.48
     cappuccio
    -0.48
     MATHEMATICAL
    -0.48
    wps
    -0.48
    Хьажоргаш
    -0.47
     perſon
    -0.47
     Verſ
    -0.47
     vand
    -0.47
     ſol
    -0.47
    POSITIVE LOGITS
     entirely
    1.48
     wholly
    1.00
     entièrement
    0.81
     purely
    0.80
     solely
    0.79
     geheel
    0.78
     gänzlich
    0.77
     sepenuhnya
    0.72
    entire
    0.70
     largely
    0.70
    Act Density 0.008%

    No Known Activations