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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating quantities or effectiveness

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

    Follows the word "relatively"

    np_acts-logits-general · gemini-2.0-flash

    adjectives qualified by relatively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    -0.58
    <blockquote>
    -0.54
     incríveis
    -0.52
     essentiels
    -0.50
     tasche
    -0.50
     bellissimo
    -0.50
     viktig
    -0.48
     bellissima
    -0.48
    !
    -0.48
     increíbles
    -0.47
    POSITIVE LOGITS
    ResumeLayout
    0.93
     Relatively
    0.88
    relatively
    0.86
    ]--;
    0.85
     relatively
    0.83
    تقاوى
    0.83
    EDEFAULT
    0.83
    
    0.81
     propOrder
    0.81
     Мексичка
    0.80
    Act Density 0.134%

    No Known Activations