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

    Neuronpedia

    INDEX
    Explanations

    words expressing degrees of intensity or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esterno
    -0.54
     baga
    -0.53
    itolo
    -0.52
     Industries
    -0.50
    liggende
    -0.50
    ISTR
    -0.49
     Gat
    -0.49
     chân
    -0.48
     containing
    -0.48
     saling
    -0.48
    POSITIVE LOGITS
     very
    0.81
    sizeCache
    0.71
    orianCalendar
    0.70
     extraordinarily
    0.69
     Мексичка
    0.69
    tagHelperRunner
    0.69
     incredibly
    0.66
    EndContext
    0.66
     Lightboxes
    0.66
    nonatomic
    0.64
    Act Density 0.341%

    No Known Activations