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

    Neuronpedia

    INDEX
    Explanations

    words or short phrases indicating reasoning or causality.

    oai_token-act-pair · gemini-2.0-flash

    French words

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.73
    :✨
    -0.72
    StoryboardSegue
    -0.69
    databinding
    -0.68
     محفوظة
    -0.66
    RetentionPolicy
    -0.63
    الحياه
    -0.63
     насељу
    -0.62
    NOPQRST
    -0.62
    ArrowToggle
    -0.61
    POSITIVE LOGITS
     abstrait
    0.57
     firſt
    0.57
     itſelf
    0.54
     producteurs
    0.53
     duquel
    0.52
     leſs
    0.52
     africain
    0.51
     biologique
    0.50
     scolas
    0.50
     spirituale
    0.50
    Act Density 3.555%

    No Known Activations