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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    counter
    0.66
    ={'
    0.65
    esquerda
    0.62
    ldots
    0.60
    О
    0.58
    =
    0.57
    Counter
    0.57
    0
    0.56
    Single
    0.56
    される
    0.55
    POSITIVE LOGITS
     Getting
    0.77
     Attraction
    0.77
     Feeling
    0.76
     Unlike
    0.73
     Karma
    0.73
     那麼
    0.71
     Marissa
    0.70
     YouTuber
    0.70
     Coronavirus
    0.69
     我們
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.