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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     oatmeal
    0.99
     bullying
    0.94
     apologized
    0.91
     anorexia
    0.90
     whining
    0.90
     vandalism
    0.90
     nervousness
    0.89
     bullied
    0.89
     startled
    0.86
     gobl
    0.86
    POSITIVE LOGITS
    с
    0.86
    т
    0.80
    м
    0.76
    ा
    0.76
    снов
    0.68
    жен
    0.67
    нутри
    0.66
    y
    0.66
    erce
    0.66
    aar
    0.65
    Act Density 0.000%

    No Known Activations