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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Connecticut
    0.88
     superstitious
    0.87
     heartwarming
    0.85
     carefree
    0.84
    ation
    0.82
     hazy
    0.82
     cramped
    0.81
     reckless
    0.80
     erratic
    0.80
     recklessly
    0.80
    POSITIVE LOGITS
    âtres
    0.75
    扇
    0.72
    ilde
    0.70
    ANDE
    0.70
    ن
    0.70
    imise
    0.69
     Peres
    0.69
     utilizz
    0.68
    andez
    0.68
    هِ
    0.67
    Act Density 0.000%

    No Known Activations