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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     alarming
    0.83
    表现
    0.79
     unsettling
    0.77
    стан
    0.76
    䣼
    0.76
    㖦
    0.75
    㕧
    0.75
    áis
    0.75
    逺
    0.74
     의미
    0.74
    POSITIVE LOGITS
     who
    0.84
     acceptors
    0.82
    Survivor
    0.82
    legten
    0.81
     cruised
    0.80
     दूसरी
    0.80
     ganger
    0.80
    shuffle
    0.80
    illegal
    0.78
     booklet
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.