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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    other
    0.60
    self
    0.59
    this
    0.56
    excellent
    0.55
    homme
    0.55
    номер
    0.54
    Fight
    0.54
    🐈
    0.53
     wod
    0.52
     এইসব
    0.52
    POSITIVE LOGITS
     By
    0.88
    By
    0.72
     BY
    0.70
     Andrew
    0.68
     Patrick
    0.67
     Paul
    0.66
     Oleh
    0.65
     Writer
    0.64
     oleh
    0.63
     Matthew
    0.63
    Act Density 0.000%

    No Known Activations