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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     -
    0.65
     [
    0.60
     "/
    0.56
     spooky
    0.56
     you
    0.53
     intermediary
    0.53
     parks
    0.52
     espes
    0.52
     °
    0.51
     Round
    0.51
    POSITIVE LOGITS
    rbara
    0.53
    ्रेट
    0.52
    eningkatan
    0.50
    ברה
    0.50
    dives
    0.50
    etah
    0.48
    TextInput
    0.48
    真是
    0.48
    šan
    0.47
    iatan
    0.47
    Act Density 0.000%

    No Known Activations