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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     in
    1.08
     on
    0.89
     from
    0.86
     has
    0.86
    berg
    0.85
    flies
    0.85
     was
    0.84
     didn
    0.84
     в
    0.83
     volunteers
    0.83
    POSITIVE LOGITS
     enorme
    0.92
    εις
    0.82
    Atoi
    0.82
     проблеми
    0.78
    Да
    0.78
     ogrom
    0.78
    這一
    0.77
    ﻝ
    0.75
    Entonces
    0.75
    NewLabel
    0.74
    Act Density 0.679%

    No Known Activations