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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gob
    -0.73
     bol
    -0.72
    apo
    -0.71
    undo
    -0.71
    weet
    -0.71
     simul
    -0.70
     SB
    -0.69
    irtual
    -0.69
    tu
    -0.65
    pa
    -0.64
    POSITIVE LOGITS
    Dialogue
    1.10
    pmwiki
    0.86
    Dead
    0.78
     unlaw
    0.73
    Stretch
    0.72
    Rh
    0.72
    ALSE
    0.72
    Sham
    0.71
    OTOS
    0.70
    UFF
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.