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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     '[
    -0.16
    enson
    -0.15
     '
    -0.15
     ‘
    -0.14
     Lastly
    -0.14
    olio
    -0.14
    ibli
    -0.14
    ologic
    -0.14
    LOAT
    -0.14
    -esque
    -0.13
    POSITIVE LOGITS
     uh
    0.17
     okay
    0.17
    Okay
    0.16
    okay
    0.16
     already
    0.16
     Marx
    0.15
    ampus
    0.15
    sort
    0.15
    OK
    0.15
    ãĥ»ãĥ»ãĥ»↵↵
    0.15
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.