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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ret
    -0.39
     po
    -0.27
     meme
    -0.26
     reír
    -0.26
     defensa
    -0.26
     hors
    -0.26
     retourner
    -0.26
     rö
    -0.25
    릿
    -0.25
     bit
    -0.24
    POSITIVE LOGITS
    AddTagHelper
    0.85
    rungsseite
    0.67
    GEBURTSDATUM
    0.67
    RegressionTest
    0.66
    tvguidetime
    0.65
    𑄮
    0.65
    <unused40>
    0.64
     zwiſchen
    0.64
    <unused53>
    0.64
    <unused58>
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.