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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    \\\\\\\\\\\\\\\\
    -0.77
     ado
    -0.66
    anie
    -0.65
     Saul
    -0.63
    adows
    -0.59
     Reply
    -0.59
     crooked
    -0.58
     masked
    -0.58
     blinding
    -0.57
    Billy
    -0.57
    POSITIVE LOGITS
     Quart
    0.85
    kaya
    0.67
    ittal
    0.67
     Travels
    0.66
    oglu
    0.66
     diapers
    0.65
    endix
    0.65
     Frey
    0.64
    ãĥ¼ãĥ³
    0.64
    ively
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.