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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    UGE
    -0.71
    CI
    -0.65
    afort
    -0.63
    IUM
    -0.62
     slic
    -0.61
    DOM
    -0.61
     Daw
    -0.60
     Mama
    -0.59
    itual
    -0.59
     IPS
    -0.59
    POSITIVE LOGITS
    Ħ
    0.66
     Saying
    0.64
     thereof
    0.63
    azo
    0.62
    xual
    0.61
     Fro
    0.59
    Ī
    0.59
    inations
    0.59
    idental
    0.58
    aml
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.