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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    /common
    -0.07
     behalf
    -0.07
    (td
    -0.07
     beide
    -0.07
     ничего
    -0.07
     شيئ
    -0.06
    -Benz
    -0.06
    _Rem
    -0.06
     venta
    -0.06
     submitting
    -0.06
    POSITIVE LOGITS
    ("`
    0.08
    律
    0.07
    撸
    0.07
     Kingston
    0.06
    olic
    0.06
     SMART
    0.06
    elect
    0.06
     dollar
    0.06
    棘
    0.06
    clude
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.