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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    괜
    -0.07
    ❋
    -0.07
     severe
    -0.06
     provision
    -0.06
     Francesco
    -0.06
     CRE
    -0.06
    ific
    -0.06
     düşün
    -0.06
     Tucson
    -0.06
    eous
    -0.06
    POSITIVE LOGITS
    传承
    0.07
    玻璃
    0.07
    隔
    0.06
    会发生
    0.06
     deeply
    0.06
    させて
    0.06
     registry
    0.06
     attrs
    0.06
    President
    0.06
    Vote
    0.06
    Act Density 0.009%

    No Known Activations