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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Haley
    -0.07
     quanto
    -0.07
    .mag
    -0.07
    逛街
    -0.07
     Kramer
    -0.07
     estos
    -0.07
    の大
    -0.06
    celand
    -0.06
     והיא
    -0.06
    滨海
    -0.06
    POSITIVE LOGITS
     öff
    0.07
     שכבר
    0.07
    WB
    0.07
     knife
    0.07
    诗词
    0.07
    睁
    0.07
    ría
    0.07
    ई
    0.06
    ⟦
    0.06
    goto
    0.06
    Act Density 0.126%

    No Known Activations