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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dangerously
    -0.07
    Fitness
    -0.07
    -nil
    -0.07
    änd
    -0.06
    Pt
    -0.06
    邪
    -0.06
    .tax
    -0.06
     contempt
    -0.06
     haute
    -0.06
     Bau
    -0.06
    POSITIVE LOGITS
     generally
    0.07
    据报道
    0.07
     shark
    0.06
     произ
    0.06
     clips
    0.06
     coil
    0.06
     vatanda
    0.06
    器件
    0.06
    ☲
    0.06
     młodzie
    0.06
    Act Density 0.001%

    No Known Activations