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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pinpoint
    -0.08
    溍
    -0.07
    Eight
    -0.07
    onds
    -0.07
     Responsible
    -0.07
    gency
    -0.07
    announce
    -0.07
     vidé
    -0.07
    isty
    -0.06
    cité
    -0.06
    POSITIVE LOGITS
     patriarch
    0.09
     vrouw
    0.08
     By
    0.07
     justified
    0.07
     Carlton
    0.07
    �
    0.07
     względu
    0.07
    _elapsed
    0.06
    ませ
    0.06
    美しい
    0.06
    Act Density 0.006%

    No Known Activations