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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     downfall
    -0.08
     hype
    -0.07
    险
    -0.07
    ada
    -0.07
    τυ
    -0.07
    �
    -0.06
     substitution
    -0.06
    决定
    -0.06
    يط
    -0.06
    ceries
    -0.06
    POSITIVE LOGITS
    ][:
    0.07
     š
    0.07
     Texans
    0.06
    /*----------------------------------------------------------------
    0.06
     PTS
    0.06
    .sk
    0.06
     wiel
    0.06
    .estado
    0.06
    ああ
    0.06
     module
    0.06
    Act Density 0.035%

    No Known Activations