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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dites
    1.32
    ште
    1.25
    б
    1.23
     rab
    1.20
     entour
    1.18
    ν
    1.14
     sonst
    1.06
     froide
    1.06
    était
    1.06
     खासा
    1.04
    POSITIVE LOGITS
    istically
    1.42
    1.34
     abusing
    1.28
    ন
    1.25
     obeying
    1.24
     controversy
    1.24
     repellent
    1.21
    1.20
    ます
    1.18
    Disposable
    1.17
    Act Density 0.000%

    No Known Activations