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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    olar
    0.38
     avoiding
    0.38
     avoided
    0.36
    ორის
    0.36
     spost
    0.35
     പൂര്‍
    0.35
    fti
    0.35
     Avoiding
    0.35
    getFrom
    0.34
     完全
    0.34
    POSITIVE LOGITS
     pepper
    0.41
    दास
    0.41
    Pepper
    0.41
     thrones
    0.40
    賜
    0.40
     throne
    0.39
     ludicrous
    0.39
     प्लेटफार्म
    0.39
     canals
    0.39
     मकसद
    0.38
    Act Density 0.001%

    No Known Activations