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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    prite
    -0.08
     inser
    -0.07
    ATAL
    -0.07
    砒
    -0.07
    俩
    -0.07
    (DialogInterface
    -0.07
    筐
    -0.07
    agnitude
    -0.07
                    ↵                ↵
    -0.07
     baptized
    -0.06
    POSITIVE LOGITS
    continental
    0.07
    )+↵
    0.07
    _quote
    0.07
    discover
    0.07
     watching
    0.06
    onaut
    0.06
    目睹
    0.06
     Canucks
    0.06
     проч
    0.06
    כים
    0.06
    Act Density 0.003%

    No Known Activations