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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ⟨
    -0.08
    ฒ
    -0.08
     Together
    -0.07
    大海
    -0.07
    .compose
    -0.07
     Saskatchewan
    -0.07
     birkaç
    -0.07
    (TYPE
    -0.07
    📋
    -0.07
     Soup
    -0.07
    POSITIVE LOGITS
     fed
    0.08
     Pont
    0.08
    Minute
    0.08
     fail
    0.07
     wartime
    0.07
     fails
    0.07
    negative
    0.07
     detriment
    0.07
    Temp
    0.07
    حط
    0.06
    Act Density 0.027%

    No Known Activations