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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     crit
    -0.07
     countdown
    -0.07
    peare
    -0.07
    Sanders
    -0.06
    Ѓ
    -0.06
    crime
    -0.06
    长长
    -0.06
    ꦇ
    -0.06
     comply
    -0.06
    -0.06
    POSITIVE LOGITS
     eyel
    0.07
    列车
    0.07
    .getSelected
    0.07
    SerializedName
    0.07
     Babylon
    0.07
    尽早
    0.06
     RN
    0.06
    -wsj
    0.06
    效果图
    0.06
    ⊢
    0.06
    Act Density 0.018%

    No Known Activations