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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orption
    -0.07
     Tar
    -0.07
     subtype
    -0.07
    callbacks
    -0.07
     guilt
    -0.06
     às
    -0.06
    frames
    -0.06
     Participant
    -0.06
    time
    -0.06
     findOne
    -0.06
    POSITIVE LOGITS
    捷
    0.07
    زي
    0.07
    Scheme
    0.07
    ATOR
    0.07
    层层
    0.06
     diam
    0.06
    �
    0.06
    לב
    0.06
    .Zero
    0.06
    ゞ
    0.06
    Act Density 0.154%

    No Known Activations