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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	Send
    -0.07
    特种
    -0.07
     Document
    -0.07
    䴗
    -0.07
     Stealth
    -0.07
     proved
    -0.06
     Petty
    -0.06
    |[
    -0.06
    谠
    -0.06
     dedicated
    -0.06
    POSITIVE LOGITS
    fab
    0.07
    ////////////////
    0.07
    昔
    0.07
     �
    0.07
    mb
    0.06
    .',
    0.06
    Emp
    0.06
    十八
    0.06
     fifteen
    0.06
    みたいな
    0.06
    Act Density 0.001%

    No Known Activations