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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     unary
    -0.07
    .Mutable
    -0.06
    Dog
    -0.06
    ??↵↵
    -0.06
     subnet
    -0.06
     obs
    -0.06
     tslint
    -0.06
    OutOfBounds
    -0.06
     quote
    -0.05
    );
↵
↵
↵
    -0.05
    POSITIVE LOGITS
    (Application
    0.07
     Plastic
    0.07
    witter
    0.07
     blender
    0.07
     criminals
    0.07
     sustain
    0.06
    άν
    0.06
     capacity
    0.06
     extraordinarily
    0.06
    INATION
    0.06
    Act Density 0.006%

    No Known Activations