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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gasoline
    -0.07
     sandwiches
    -0.07
     socks
    -0.06
    averse
    -0.06
     presidential
    -0.06
    	ti
    -0.06
    ousing
    -0.06
    箫
    -0.06
    icerca
    -0.06
    .sender
    -0.06
    POSITIVE LOGITS
     felon
    0.07
     który
    0.07
     afflicted
    0.07
     {:?}",
    0.06
    _ATTRIBUTES
    0.06
     קטן
    0.06
    RB
    0.06
    (cluster
    0.06
    建档立
    0.06
    מקד
    0.06
    Act Density 0.001%

    No Known Activations