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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    building
    -0.07
     leven
    -0.07
     wheelchair
    -0.07
    (train
    -0.07
    enade
    -0.07
     cellar
    -0.07
    艦
    -0.07
    .key
    -0.07
     teens
    -0.07
    /devices
    -0.07
    POSITIVE LOGITS
    .put
    0.08
     putting
    0.08
     put
    0.08
    put
    0.07
    不负
    0.07
    엎
    0.07
     puts
    0.07
    _end
    0.07
    大夫
    0.07
    	fi
    0.06
    Act Density 0.044%

    No Known Activations