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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (lbl
    -0.07
    	sound
    -0.07
    \Abstract
    -0.07
    precation
    -0.07
    גרפי
    -0.07
     asphalt
    -0.07
     przez
    -0.07
     Shirt
    -0.07
    Eat
    -0.07
     screams
    -0.07
    POSITIVE LOGITS
    铊
    0.07
    (",")↵
    0.07
     Trail
    0.07
    💗
    0.07
    😍
    0.06
    带
    0.06
    .get
    0.06
    主力
    0.06
    client
    0.06
    .persistence
    0.06
    Act Density 0.002%

    No Known Activations