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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ([$
    -0.08
    }")↵↵
    -0.08
     infix
    -0.08
    那个人
    -0.07
    ↵                    ↵
    -0.07
    颁发
    -0.07
     equipos
    -0.07
    >↵↵↵↵
    -0.07
    ']↵↵
    -0.07
     deluxe
    -0.07
    POSITIVE LOGITS
    	ent
    0.07
     saddened
    0.07
    exact
    0.07
    chunk
    0.07
    قوا
    0.07
    <Map
    0.07
     kidn
    0.07
     Bihar
    0.06
    dn
    0.06
    itten
    0.06
    Act Density 0.060%

    No Known Activations