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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     torture
    -0.07
    quets
    -0.07
     encryption
    -0.07
    'est
    -0.07
     deter
    -0.07
    ]/
    -0.07
     Announcement
    -0.07
    一颗
    -0.06
    February
    -0.06
     neuken
    -0.06
    POSITIVE LOGITS
     higher
    0.08
     shouted
    0.07
    记者从
    0.07
    -long
    0.07
    ,['
    0.07
    🥛
    0.07
    .fail
    0.07
    榱
    0.07
    侔
    0.07
    	className
    0.07
    Act Density 0.023%

    No Known Activations