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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sistema
    -0.09
     roaring
    -0.07
     trillion
    -0.07
     bride
    -0.07
    调味
    -0.07
     Indy
    -0.06
     rh
    -0.06
    .then
    -0.06
    واء
    -0.06
    iesel
    -0.06
    POSITIVE LOGITS
    BERT
    0.08
    INI
    0.07
    RITE
    0.07
     Comput
    0.07
    二级
    0.07
     FIG
    0.06
    Hostname
    0.06
    POSIT
    0.06
            
↵
    0.06
     forums
    0.06
    Act Density 0.080%

    No Known Activations