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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    不够
    -0.07
    _extraction
    -0.07
    например
    -0.07
     Reflect
    -0.07
    Pear
    -0.07
    ennent
    -0.07
    .rev
    -0.06
    	finally
    -0.06
    çon
    -0.06
    quelle
    -0.06
    POSITIVE LOGITS
     ){
    0.07
     ############
    0.07
     anime
    0.07
    _likes
    0.07
     push
    0.06
    :)↵
    0.06
    ⽰
    0.06
     Clintons
    0.06
     hassle
    0.06
    必
    0.06
    Act Density 0.000%

    No Known Activations