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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    onis
    -0.67
    idth
    -0.65
     Lans
    -0.60
    nia
    -0.60
    mare
    -0.59
     expresses
    -0.59
     Sel
    -0.59
    enture
    -0.59
    wolf
    -0.59
    azo
    -0.58
    POSITIVE LOGITS
    METHOD
    0.66
    effic
    0.66
    CLOSE
    0.64
    ":[
    0.63
    desc
    0.63
    OSP
    0.63
    ²¾
    0.62
    ãĥĺ
    0.60
     inaccur
    0.59
    Republicans
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.