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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    esters
    -0.81
    ãĤ´ãĥ³
    -0.70
    :{
    -0.67
    ename
    -0.66
    NPR
    -0.66
    ¥µ
    -0.64
    bott
    -0.64
    Friends
    -0.64
    å°Ĩ
    -0.63
    OTH
    -0.63
    POSITIVE LOGITS
     QR
    0.66
     Taco
    0.66
     Soc
    0.66
     NX
    0.63
     Curve
    0.63
     SD
    0.62
    acy
    0.62
    afa
    0.60
     Shah
    0.60
     Sect
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.