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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lik
    -0.66
    ð
    -0.66
    MET
    -0.65
     NEC
    -0.64
    cia
    -0.64
    olesterol
    -0.64
     na
    -0.63
    rit
    -0.61
    eport
    -0.60
    hen
    -0.59
    POSITIVE LOGITS
    vier
    0.69
     whis
    0.69
    opez
    0.63
    CLASSIFIED
    0.61
     McH
    0.61
     Terr
    0.60
     Sco
    0.59
    xxx
    0.59
    alties
    0.58
    ĵĺ
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.