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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Farrell
    -0.07
     Buffy
    -0.07
    뜀
    -0.07
    胴
    -0.07
     POP
    -0.06
    occer
    -0.06
    temperature
    -0.06
     Pry
    -0.06
    /slider
    -0.06
    obi
    -0.06
    POSITIVE LOGITS
    >\
    0.07
     lic
    0.07
     analsex
    0.07
    TERM
    0.07
    |"
    0.07
    谍
    0.07
     unas
    0.06
    *x
    0.06
    -------
    0.06
    (-
    0.06
    Act Density 0.009%

    No Known Activations