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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Horses
    -0.71
    statement
    -0.70
     Cruise
    -0.69
     Grind
    -0.66
     Rated
    -0.65
    Recipe
    -0.65
    eatures
    -0.65
    Reviewer
    -0.64
     rave
    -0.63
     Cheap
    -0.63
    POSITIVE LOGITS
    iaz
    0.69
    atchewan
    0.69
    dfx
    0.66
     [âĢ¦]
    0.66
    hua
    0.66
    llah
    0.64
    EMA
    0.64
    itiz
    0.64
    ucha
    0.63
    ertodd
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.