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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cakes
    -0.68
    azaki
    -0.67
    hao
    -0.66
    mort
    -0.66
     Bearing
    -0.65
    ament
    -0.65
    asso
    -0.65
    agh
    -0.65
     Traps
    -0.64
    agi
    -0.64
    POSITIVE LOGITS
    Writer
    0.74
    writer
    0.72
    Param
    0.70
    Len
    0.68
    ardless
    0.68
    Statistics
    0.67
    FTWARE
    0.67
    Offic
    0.65
    Row
    0.65
     Scrib
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.