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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cube
    -0.65
    oké
    -0.64
    estyles
    -0.64
     compartment
    -0.63
    uttered
    -0.62
     Flip
    -0.61
     subsequ
    -0.61
     plastic
    -0.61
     closet
    -0.61
     exclusive
    -0.60
    POSITIVE LOGITS
    onica
    0.88
    rists
    0.85
    arians
    0.76
    ulia
    0.75
    ada
    0.75
    aru
    0.73
    irez
    0.70
    cgi
    0.70
    rises
    0.70
    çĶ°
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.