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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    DOWN
    -0.87
    Merc
    -0.74
    shots
    -0.70
    =-=-=-=-=-=-=-=-
    -0.70
    ractor
    -0.70
    package
    -0.66
    Technical
    -0.66
    ¶
    -0.66
    rats
    -0.65
    Wil
    -0.65
    POSITIVE LOGITS
     Absent
    0.70
    ĸļ
    0.68
    etter
    0.66
    ischer
    0.64
     recounted
    0.64
     Overse
    0.64
    wered
    0.63
     honoured
    0.63
     payable
    0.63
     Quarterly
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.