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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    veyard
    -0.71
    seek
    -0.64
    complete
    -0.62
     Thanksgiving
    -0.62
     prow
    -0.61
     Chero
    -0.60
     Pebble
    -0.60
     paused
    -0.60
     Poe
    -0.59
     Cherokee
    -0.59
    POSITIVE LOGITS
    lement
    0.78
    ORGE
    0.71
    HAEL
    0.67
    obi
    0.66
     Alonso
    0.65
    IRD
    0.65
     Catalyst
    0.65
    iliary
    0.64
     Alvarez
    0.64
    ilib
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.