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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    )=(
    -0.66
     nostalgic
    -0.65
     transc
    -0.64
    gdala
    -0.63
     Runes
    -0.63
     halves
    -0.61
     Gems
    -0.61
    enium
    -0.59
     clo
    -0.59
     scrolls
    -0.58
    POSITIVE LOGITS
    daq
    0.78
    ifix
    0.68
    ake
    0.68
    akable
    0.67
    confirmed
    0.67
    operation
    0.67
    itation
    0.66
    endish
    0.66
    icator
    0.66
     STAND
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.