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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    heric
    -0.85
    cies
    -0.69
    orkshire
    -0.67
    ouver
    -0.66
     climbers
    -0.64
    commit
    -0.63
    liners
    -0.63
    keye
    -0.62
    erential
    -0.62
    eu
    -0.61
    POSITIVE LOGITS
     Weight
    0.70
     Swords
    0.69
     Sabbath
    0.67
    mast
    0.67
    ldom
    0.65
    .:
    0.60
     phantom
    0.60
     âľ
    0.60
    ---------
    0.59
    none
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.