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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orno
    -0.77
    DATA
    -0.72
    sic
    -0.69
    âĢ¦]
    -0.68
     multiplication
    -0.67
    endo
    -0.65
    ivities
    -0.65
    apo
    -0.63
    oleon
    -0.61
    STER
    -0.61
    POSITIVE LOGITS
    peria
    0.73
     warr
    0.72
     upon
    0.67
    à©
    0.66
    onday
    0.61
    agements
    0.61
    ãĤŃ
    0.60
    ggies
    0.59
    alty
    0.59
    elight
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.