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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    phalt
    -0.82
    ambo
    -0.80
    uden
    -0.72
    htaking
    -0.70
    pez
    -0.67
    stro
    -0.65
    vae
    -0.65
    itol
    -0.65
    blems
    -0.65
    rup
    -0.64
    POSITIVE LOGITS
    »Ĵ
    0.66
     Karn
    0.64
     Timeline
    0.61
    ²¾
    0.60
    é¾įåĸļ士
    0.60
    ONY
    0.60
    AGES
    0.60
     blacklist
    0.60
     duo
    0.59
     unfocusedRange
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.