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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    catentry
    -0.75
    âĸ¬
    -0.72
    ESA
    -0.70
    ILA
    -0.70
    olis
    -0.68
    IED
    -0.66
    onymous
    -0.65
    FIELD
    -0.64
    ãĥĨãĤ£
    -0.64
    cia
    -0.63
    POSITIVE LOGITS
    ĸļ
    0.69
    ibrary
    0.69
     Yard
    0.67
    breaker
    0.66
    rison
    0.66
     Hoy
    0.65
    oslov
    0.63
    orate
    0.62
     Chamberlain
    0.62
    cffff
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.