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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .Magenta
    -0.06
    antee
    -0.06
    cdr
    -0.06
    inea
    -0.06
    brid
    -0.06
     ary
    -0.05
     åį
    -0.05
    ledi
    -0.05
     Wid
    -0.05
     bills
    -0.05
    POSITIVE LOGITS
    ewriter
    0.08
     Seznam
    0.07
    ziej
    0.07
    arro
    0.07
    ÑĮеÑĢ
    0.07
    ohl
    0.07
    ERG
    0.07
    ç£
    0.06
    åľ
    0.06
    ivate
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.