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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥĵ
    -0.79
    ews
    -0.70
    olid
    -0.65
    isted
    -0.63
    tml
    -0.63
     sqor
    -0.62
    uffed
    -0.62
     tremend
    -0.62
    iesel
    -0.62
     Ow
    -0.60
    POSITIVE LOGITS
    NOR
    0.77
    emphasis
    0.75
     SAT
    0.69
    ``
    0.68
    SN
    0.67
    ...)
    0.67
    UV
    0.64
    /-
    0.64
    whatever
    0.64
    MS
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.