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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     operated
    -0.79
     experimented
    -0.74
     advertised
    -0.71
     fronts
    -0.68
     competed
    -0.67
     maintained
    -0.66
     claimed
    -0.66
     Orchestra
    -0.65
    alty
    -0.64
     braces
    -0.63
    POSITIVE LOGITS
    SourceFile
    0.79
    othy
    0.74
    amera
    0.72
    Allah
    0.71
    ockets
    0.68
    igan
    0.67
    agos
    0.66
    swing
    0.66
    ayne
    0.65
    Buff
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.