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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    leans
    -0.83
    nikov
    -0.76
    terday
    -0.75
    =~
    -0.74
    yk
    -0.73
    EEE
    -0.73
    apo
    -0.73
    llah
    -0.72
    shirt
    -0.70
    spir
    -0.69
    POSITIVE LOGITS
     Compatibility
    0.80
     consolidation
    0.75
     Aging
    0.73
     adaptations
    0.70
     Bradford
    0.70
     Strategy
    0.69
     strategy
    0.69
     bottleneck
    0.68
    Scan
    0.68
     Specifications
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.