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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Eva
    -0.93
    eca
    -0.86
    kson
    -0.85
    gress
    -0.82
    yg
    -0.80
     Roz
    -0.79
     Sasha
    -0.78
     seiz
    -0.76
     Roose
    -0.75
    ovych
    -0.74
    POSITIVE LOGITS
    ional
    0.75
    liner
    0.73
     managers
    0.70
     manager
    0.68
    oke
    0.66
     leverage
    0.66
    matic
    0.65
     Engineers
    0.64
     management
    0.63
     powers
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.