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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     arsen
    -0.72
    enthal
    -0.72
    ktop
    -0.70
    xus
    -0.69
    emia
    -0.66
     Screen
    -0.66
     Shelter
    -0.66
     Dome
    -0.65
    istries
    -0.65
    ebin
    -0.65
    POSITIVE LOGITS
    SPONSORED
    0.78
    oward
    0.77
     onwards
    0.74
    ========
    0.67
    áµ
    0.65
    Interested
    0.63
    Downloadha
    0.63
    isin
    0.61
     favour
    0.60
    ��
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.