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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     advising
    -0.64
    qus
    -0.63
     icon
    -0.63
    ourge
    -0.61
     optimized
    -0.61
    athing
    -0.61
     UX
    -0.61
    chairs
    -0.60
     icons
    -0.60
     turnover
    -0.60
    POSITIVE LOGITS
    )].
    0.85
    amina
    0.78
    atis
    0.74
     Barney
    0.67
     Winc
    0.66
    ãĥ³ãĤ¸
    0.66
    aber
    0.66
     Prosecut
    0.65
    NetMessage
    0.65
    amiya
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.