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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Prediction
    -0.67
    apolis
    -0.67
    efe
    -0.66
    adow
    -0.65
     favor
    -0.64
     Rasmussen
    -0.64
     Favor
    -0.63
    rated
    -0.62
     trusted
    -0.62
    orthy
    -0.61
    POSITIVE LOGITS
    Ble
    0.80
     Ley
    0.79
     Chains
    0.77
    Kn
    0.77
    ================================
    0.74
    Origin
    0.73
    Ing
    0.71
    Beh
    0.71
    Ta
    0.71
    UCT
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.