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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orage
    -0.86
    asures
    -0.73
     Sacrifice
    -0.68
    iture
    -0.68
    ilver
    -0.68
    mast
    -0.68
    eanor
    -0.66
    iotics
    -0.65
    uber
    -0.64
    poses
    -0.64
    POSITIVE LOGITS
    KC
    0.74
     Wick
    0.71
    FP
    0.68
     DOI
    0.68
     Welch
    0.66
    onew
    0.64
     FM
    0.63
    CE
    0.63
     Conway
    0.62
    eers
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.