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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ispers
    -0.71
    Äĩ
    -0.67
     coy
    -0.67
    icz
    -0.65
     Nicarag
    -0.63
    Santa
    -0.62
    6666
    -0.62
    SPONSORED
    -0.61
    ONSORED
    -0.61
     Chen
    -0.60
    POSITIVE LOGITS
    roups
    0.73
    together
    0.72
    ongh
    0.69
     UX
    0.63
     milliseconds
    0.62
    Offline
    0.61
    iton
    0.61
    Active
    0.59
    Forward
    0.58
    oslav
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.