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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ophers
    -0.75
    blance
    -0.70
    Interview
    -0.66
    Export
    -0.66
    odox
    -0.65
    Leaks
    -0.65
    Table
    -0.65
    Planet
    -0.64
    oru
    -0.63
    reason
    -0.62
    POSITIVE LOGITS
     bride
    0.71
     cruising
    0.66
     Seym
    0.66
     neighbourhood
    0.63
     boarding
    0.63
     sanctuary
    0.62
    iery
    0.62
    buster
    0.61
     locality
    0.61
    rame
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.