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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sec
    -0.74
     Swanson
    -0.71
    arcer
    -0.67
    ternity
    -0.66
     sew
    -0.65
    wic
    -0.61
    ilia
    -0.61
     Whedon
    -0.61
    irus
    -0.60
    ansson
    -0.59
    POSITIVE LOGITS
    soDeliveryDate
    0.95
     Appears
    0.84
    LCS
    0.68
    EngineDebug
    0.68
    thening
    0.68
    Thumbnail
    0.66
     accelerator
    0.65
    sonian
    0.64
    oln
    0.64
    Deal
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.