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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ĭ
    -0.67
    ĸ
    -0.65
    ²¾
    -0.63
     unden
    -0.62
    ī
    -0.61
    idian
    -0.60
     favors
    -0.59
     polymorph
    -0.59
     darts
    -0.59
    archs
    -0.58
    POSITIVE LOGITS
    Beat
    0.76
    pour
    0.75
    rawdownloadcloneembedreportprint
    0.75
    aughs
    0.71
    cape
    0.71
     Networks
    0.70
    ér
    0.68
    bil
    0.65
    inventoryQuantity
    0.64
    Kn
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.