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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dia
    -0.73
    rac
    -0.68
     diam
    -0.63
     explorer
    -0.62
    addons
    -0.60
    Leader
    -0.60
    HF
    -0.60
     synonymous
    -0.60
     arist
    -0.59
    âĸ¬âĸ¬
    -0.59
    POSITIVE LOGITS
    enegger
    0.83
    ternity
    0.82
    oÄŁ
    0.80
    fty
    0.76
    ategory
    0.76
    toe
    0.75
    rongh
    0.74
    owship
    0.71
    outube
    0.70
    _-
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.