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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bed
    -0.66
    gery
    -0.66
    abad
    -0.64
    ¯¯¯¯¯¯¯¯
    -0.64
    --------------------
    -0.64
     Protocol
    -0.63
    stroke
    -0.61
     USE
    -0.60
    ========
    -0.59
     suscept
    -0.59
    POSITIVE LOGITS
    rique
    0.67
    ategories
    0.65
     Kro
    0.65
    umo
    0.64
    ending
    0.63
    ategory
    0.63
    ¨
    0.62
    heimer
    0.61
    stic
    0.61
    WI
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.