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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ''.
    -0.74
    treatment
    -0.72
    title
    -0.72
    antry
    -0.71
    ariat
    -0.70
    axis
    -0.69
    appropriate
    -0.69
    calling
    -0.67
    .''
    -0.66
    args
    -0.65
    POSITIVE LOGITS
     Mellon
    0.84
    Downloadha
    0.72
    pload
    0.70
    DN
    0.69
    DNA
    0.65
     Harbor
    0.65
    Grid
    0.62
    psc
    0.61
     Klux
    0.61
    hou
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.