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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    etheless
    -0.83
    aughter
    -0.69
    anson
    -0.68
     Typh
    -0.68
    pict
    -0.66
     welf
    -0.65
    milo
    -0.61
     adjourn
    -0.61
     Fantastic
    -0.61
    %%%%
    -0.60
    POSITIVE LOGITS
    /
    0.71
    igraph
    0.67
    smart
    0.66
    prising
    0.65
    stract
    0.63
    esides
    0.59
    imb
    0.59
     shoulder
    0.59
    Lev
    0.58
    vier
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.