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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.90
    isp
    -0.75
    rogens
    -0.74
    adata
    -0.69
    arium
    -0.68
    artz
    -0.66
    ħĭ
    -0.65
    ngth
    -0.63
     Goodell
    -0.63
     arrest
    -0.63
    POSITIVE LOGITS
    ëĭ
    0.70
    owe
    0.68
     gul
    0.67
     Tues
    0.66
     Gul
    0.66
     ka
    0.65
    ****************
    0.64
    su
    0.63
    munition
    0.62
    luaj
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.