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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    regor
    -0.85
    inder
    -0.76
    inders
    -0.71
    ModLoader
    -0.70
    cffff
    -0.70
     therap
    -0.69
    OUNT
    -0.69
    undo
    -0.67
    oké
    -0.66
     mathemat
    -0.66
    POSITIVE LOGITS
     Gazette
    0.72
     Lama
    0.72
    eny
    0.68
    rez
    0.67
    utra
    0.67
    bang
    0.66
    Attach
    0.66
    yah
    0.63
    ocr
    0.62
    legram
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.