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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bos
    -0.74
     Cambod
    -0.70
     Timbers
    -0.70
    DragonMagazine
    -0.69
    rations
    -0.69
    ATCH
    -0.68
    kered
    -0.68
     Vas
    -0.68
     Curiosity
    -0.66
     Klaus
    -0.65
    POSITIVE LOGITS
     Dwell
    0.85
    minent
    0.72
     Default
    0.67
    mg
    0.67
     impover
    0.66
    ivid
    0.65
     consolidation
    0.65
    iliate
    0.65
     Breach
    0.64
    osp
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.