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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    emetery
    -0.77
    inar
    -0.71
    roxy
    -0.68
     Abstract
    -0.67
    rored
    -0.65
    ña
    -0.65
    ril
    -0.63
    ARC
    -0.63
    acle
    -0.62
     ISI
    -0.62
    POSITIVE LOGITS
    enthal
    0.76
     sacrific
    0.76
     stret
    0.69
     stre
    0.67
     manslaughter
    0.66
    repair
    0.65
     sole
    0.64
     proble
    0.64
     metic
    0.62
     unsolved
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.