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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     corners
    -0.69
    akuya
    -0.67
    ioxide
    -0.66
     demand
    -0.66
    duction
    -0.63
    iyah
    -0.62
    iken
    -0.61
    poke
    -0.60
    null
    -0.60
    stanbul
    -0.60
    POSITIVE LOGITS
     psychiat
    0.76
    Fed
    0.74
    Import
    0.71
    uchin
    0.70
    jri
    0.70
    VM
    0.70
    immune
    0.69
    ogie
    0.69
    anni
    0.68
     withd
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.