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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    buquerque
    -0.77
    matter
    -0.75
    urst
    -0.75
    ocrat
    -0.72
    Charl
    -0.69
    linger
    -0.69
     Invention
    -0.67
    pot
    -0.66
    onom
    -0.66
    efeated
    -0.65
    POSITIVE LOGITS
    acters
    0.70
    anus
    0.70
     mosquito
    0.68
     drainage
    0.65
     cyan
    0.63
     horizont
    0.62
     mosquitoes
    0.62
    oses
    0.61
    elected
    0.61
    vernment
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.