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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    fters
    -0.86
    poons
    -0.78
    igree
    -0.75
    cup
    -0.72
    antha
    -0.68
    strings
    -0.68
    ription
    -0.67
    endo
    -0.67
    ency
    -0.66
    eah
    -0.66
    POSITIVE LOGITS
     Advocate
    0.75
    externalActionCode
    0.73
    OPLE
    0.68
    APS
    0.67
    Ku
    0.66
    çĦ
    0.66
    ospel
    0.66
    greg
    0.65
     homicides
    0.62
     plates
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.