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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     RI
    -0.70
     purge
    -0.68
    fect
    -0.65
     Mods
    -0.64
    arna
    -0.64
     Kodi
    -0.64
     steroids
    -0.62
     Frog
    -0.62
     Commando
    -0.62
     Suc
    -0.61
    POSITIVE LOGITS
    EMS
    0.90
    obe
    0.78
    imes
    0.71
    idth
    0.70
    soDeliveryDate
    0.69
    LESS
    0.68
    anmar
    0.67
    MSN
    0.65
    istas
    0.64
    obos
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.