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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Mexico
    -0.67
     Uruguay
    -0.66
     Schultz
    -0.64
     Rohingya
    -0.63
     Bender
    -0.62
     Yugoslav
    -0.62
     dictators
    -0.62
     Marino
    -0.62
     Samoa
    -0.61
     Rhodes
    -0.60
    POSITIVE LOGITS
    ophe
    0.65
    cius
    0.64
    falls
    0.63
    door
    0.62
    ions
    0.62
    fully
    0.61
     twitch
    0.61
    athan
    0.60
    oard
    0.59
    ois
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.