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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    icultural
    -0.78
     leaf
    -0.71
    icity
    -0.70
    ophob
    -0.69
    iqueness
    -0.69
    eness
    -0.69
    ese
    -0.69
    otin
    -0.69
     Timberwolves
    -0.66
    olitan
    -0.66
    POSITIVE LOGITS
     constitu
    0.76
    ARB
    0.70
    upon
    0.70
    ploma
    0.69
     Patron
    0.68
    ETH
    0.68
     SOLD
    0.67
    ARR
    0.66
    alpha
    0.65
     Fountain
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.