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

    Neuronpedia

    INDEX
    Explanations

    references to 'Columbia' in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    y
    -1.21
    n
    -0.77
    r
    -0.75
    k
    -0.70
    x
    -0.69
    isArray
    -0.67
    er
    -0.67
    nh
    -0.65
    b
    -0.64
    z
    -0.64
    POSITIVE LOGITS
    UMBIA
    1.17
     Monfieur
    1.08
     Majefty
    1.04
     Columbia
    1.03
    Columbia
    1.03
    Autoritní
    1.02
    ")));
    1.02
    .)}
    1.01
     myſelf
    1.00
    columbia
    0.99
    Act Density 0.030%

    No Known Activations