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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting imaginative thought or hypothetical scenarios

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     referenties
    -0.82
     StatefulWidget
    -0.78
    s
    -0.64
    bs
    -0.61
    geführt
    -0.58
    p
    -0.58
    sy
    -0.57
     Corbett
    -0.56
    ied
    -0.55
    tede
    -0.54
    POSITIVE LOGITS
     Imagination
    1.09
    Imagin
    1.07
     imagining
    1.02
    imagination
    0.99
     Imagine
    0.98
     Imagin
    0.98
     imagine
    0.95
     IMAG
    0.94
     imagin
    0.93
    imaginary
    0.93
    Act Density 0.006%

    No Known Activations