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

    Neuronpedia

    INDEX
    Explanations

    references to slope measurements in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    {\
    -0.66
     ан
    -0.60
     {\
    -0.60
    Fig
    -0.59
    unsqueeze
    -0.57
    mati
    -0.56
     kal
    -0.56
     anillos
    -0.56
    Aug
    -0.55
     ch
    -0.54
    POSITIVE LOGITS
     slopes
    1.67
     Slope
    1.61
     slope
    1.52
    Slope
    1.49
    slope
    1.46
     SLO
    1.23
    PyExc
    1.15
     sloping
    1.14
     Slo
    1.13
    Slo
    1.13
    Act Density 0.005%

    No Known Activations