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

    Neuronpedia

    INDEX
    Explanations

    details related to weights and measures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    western
    -0.61
     Chapman
    -0.54
    duction
    -0.51
    utenant
    -0.49
    ogyn
    -0.49
    rosis
    -0.49
    isation
    -0.48
     subp
    -0.48
    comed
    -0.48
     Paradox
    -0.47
    POSITIVE LOGITS
    eki
    0.70
    acity
    0.61
    ages
    0.58
    lies
    0.58
    ible
    0.57
    MENTS
    0.57
    cake
    0.56
    ables
    0.56
    ickr
    0.55
    Merit
    0.54
    Act Density 9.807%

    No Known Activations