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

    Neuronpedia

    INDEX
    Explanations

    phrases related to judgment, evaluation, and worthiness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fortn
    -0.75
     impractica
    -0.73
     wherea
    -0.72
     inev
    -0.70
     maneu
    -0.69
     cuck
    -0.68
     ACKNOWLEDGMENTS
    -0.68
     indestru
    -0.67
     disreg
    -0.66
     reconnaît
    -0.66
    POSITIVE LOGITS
     suitability
    0.68
     suitable
    0.66
     worthy
    0.66
     deserving
    0.65
    Suitable
    0.62
     Suitable
    0.61
    IsContent
    0.60
    <bos>
    0.60
    vencia
    0.59
    fit
    0.57
    Act Density 0.559%

    No Known Activations