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

    Neuronpedia

    INDEX
    Explanations

    references to software applications or utilities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.78
     vēl
    -0.89
     iesp
    -0.84
     ķ
    -0.80
     īpa
    -0.79
     šķ
    -0.79
     daudz
    -0.76
     vairāk
    -0.75
     bēr
    -0.72
     ļ
    -0.72
    POSITIVE LOGITS
     affor
    1.59
     increa
    1.56
     impra
    1.55
     milf
    1.54
     shenan
    1.49
     coar
    1.49
     madonna
    1.47
     depic
    1.47
     excru
    1.44
     lidl
    1.44
    Act Density 0.939%

    No Known Activations