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

    Neuronpedia

    INDEX
    Explanations

    rankings and statistical information related to performance or evaluation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shenan
    -1.22
     gaily
    -1.22
     maneu
    -1.17
     guarante
    -1.16
     affor
    -1.15
     snoopy
    -1.14
     indestru
    -1.13
     impra
    -1.13
     milf
    -1.12
     depic
    -1.12
    POSITIVE LOGITS
     top
    0.87
    <bos>
    0.87
     Top
    0.83
    top
    0.83
    Top
    0.82
    TOP
    0.75
     TOP
    0.68
     tops
    0.61
     ten
    0.61
    0
    0.59
    Act Density 0.102%

    No Known Activations