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

    Neuronpedia

    INDEX
    Explanations

    comments in code

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.60
    .
    -0.60
     am
    -0.59
    ’
    -0.59
     and
    -0.57
    -
    -0.56
    <sup>
    -0.56
     der
    -0.56
     office
    -0.55
    <eos>
    -0.55
    POSITIVE LOGITS
     thermomix
    1.71
     lidl
    1.56
     sappi
    1.56
     dispen
    1.48
     michelin
    1.47
     tupperware
    1.46
     guarante
    1.43
     matel
    1.42
     peppa
    1.41
     purcha
    1.39
    Act Density 0.047%

    No Known Activations