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

    Neuronpedia

    INDEX
    Explanations

    URLs and code snippets related to software and technology setups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    getLastName
    -0.60
     «
    -0.60
     “
    -0.56
    ]:
    -0.55
     „
    -0.54
     
    -0.52
     "
    -0.52
    「
    -0.52
    <eos>
    -0.52
     ‘
    -0.51
    POSITIVE LOGITS
     saluti
    1.15
     sappi
    1.14
     soggior
    1.13
     Luglio
    1.10
     quoique
    1.09
     appunt
    1.07
     simplif
    1.06
     Ottobre
    1.05
     scrat
    1.05
     parteci
    1.03
    Act Density 0.195%

    No Known Activations