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

    Neuronpedia

    INDEX
    Explanations

    requests for feedback or communication prompts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     javier
    -0.77
     magis
    -0.74
     Juf
    -0.71
     santiago
    -0.70
     imbal
    -0.68
     roberto
    -0.67
     alberto
    -0.66
     claudia
    -0.66
     fua
    -0.66
     frankfurt
    -0.65
    POSITIVE LOGITS
     contact
    0.60
    SharedDtor
    0.56
     please
    0.55
    contact
    0.53
     NSCoder
    0.51
     Contact
    0.51
     CONTACT
    0.50
    please
    0.49
    <bos>
    0.49
     rivol
    0.48
    Act Density 0.172%

    No Known Activations