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

    Neuronpedia

    INDEX
    Explanations

    invitations for feedback or audience interaction

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    £ı
    -0.74
     Skydragon
    -0.67
     ubiqu
    -0.62
    inventoryQuantity
    -0.58
    printf
    -0.57
    cler
    -0.57
    olid
    -0.57
    peror
    -0.57
    orage
    -0.57
    Merc
    -0.57
    POSITIVE LOGITS
     Comment
    0.97
     feedback
    0.93
     comments
    0.90
     suggestions
    0.87
     Favorite
    0.86
     comment
    0.86
     Feedback
    0.85
     favorites
    0.84
    comments
    0.84
    Comment
    0.83
    Act Density 0.163%

    No Known Activations