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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to technology products and promotions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    artment
    -0.79
     withdraw
    -0.78
     Procedures
    -0.74
     withdrew
    -0.74
     wording
    -0.72
     withdrawing
    -0.71
     voluntary
    -0.71
     Partial
    -0.71
     partitions
    -0.68
     mediation
    -0.68
    POSITIVE LOGITS
     unforgettable
    1.24
     unbeat
    1.04
     unstoppable
    1.02
     rave
    0.98
     legendary
    0.97
    icion
    0.93
     unparalleled
    0.93
     unmatched
    0.93
     thrilling
    0.92
     thrill
    0.92
    Act Density 4.205%

    No Known Activations