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

    Neuronpedia

    INDEX
    Explanations

    the word "bra" or words ending in "bra"

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific anatomical terms and medical terminology related to the spine and eligibility criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geoffrey
    -0.72
    adobe
    -0.68
     Alexand
    -0.68
     Django
    -0.66
     Ud
    -0.65
     astronomer
    -0.64
     Gregory
    -0.64
     Moroccan
    -0.64
     Zup
    -0.63
     Ghana
    -0.62
    POSITIVE LOGITS
    leen
    1.49
    bra
    1.46
     eligibility
    1.42
     unintended
    1.38
    BRE
    1.23
    pri
    1.21
     rib
    1.19
     trickle
    1.18
     regress
    1.02
     regression
    0.90
    Act Density 0.034%

    No Known Activations