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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that indicate comparisons or distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bran
    -0.14
     Bloc
    -0.14
    tran
    -0.14
     RequestContext
    -0.13
     TMPro
    -0.13
    393
    -0.13
     Brick
    -0.13
    Bond
    -0.13
    stor
    -0.13
     mutual
    -0.13
    POSITIVE LOGITS
     bew
    0.49
     bet
    0.48
     bt
    0.39
    bet
    0.37
     btw
    0.37
     bw
    0.37
     beet
    0.34
    bew
    0.30
     be
    0.29
     Bet
    0.28
    Act Density 0.068%

    No Known Activations