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

    Neuronpedia

    INDEX
    Explanations

    references to the word "bra."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    боÑĤ
    -0.16
    retched
    -0.16
    便
    -0.15
    uppy
    -0.14
    ogan
    -0.14
    yro
    -0.14
    lixir
    -0.14
    åı¬
    -0.14
    astes
    -0.14
    309
    -0.14
    POSITIVE LOGITS
    ided
    0.25
     Bra
    0.22
    hma
    0.21
     bra
    0.21
    odcast
    0.19
    intree
    0.19
     BRA
    0.19
     Brah
    0.18
    bra
    0.18
    unsch
    0.18
    Act Density 0.008%

    No Known Activations