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

    Neuronpedia

    INDEX
    Explanations

    words that contain the letters "b", "u", and "t" in that order

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'b' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BART
    -0.70
     Stall
    -0.63
     Investigative
    -0.62
     Geh
    -0.62
     subsistence
    -0.61
     Ãľ
    -0.60
     Wer
    -0.60
     expires
    -0.60
     Gent
    -0.60
     ORIG
    -0.60
    POSITIVE LOGITS
    rief
    1.45
    odies
    1.33
    rought
    1.25
    attery
    1.20
    rows
    1.20
    amboo
    1.19
    urden
    1.18
    undle
    1.17
    acteria
    1.17
    ibli
    1.17
    Act Density 0.058%

    No Known Activations