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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'b' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.61
    Magikarp
    -0.61
     Lear
    -0.61
     Geh
    -0.60
     Stall
    -0.59
     Gent
    -0.58
     Enix
    -0.58
     spect
    -0.57
     NTS
    -0.57
    DEM
    -0.56
    POSITIVE LOGITS
    rief
    1.34
    odies
    1.23
    attery
    1.20
    amboo
    1.17
    rities
    1.16
    ibli
    1.16
    ruary
    1.14
    untu
    1.13
    ilingual
    1.12
    isexual
    1.08
    Act Density 0.051%

    No Known Activations