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

    Neuronpedia

    INDEX
    Explanations

    capital letters, specifically the letter 'B' and variations with lowercase 'b'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Akt
    -0.15
    ainer
    -0.14
     extras
    -0.14
    ilden
    -0.14
    ufen
    -0.14
    Ø´ÙĪ
    -0.14
    indow
    -0.14
    affen
    -0.14
    quisition
    -0.14
    Duplicates
    -0.14
    POSITIVE LOGITS
    rides
    0.24
    achel
    0.19
    outine
    0.18
    FF
    0.18
    day
    0.18
    loop
    0.17
    -day
    0.17
    FFF
    0.17
    etch
    0.17
    iance
    0.17
    Act Density 0.035%

    No Known Activations