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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "aka."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Baraka."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ancest
    -0.74
    ĻĤ
    -0.73
    Ö¼
    -0.68
    encers
    -0.66
    ttle
    -0.65
    rals
    -0.64
    relations
    -0.63
    matically
    -0.62
    egg
    -0.61
    child
    -0.61
    POSITIVE LOGITS
    aka
    1.08
    unta
    1.07
    ichi
    1.03
    oka
    0.89
    oba
    0.89
    emia
    0.86
    izu
    0.86
    awa
    0.86
    ña
    0.85
    ñ
    0.85
    Act Density 0.005%

    No Known Activations