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

    Neuronpedia

    INDEX
    Explanations

    the name "beba" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ba" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Attention
    -0.79
    ICLE
    -0.70
    worldly
    -0.70
    Uncommon
    -0.69
    ivities
    -0.67
    lessly
    -0.66
    externalActionCode
    -0.65
    andem
    -0.64
     Dragonbound
    -0.64
     Principle
    -0.64
    POSITIVE LOGITS
    ques
    1.05
    ba
    1.03
    ñ
    0.97
    uble
    0.89
    aba
    0.88
    ffe
    0.86
    bsite
    0.82
    olean
    0.81
    velength
    0.80
    que
    0.78
    Act Density 0.004%

    No Known Activations