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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific subject or entity, "Ba" followed by a varying number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ba" followed by various characters or words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otle
    -0.83
    wise
    -0.79
    lessly
    -0.77
    ments
    -0.74
    mented
    -0.70
    MAS
    -0.68
    geist
    -0.66
    ament
    -0.66
    LAND
    -0.63
     address
    -0.63
    POSITIVE LOGITS
    uble
    1.14
    iting
    1.04
    iley
    0.99
    umann
    0.99
    uman
    0.93
    ñ
    0.93
    atar
    0.92
    ÅŁ
    0.86
    plin
    0.84
    ãĤ§
    0.83
    Act Density 0.037%

    No Known Activations