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

    Neuronpedia

    INDEX
    Explanations

    key terms related to additions or enhancements

    oai_token-act-pair · gpt-3.5-turbo

    references to additional features or enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ards
    -0.73
    NING
    -0.72
    ARE
    -0.72
    cies
    -0.69
    bane
    -0.68
    yah
    -0.66
    bird
    -0.66
    Bey
    -0.65
     Zimmer
    -0.65
     Zel
    -0.63
    POSITIVE LOGITS
    endum
    1.03
     insult
    0.96
    itionally
    0.92
    added
    0.88
     impetus
    0.86
    ictions
    0.85
    itional
    0.85
     thereto
    0.84
    itious
    0.79
     bonus
    0.79
    Act Density 0.032%

    No Known Activations