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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "baby" or variations of the word

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands or product lines, particularly related to technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iveness
    -0.73
    atern
    -0.70
    ources
    -0.69
    ivity
    -0.68
    sol
    -0.68
    encing
    -0.67
    endiary
    -0.67
    attr
    -0.66
    isters
    -0.66
    aciously
    -0.65
    POSITIVE LOGITS
    aby
    1.14
    azo
    0.83
    aroo
    0.82
    ħĭ
    0.77
    ablo
    0.72
     Ones
    0.71
    arat
    0.70
     Isles
    0.69
    rand
    0.69
    ooth
    0.69
    Act Density 0.011%

    No Known Activations