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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and references to personal experiences or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gutenberg
    -0.69
     Haku
    -0.67
     Substance
    -0.62
     sustainability
    -0.62
     decoration
    -0.61
     vocational
    -0.59
     membrane
    -0.58
     beauty
    -0.58
    lets
    -0.58
     hardship
    -0.57
    POSITIVE LOGITS
    ñ
    0.91
     presume
    0.79
    arag
    0.78
    ldon
    0.77
    pec
    0.74
    ggy
    0.73
    opia
    0.73
    igan
    0.73
    iq
    0.73
    ibo
    0.72
    Act Density 0.466%

    No Known Activations