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

    Neuronpedia

    INDEX
    Explanations

    relevant URLs, email addresses, and other structured text formats

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "rs" which likely indicates a specific word or context associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ABLE
    -0.69
     Galile
    -0.67
    ISO
    -0.66
    SUP
    -0.65
    Front
    -0.65
     Zamb
    -0.65
    OTS
    -0.63
    GROUND
    -0.62
    LET
    -0.62
     Silk
    -0.61
    POSITIVE LOGITS
    mith
    1.26
    terday
    1.18
    nyder
    1.06
    ession
    1.06
    ources
    1.04
    idency
    1.00
    ummer
    0.99
    pring
    0.97
    ÑĮ
    0.97
    undown
    0.97
    Act Density 0.024%

    No Known Activations