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

    Neuronpedia

    INDEX
    Explanations

    Creative Commons licensing information in text content

    oai_token-act-pair · gpt-3.5-turbo

    references to specific licensing types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.86
    lace
    -0.81
    ships
    -0.80
    naire
    -0.77
    ysis
    -0.71
    naires
    -0.71
    ness
    -0.68
    acles
    -0.68
    hower
    -0.67
     MacArthur
    -0.67
    POSITIVE LOGITS
    VE
    1.32
    ULT
    1.01
    ven
    1.00
    FE
    0.99
    IDS
    0.93
    BILITY
    0.93
    ccess
    0.92
    UG
    0.91
    BILITIES
    0.91
    plings
    0.90
    Act Density 0.023%

    No Known Activations