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

    Neuronpedia

    INDEX
    Explanations

    mentions of the abbreviation "AL" at varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "AL" and associated numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.84
    ãĥ¼ãĥĨãĤ£
    -0.82
    ãĤ©
    -0.79
    achu
    -0.79
    hered
    -0.74
    framework
    -0.74
    enegger
    -0.74
    lication
    -0.73
    pload
    -0.72
    hung
    -0.70
    POSITIVE LOGITS
    WAYS
    1.05
    IAS
    1.00
    anguage
    0.97
    TERN
    0.93
    IST
    0.90
    ERT
    0.87
    GBT
    0.87
    ITY
    0.87
    manac
    0.84
    ICE
    0.83
    Act Density 0.014%

    No Known Activations