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

    Neuronpedia

    INDEX
    Explanations

    mentions of the abbreviation "AB" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "AB" or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andum
    -0.75
     Tycoon
    -0.72
    ician
    -0.71
     Beir
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.69
    omore
    -0.67
    ciating
    -0.66
     Daytona
    -0.66
     Shroud
    -0.65
     Episcopal
    -0.64
    POSITIVE LOGITS
    RAM
    1.03
    stract
    1.00
    RIC
    0.89
    rams
    0.87
    raham
    0.87
    bey
    0.83
    rav
    0.81
    AB
    0.81
    duct
    0.80
    rave
    0.79
    Act Density 0.005%

    No Known Activations