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

    Neuronpedia

    INDEX
    Explanations

    proper nouns as they relate to people's names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Don."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.81
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.72
     SYSTEM
    -0.68
     Austral
    -0.66
    WARE
    -0.66
    ļé
    -0.66
    ULT
    -0.65
     afore
    -0.65
    Gaza
    -0.64
     CONTROL
    -0.64
    POSITIVE LOGITS
    't
    1.20
    nie
    1.11
    ners
    1.01
    ning
    0.92
    nell
    0.90
    ates
    0.90
    ned
    0.90
    ny
    0.89
    ating
    0.88
    kie
    0.87
    Act Density 0.052%

    No Known Activations