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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental actions or policies

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "government of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chops
    -0.78
    fights
    -0.67
     chores
    -0.66
    paces
    -0.66
     routines
    -0.66
     specials
    -0.65
     enthus
    -0.65
    erv
    -0.65
     introdu
    -0.64
     certs
    -0.63
    POSITIVE LOGITS
     Estonia
    1.18
     Kazakhstan
    1.12
     Yugoslavia
    1.10
     Ukraine
    1.08
     Qatar
    1.06
     Honduras
    1.06
     Albania
    1.05
     Latvia
    1.04
     Israel
    1.04
     Uganda
    1.04
    Act Density 0.107%

    No Known Activations