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

    Neuronpedia

    INDEX
    Explanations

    mentions of countries

    oai_token-act-pair · gpt-3.5-turbo

    references to Belgium and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mits
    -0.84
    mitting
    -0.82
    apers
    -0.80
    seeking
    -0.79
    pter
    -0.75
    ãģ¦
    -0.73
    mit
    -0.73
    mable
    -0.72
    ming
    -0.71
    sworth
    -0.70
    POSITIVE LOGITS
     Congo
    0.99
     Belg
    0.97
    ois
    0.96
    rave
    0.92
     Admir
    0.90
     Belgian
    0.89
     Airlines
    0.89
     Belgium
    0.83
     Columb
    0.75
     Trave
    0.73
    Act Density 0.009%

    No Known Activations