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

    Neuronpedia

    INDEX
    Explanations

    references to the United Nations (UN)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the United Nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.66
     \(
    -0.66
     Demons
    -0.65
     Gum
    -0.63
     Guardiola
    -0.63
     Elect
    -0.62
     veins
    -0.61
     Malfoy
    -0.61
     Camb
    -0.60
     coh
    -0.60
    POSITIVE LOGITS
    KNOWN
    1.28
    ICE
    1.19
    SC
    1.18
    ISON
    1.14
    LV
    1.08
    IVERS
    1.05
    GA
    1.05
    ITED
    1.04
    ESCO
    1.00
    IX
    0.99
    Act Density 0.016%

    No Known Activations