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

    Neuronpedia

    INDEX
    Explanations

    references to the United Nations

    oai_token-act-pair · gpt-3.5-turbo

    references to the United Nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utic
    -0.89
    æ³
    -0.82
    thora
    -0.78
     Guardiola
    -0.68
    iris
    -0.67
     sheets
    -0.66
    otto
    -0.64
    OTE
    -0.63
     buds
    -0.62
     DRAG
    -0.62
    POSITIVE LOGITS
     Nations
    0.87
    peace
    0.80
    ilateral
    0.80
    ationally
    0.78
     Headquarters
    0.75
    igroup
    0.75
     Embassy
    0.75
     Ambassador
    0.74
     treaty
    0.74
     diplomatic
    0.73
    Act Density 0.011%

    No Known Activations