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

    Neuronpedia

    INDEX
    Explanations

    mentions of 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
    æ³
    -0.69
    thora
    -0.69
     sheets
    -0.68
     Guardiola
    -0.66
     mills
    -0.65
     sheet
    -0.65
    veland
    -0.64
     Ballard
    -0.63
     strengths
    -0.62
    rosse
    -0.62
    POSITIVE LOGITS
    ilateral
    0.93
    peace
    0.83
     treaty
    0.82
     Headquarters
    0.80
     envoy
    0.80
    ĸļ
    0.77
     Ambassador
    0.76
     delegation
    0.76
     Security
    0.75
     Relief
    0.75
    Act Density 0.011%

    No Known Activations