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

    Neuronpedia

    INDEX
    Explanations

    references to peace agreements, initiatives, or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to peace and peace-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STDOUT
    -0.67
    AMES
    -0.65
    chy
    -0.64
    versions
    -0.61
    advertisement
    -0.60
    åĭ
    -0.60
     Sins
    -0.60
    Publisher
    -0.59
     blat
    -0.58
    ames
    -0.57
    POSITIVE LOGITS
    keeping
    1.39
    keepers
    1.33
    keeper
    1.28
    ably
    1.08
    ful
    1.01
     treaty
    0.98
     treaties
    0.96
    fulness
    0.89
    abil
    0.89
     Treaty
    0.87
    Act Density 0.046%

    No Known Activations