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

    Neuronpedia

    INDEX
    Explanations

    references to military actions and geopolitical alliances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    089
    -0.18
     boj
    -0.15
     quot
    -0.14
    licted
    -0.14
    izzo
    -0.14
     contro
    -0.14
     rating
    -0.13
     moderne
    -0.13
    agher
    -0.13
    olland
    -0.13
    POSITIVE LOGITS
     talks
    0.24
     peace
    0.23
     broker
    0.21
     Talks
    0.20
    broker
    0.20
     mediator
    0.20
     UNS
    0.19
     dialogue
    0.19
    peace
    0.19
     Peace
    0.19
    Act Density 0.135%

    No Known Activations