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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diplomatic agreements or arrangements, specifically focusing on ceasefires

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ceasefires and truces in conflict situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lear
    -0.93
    Leary
    -0.91
    aum
    -0.79
    Arc
    -0.78
    Americans
    -0.78
    yon
    -0.76
    AMES
    -0.73
    Club
    -0.72
    Magikarp
    -0.72
    apore
    -0.72
    POSITIVE LOGITS
     ceasefire
    1.49
     truce
    1.33
     treaty
    0.97
     disarm
    0.94
     agreement
    0.91
     peace
    0.90
     blockade
    0.90
     hostilities
    0.89
     treaties
    0.88
     agre
    0.86
    Act Density 0.015%

    No Known Activations