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

    Neuronpedia

    INDEX
    Explanations

    mentions of support or conflict with rebel groups in various contexts, particularly in military or political situations

    oai_token-act-pair · gpt-3.5-turbo

    references to groups involved in conflict, particularly adversarial factions like rebels and separatists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographies
    -0.97
    thora
    -0.75
    itation
    -0.74
    ographical
    -0.74
     Liberties
    -0.74
     Ct
    -0.74
    Arthur
    -0.71
     Honolulu
    -0.71
    ASED
    -0.70
     Atmospheric
    -0.70
    POSITIVE LOGITS
     rebels
    1.17
     milit
    0.93
     Rebels
    0.91
     rebel
    0.89
     insurgents
    0.89
     loyal
    0.88
     pitted
    0.85
     trou
    0.84
     waging
    0.84
     besie
    0.84
    Act Density 0.013%

    No Known Activations