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

    Neuronpedia

    INDEX
    Explanations

    words related to warfare

    oai_token-act-pair · gpt-3.5-turbo

    references to "War," particularly in different contexts or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sembly
    -0.90
    İĭ
    -0.87
    Ħ¢
    -0.83
    essee
    -0.76
    aunder
    -0.76
    aminer
    -0.75
    ¥ŀ
    -0.74
     millenn
    -0.73
    etsk
    -0.71
    ħĭ
    -0.68
    POSITIVE LOGITS
    lords
    1.13
    rior
    1.08
    riors
    1.06
    fare
    1.04
     War
    1.04
    lord
    1.00
     Wars
    0.92
    War
    0.91
    war
    0.87
    locks
    0.86
    Act Density 0.016%

    No Known Activations