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

    Neuronpedia

    INDEX
    Explanations

    locations and geopolitical terms related to conflict zones

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with geographical locations and military-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resil
    -0.75
     ster
    -0.74
     skelet
    -0.74
     EVER
    -0.72
    Pitt
    -0.72
     Hubble
    -0.70
     watt
    -0.70
     GER
    -0.67
     horm
    -0.66
     OW
    -0.66
    POSITIVE LOGITS
     Islands
    0.92
     Parish
    0.88
    jri
    0.86
     Province
    0.85
    uala
    0.84
     Peninsula
    0.82
     peninsula
    0.82
    arij
    0.81
     Highlands
    0.81
     village
    0.80
    Act Density 0.166%

    No Known Activations