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

    Neuronpedia

    INDEX
    Explanations

    phrases related to wars or military conflicts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "war" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obook
    -0.75
    Row
    -0.74
    aminer
    -0.73
    icles
    -0.70
    erd
    -0.70
     Wiz
    -0.70
    Choice
    -0.70
    ocl
    -0.68
    ocracy
    -0.68
     kinderg
    -0.68
    POSITIVE LOGITS
    lords
    0.85
     1914
    0.77
     1941
    0.77
     Patton
    0.77
     1942
    0.76
    lord
    0.76
     Churchill
    0.76
     era
    0.76
     1939
    0.75
     Norton
    0.74
    Act Density 0.053%

    No Known Activations