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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military or intelligence units and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vikipedi
    -0.50
    ########.
    -0.49
     Савезне
    -0.49
    webElementXpaths
    -0.48
     actionPerformed
    -0.48
     vzor
    -0.47
     Италијани
    -0.47
     berke
    -0.46
     uitz
    -0.44
    Diweddarwch
    -0.44
    POSITIVE LOGITS
     Air
    0.84
     USAF
    0.69
    Air
    0.66
     air
    0.61
     AFB
    0.59
     AIR
    0.57
     AF
    0.56
    空
    0.55
     AFA
    0.55
     AFR
    0.54
    Act Density 0.211%

    No Known Activations