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

    Neuronpedia

    INDEX
    Explanations

    references to military-related topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶģ
    -0.89
    gger
    -0.83
    luck
    -0.80
    flush
    -0.74
    uv
    -0.73
    nob
    -0.71
     Seller
    -0.71
    nothing
    -0.71
    Els
    -0.70
    ologue
    -0.70
    POSITIVE LOGITS
     fatig
    1.12
     personnel
    1.07
     acad
    1.01
     barracks
    0.99
     academy
    0.98
     stationed
    0.95
     commanders
    0.95
     contractor
    0.94
     servic
    0.92
     contractors
    0.92
    Act Density 0.029%

    No Known Activations