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

    Neuronpedia

    INDEX
    Explanations

    words related to military contexts and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     femininos
    -0.38
     unangemessene
    -0.37
     Öffentlichkeit
    -0.35
    agaimana
    -0.35
     asegurarse
    -0.34
    carian
    -0.34
     dirigeants
    -0.34
     engraçadas
    -0.33
     ujarnya
    -0.33
     embuti
    -0.33
    POSITIVE LOGITS
     mil
    0.83
    mil
    0.81
     Mil
    0.81
    Mil
    0.79
     MIL
    0.77
    MIL
    0.76
     Dead
    0.70
    dead
    0.67
     dead
    0.66
     Killed
    0.66
    Act Density 1.726%

    No Known Activations