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

    Neuronpedia

    INDEX
    Explanations

    words related to armed military forces and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to military forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hop
    -0.83
    \\\\\\\\
    -0.77
    MAL
    -0.71
    STER
    -0.69
    CAST
    -0.69
    å£
    -0.68
    Dub
    -0.68
    ston
    -0.67
    gdala
    -0.65
    York
    -0.65
    POSITIVE LOGITS
     stationed
    1.02
     recruited
    0.88
     deployed
    0.88
     mobilized
    0.87
     maj
    0.85
     forces
    0.85
     fatig
    0.85
    forces
    0.84
     loyal
    0.82
     force
    0.82
    Act Density 0.024%

    No Known Activations