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

    Neuronpedia

    INDEX
    Explanations

    references to military commanders

    oai_token-act-pair · gpt-3.5-turbo

    references to military ranks or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eat
    -0.76
    employment
    -0.67
    icles
    -0.66
    rin
    -0.65
    430
    -0.64
    dust
    -0.63
    Democrats
    -0.62
    osponsors
    -0.62
    esville
    -0.61
    encers
    -0.61
    POSITIVE LOGITS
    chief
    0.86
     commander
    0.78
    utenant
    0.75
     Kham
    0.74
     commanding
    0.73
     commands
    0.73
     commanders
    0.73
    stration
    0.73
    selage
    0.72
     stationed
    0.71
    Act Density 0.017%

    No Known Activations