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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military rank and hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    references to ranks or levels of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ezek
    -0.78
    vous
    -0.73
     Beir
    -0.73
    argo
    -0.66
    reens
    -0.65
    credit
    -0.65
    agic
    -0.64
    berra
    -0.64
    orescence
    -0.64
    pmwiki
    -0.64
    POSITIVE LOGITS
    nance
    0.92
    Rank
    0.86
     insign
    0.82
     quo
    0.82
    able
    0.80
    eters
    0.80
    liness
    0.77
    irection
    0.77
    ably
    0.76
     bidder
    0.74
    Act Density 0.014%

    No Known Activations