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

    Neuronpedia

    INDEX
    Explanations

    ranks and titles in military contexts

    oai_token-act-pair · gpt-3.5-turbo

    military ranks and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aver
    -0.69
     fracture
    -0.68
     collide
    -0.68
    eat
    -0.67
     intersect
    -0.62
    ACA
    -0.61
    atown
    -0.61
     renters
    -0.59
    ankind
    -0.59
     tense
    -0.59
    POSITIVE LOGITS
    doms
    0.97
    esses
    0.96
     Joseph
    0.89
    ess
    0.86
     GENERAL
    0.84
     Shy
    0.83
     Marshal
    0.83
    general
    0.82
    osate
    0.82
     Viktor
    0.81
    Act Density 0.141%

    No Known Activations