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

    Neuronpedia

    INDEX
    Explanations

    instances of military ranks and leadership qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pent
    -0.18
    lobal
    -0.18
     titre
    -0.16
    itti
    -0.14
     auxiliary
    -0.14
     Gentle
    -0.14
     hired
    -0.13
     peu
    -0.13
     sail
    -0.13
     hire
    -0.13
    POSITIVE LOGITS
     gall
    0.20
     crawled
    0.19
     enemy
    0.18
     disob
    0.17
     disregard
    0.17
    crawl
    0.17
     bay
    0.17
     personally
    0.16
     pinned
    0.16
    殿
    0.16
    Act Density 0.027%

    No Known Activations