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

    Neuronpedia

    INDEX
    Explanations

    indicators of military rank and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampler
    -0.16
    cheid
    -0.16
    bern
    -0.15
    UCE
    -0.15
    OLLOW
    -0.14
    ulers
    -0.14
    ôn
    -0.14
    нÑĮ
    -0.14
    orgot
    -0.14
    ãĥ¯ãĥ¼
    -0.14
    POSITIVE LOGITS
     rank
    0.24
     ranks
    0.20
     promotion
    0.20
    rank
    0.20
     Promotion
    0.19
     Rank
    0.18
    promotion
    0.18
     promot
    0.18
    _rank
    0.17
    ital
    0.17
    Act Density 0.039%

    No Known Activations