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

    Neuronpedia

    INDEX
    Explanations

    themes of consistency and continuity in sequences or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uro
    -0.14
     æ¥Ń
    -0.13
     pep
    -0.13
    ystems
    -0.13
    OLL
    -0.13
     kia
    -0.13
     nors
    -0.13
    Prim
    -0.13
    acent
    -0.13
    ampa
    -0.12
    POSITIVE LOGITS
    idor
    0.14
     Fay
    0.14
    è¡
    0.14
    kola
    0.14
    ileaks
    0.14
    anye
    0.14
    isle
    0.13
    idd
    0.13
    mont
    0.13
    mmc
    0.13
    Act Density 0.450%

    No Known Activations