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

    Neuronpedia

    INDEX
    Explanations

    references to structural components and characteristics in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     repl
    -0.15
    ishi
    -0.14
     Dop
    -0.13
    ï¸
    -0.13
     promot
    -0.13
    ãĥªãĥ¼
    -0.13
     Vas
    -0.13
     Undo
    -0.13
    uno
    -0.12
    APS
    -0.12
    POSITIVE LOGITS
     Trap
    0.17
    -lnd
    0.15
    833
    0.15
    urtle
    0.15
    arem
    0.15
    olt
    0.14
     trap
    0.14
    /Dk
    0.14
    trap
    0.14
    ered
    0.14
    Act Density 0.214%

    No Known Activations