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

    Neuronpedia

    INDEX
    Explanations

    terms and references related to legal settlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avors
    -0.14
    coni
    -0.14
     McCart
    -0.14
    Naz
    -0.14
     steady
    -0.14
    yar
    -0.14
     hi
    -0.14
     rud
    -0.13
    ormsg
    -0.13
     stabil
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.18
    antro
    0.18
     releases
    0.17
    anol
    0.17
    orz
    0.16
    serrat
    0.16
    release
    0.16
     releasing
    0.16
     release
    0.15
     Releases
    0.15
    Act Density 0.035%

    No Known Activations