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

    Neuronpedia

    INDEX
    Explanations

    references to newness or newly introduced items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.16
    ellas
    -0.15
    ÑĭÑģ
    -0.15
    innen
    -0.15
     nic
    -0.14
    ennen
    -0.14
     bump
    -0.14
    ħ§
    -0.14
    inel
    -0.13
    umno
    -0.13
    POSITIVE LOGITS
    ponce
    0.15
    psc
    0.14
    ivers
    0.14
    Ŀ
    0.14
    aná
    0.14
     OPTIONAL
    0.14
    BootApplication
    0.14
    zte
    0.13
    ally
    0.13
    awks
    0.13
    Act Density 0.003%

    No Known Activations