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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety nets and support systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Karlov
    -0.15
    imits
    -0.15
    punk
    -0.15
    GROUND
    -0.14
    ovice
    -0.14
    etwork
    -0.14
    okit
    -0.14
    olla
    -0.14
    NetMessage
    -0.13
    zeit
    -0.13
    POSITIVE LOGITS
    -down
    0.15
    ãĤ§
    0.14
    wald
    0.14
    éļĬ
    0.14
    asier
    0.14
    uth
    0.14
     saja
    0.13
     sos
    0.13
    aus
    0.13
    wat
    0.13
    Act Density 0.078%

    No Known Activations