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

    Neuronpedia

    INDEX
    Explanations

    references to large quantities of people or monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollapsed
    -0.15
    ãĤĩãģĨ
    -0.14
    icable
    -0.14
     nid
    -0.14
     Waters
    -0.13
    yled
    -0.13
    aml
    -0.13
    ewith
    -0.13
    ventus
    -0.13
    uli
    -0.13
    POSITIVE LOGITS
    idget
    0.14
    altar
    0.14
    earable
    0.14
    ascar
    0.14
     Hundreds
    0.14
    rung
    0.14
    HostException
    0.13
    stdexcept
    0.13
    errupted
    0.13
     Verg
    0.13
    Act Density 0.016%

    No Known Activations