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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or contractual language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Xaml
    -0.16
    emia
    -0.16
    ãĤ¤ãĤ¹
    -0.16
     Essentials
    -0.15
     ips
    -0.15
    /Runtime
    -0.15
    ldb
    -0.14
    ledge
    -0.14
    ÑģÑĤва
    -0.14
    bras
    -0.14
    POSITIVE LOGITS
    trl
    0.17
    uelle
    0.16
     Co
    0.15
    inel
    0.15
    ector
    0.14
     Vander
    0.14
    issors
    0.14
     partial
    0.14
     secure
    0.14
    imbus
    0.14
    Act Density 0.001%

    No Known Activations