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

    Neuronpedia

    INDEX
    Explanations

    specific keywords that indicate significant elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canary
    -0.16
    049
    -0.16
    plib
    -0.15
    orea
    -0.15
    ç¶
    -0.15
     SpringApplication
    -0.14
    isclosed
    -0.14
    Archive
    -0.14
    089
    -0.14
    insky
    -0.14
    POSITIVE LOGITS
    stub
    0.18
     fore
    0.16
    stery
    0.14
    evice
    0.14
    æĦıæĢĿ
    0.14
     Deg
    0.14
    æĬŀ
    0.13
    bine
    0.13
    ullen
    0.13
    ãĥ³ãĥģ
    0.13
    Act Density 0.006%

    No Known Activations