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

    Neuronpedia

    INDEX
    Explanations

    instances of code-related operations and comparisons within documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERSION
    -0.15
     Coron
    -0.14
    ITTER
    -0.14
    ERG
    -0.14
    ragon
    -0.14
    /MPL
    -0.14
    że
    -0.13
    gate
    -0.13
     blackout
    -0.13
    erc
    -0.13
    POSITIVE LOGITS
    itm
    0.14
    ackle
    0.14
    arrow
    0.13
     baÅŁÄ±nda
    0.13
    raries
    0.13
    EK
    0.13
    izzle
    0.13
    ea
    0.13
    arranty
    0.13
    au
    0.13
    Act Density 1.247%

    No Known Activations