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

    Neuronpedia

    INDEX
    Explanations

    words that indicate ranking, preference, or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imers
    -0.17
    oses
    -0.15
    298
    -0.15
    ries
    -0.15
    ocker
    -0.14
    ucs
    -0.14
    434
    -0.14
    quet
    -0.14
     Vine
    -0.13
    Ñĸп
    -0.13
    POSITIVE LOGITS
    chas
    0.17
    ulia
    0.15
     curl
    0.15
    antas
    0.15
    ullo
    0.15
     OnTrigger
    0.14
    ipsis
    0.14
    .setViewport
    0.14
    agem
    0.14
    ulla
    0.14
    Act Density 0.006%

    No Known Activations