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

    Neuronpedia

    INDEX
    Explanations

    characters and symbols that indicate code changes or execution in a script

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oxel
    -0.14
    lisi
    -0.14
    jem
    -0.14
    oven
    -0.14
    .getProperties
    -0.14
    marine
    -0.14
    tah
    -0.14
    kle
    -0.14
    266
    -0.14
    FromString
    -0.14
    POSITIVE LOGITS
    s
    0.16
    adal
    0.15
     bas
    0.14
     Lamp
    0.14
    Cached
    0.14
    اج
    0.14
    -leg
    0.13
    ohn
    0.13
    è¿ĺ
    0.13
    zano
    0.13
    Act Density 0.014%

    No Known Activations