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

    Neuronpedia

    INDEX
    Explanations

    instances of code formatting and special characters in technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.15
    &nbsp
    -0.14
    (Have
    -0.14
    ãĥ«ãĥķ
    -0.13
    ampton
    -0.13
    %D
    -0.13
    ")↵
    -0.13
    ’ta
    -0.13
    ");↵
    -0.12
    uniacid
    -0.12
    POSITIVE LOGITS
    ()`
    0.18
    *_
    0.17
    :`
    0.16
    .`
    0.16
    agina
    0.15
    boo
    0.14
    }`
    0.14
    432
    0.14
    olle
    0.13
    ~
    0.13
    Act Density 0.074%

    No Known Activations