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

    Neuronpedia

    INDEX
    Explanations

    symbolic characters and formatting elements often used in coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĪĩãĤĬ
    -0.15
    νοι
    -0.15
    .sdk
    -0.15
    нии
    -0.15
    agedList
    -0.14
    andom
    -0.14
     plu
    -0.14
    §Ãĥ
    -0.14
    íķĺìļ°
    -0.14
    abee
    -0.14
    POSITIVE LOGITS
    q
    0.15
    ~
    0.14
     Cooperative
    0.14
     h
    0.14
     @
    0.14
     *
    0.14
     {
    0.13
     introdu
    0.13
    rodu
    0.13
     s
    0.13
    Act Density 0.001%

    No Known Activations