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

    Neuronpedia

    INDEX
    Explanations

    instances of collaborative efforts or co-authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    år
    -0.15
    hack
    -0.15
    uso
    -0.15
    okus
    -0.15
    ALI
    -0.15
    illet
    -0.14
    onen
    -0.14
    ali
    -0.14
     sto
    -0.14
    .assert
    -0.14
    POSITIVE LOGITS
    agu
    0.16
    shed
    0.16
    LEGRO
    0.15
    KIT
    0.15
    eters
    0.15
    atoria
    0.15
     unordered
    0.14
    ť
    0.14
    lags
    0.14
    ):?>↵
    0.14
    Act Density 0.016%

    No Known Activations