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

    Neuronpedia

    INDEX
    Explanations

    legal references and sections related to laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oken
    -0.16
    æĭĶ
    -0.15
    roz
    -0.15
    riter
    -0.15
    atte
    -0.14
    xae
    -0.14
    agrant
    -0.14
    urse
    -0.14
     éĻ
    -0.14
    UGH
    -0.13
    POSITIVE LOGITS
     insert
    0.19
     Insert
    0.19
    .insert
    0.17
    .Insert
    0.17
    insert
    0.17
    ellen
    0.16
     Strike
    0.16
    Strike
    0.16
    (insert
    0.15
     inserting
    0.15
    Act Density 0.006%

    No Known Activations