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

    Neuronpedia

    INDEX
    Explanations

    the presence of words that indicate existence or being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    598
    -0.17
    ntag
    -0.14
    çº
    -0.14
    Ëĺ
    -0.14
    èıĮ
    -0.14
     Affero
    -0.14
    ÏģÏİ
    -0.14
     candidacy
    -0.14
    arnings
    -0.14
    енка
    -0.14
    POSITIVE LOGITS
    ãģĻ
    0.15
    opard
    0.15
    StackNavigator
    0.14
     Hammond
    0.14
    reh
    0.14
    .backend
    0.14
    illon
    0.13
    ÏĦÏģι
    0.13
    xe
    0.13
    缮ãĤĴ
    0.13
    Act Density 0.004%

    No Known Activations