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

    Neuronpedia

    INDEX
    Explanations

    dashes used as punctuation or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortal
    -0.17
    erver
    -0.15
    ervers
    -0.15
    arrera
    -0.15
    inct
    -0.14
    erna
    -0.14
    ingu
    -0.14
    ãģ®ãģĭ
    -0.14
    isis
    -0.14
    akt
    -0.14
    POSITIVE LOGITS
     putas
    0.17
    eck
    0.14
     glue
    0.14
     principle
    0.14
    culus
    0.14
    tring
    0.14
     Gol
    0.14
    lands
    0.14
     broadly
    0.14
     cust
    0.14
    Act Density 0.000%

    No Known Activations