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

    Neuronpedia

    INDEX
    Explanations

    terms related to issues and challenges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .updateDynamic
    -0.16
    verity
    -0.16
     çift
    -0.15
     pigeon
    -0.15
    Äįel
    -0.14
    aler
    -0.14
    esson
    -0.13
    еÑģа
    -0.13
    Äįet
    -0.13
    979
    -0.13
    POSITIVE LOGITS
     instead
    0.19
    ekil
    0.14
    andal
    0.14
    instead
    0.14
     problem
    0.14
    oste
    0.14
    оÑĩной
    0.14
    uala
    0.13
    iazza
    0.13
     Instead
    0.13
    Act Density 0.006%

    No Known Activations