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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ække
    -0.16
    ihn
    -0.14
    ordo
    -0.14
     BaseController
    -0.14
    lyn
    -0.14
     ближ
    -0.14
    ovah
    -0.14
    ender
    -0.14
     Luc
    -0.13
    azy
    -0.13
    POSITIVE LOGITS
     nau
    0.18
    amma
    0.17
     Saras
    0.17
     akka
    0.16
     naam
    0.15
    pte
    0.15
     Inspector
    0.15
    mast
    0.14
     Vall
    0.14
    ("$.
    0.14
    Act Density 1.557%

    No Known Activations