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

    Neuronpedia

    INDEX
    Explanations

    references to information retrieval tasks and chat systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exclus
    -0.14
    rac
    -0.13
    esen
    -0.13
     slav
    -0.13
    aks
    -0.13
    aksi
    -0.13
    itere
    -0.13
    ogene
    -0.13
    oller
    -0.13
    rase
    -0.13
    POSITIVE LOGITS
    entionPolicy
    0.15
    âĸį
    0.14
     TMPro
    0.14
    Å¡ak
    0.14
    ~
    0.13
    otypical
    0.13
     atleast
    0.13
    vae
    0.13
    ugins
    0.13
    ·»
    0.13
    Act Density 0.017%

    No Known Activations