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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and key numerical details in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alian
    -0.15
    oral
    -0.15
    vd
    -0.15
    avel
    -0.15
    kt
    -0.15
    ober
    -0.14
    lds
    -0.14
    ado
    -0.14
    alo
    -0.14
    ven
    -0.14
    POSITIVE LOGITS
    uae
    0.22
    ocale
    0.18
    tah
    0.15
    erval
    0.15
     enf
    0.15
    dzi
    0.15
    asto
    0.15
    sworth
    0.14
    ÃľRK
    0.14
    serter
    0.14
    Act Density 0.019%

    No Known Activations