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

    Neuronpedia

    INDEX
    Explanations

    references to professional practices in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lassen
    -0.15
     Jou
    -0.15
    etty
    -0.15
    assi
    -0.14
    abbit
    -0.14
    iffe
    -0.14
    arness
    -0.14
    161
    -0.13
    aign
    -0.13
     alike
    -0.13
    POSITIVE LOGITS
    fully
    0.15
    aç
    0.15
    kest
    0.14
    æ¾
    0.14
    Son
    0.14
     thinking
    0.14
     tren
    0.14
    ancial
    0.13
    elden
    0.13
    ollar
    0.13
    Act Density 0.011%

    No Known Activations