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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accessibility and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kat
    -0.16
    ched
    -0.15
    zc
    -0.15
    igg
    -0.15
    annel
    -0.14
    CRET
    -0.14
     activated
    -0.14
    ashes
    -0.14
    activate
    -0.14
    alice
    -0.13
    POSITIVE LOGITS
    -origin
    0.15
    857
    0.15
    Saga
    0.15
     moh
    0.14
    arah
    0.14
     Mill
    0.14
    olini
    0.14
    گاÙĨÛĮ
    0.14
    angered
    0.14
    heimer
    0.14
    Act Density 0.013%

    No Known Activations