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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreements and consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.18
    hoo
    -0.14
    adge
    -0.14
    nan
    -0.14
    press
    -0.14
     Fran
    -0.14
    unar
    -0.14
    annonce
    -0.14
    file
    -0.14
    Å¡li
    -0.14
    POSITIVE LOGITS
     upon
    0.21
    ably
    0.17
     Upon
    0.17
    vecs
    0.17
    Upon
    0.17
     Ain
    0.16
    ingly
    0.16
     terms
    0.16
     ìĤ¬íķŃ
    0.15
    大åĪ©
    0.15
    Act Density 0.019%

    No Known Activations