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

    Neuronpedia

    INDEX
    Explanations

    references to legal and ethical considerations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awl
    -0.16
    ithe
    -0.14
     Arbitrary
    -0.14
    ivor
    -0.14
     BOTH
    -0.13
    æ··åIJĪ
    -0.13
    ullan
    -0.13
    ocale
    -0.13
    jang
    -0.13
    .News
    -0.13
    POSITIVE LOGITS
     conventional
    0.38
     obvious
    0.36
     traditional
    0.36
     usual
    0.36
    traditional
    0.30
     regular
    0.29
    usual
    0.28
     normal
    0.26
    Traditional
    0.26
     Traditional
    0.26
    Act Density 0.140%

    No Known Activations