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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sel
    -0.16
    iner
    -0.15
     ton
    -0.14
    olls
    -0.14
    ell
    -0.14
    dale
    -0.13
    icl
    -0.13
    et
    -0.13
    æĸĹ
    -0.13
     nowhere
    -0.13
    POSITIVE LOGITS
    uding
    0.20
    ayed
    0.18
     about
    0.17
    ivet
    0.17
    uring
    0.17
    uded
    0.17
    aylight
    0.17
    igned
    0.16
    Greek
    0.16
    äºĽ
    0.15
    Act Density 0.030%

    No Known Activations