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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing speculation and discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BOTH
    -0.15
     neither
    -0.14
     EITHER
    -0.14
    ÑĢоÑģÑĤо
    -0.13
     Woo
    -0.13
     lately
    -0.13
    ije
    -0.13
    .liferay
    -0.13
    antium
    -0.13
    erce
    -0.13
    POSITIVE LOGITS
     further
    0.20
     actual
    0.20
    å®ŀéĻħ
    0.19
     ëĺIJ
    0.18
     another
    0.17
    actually
    0.17
     actually
    0.17
     countless
    0.17
     weitere
    0.16
     otra
    0.15
    Act Density 0.038%

    No Known Activations