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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "more" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewise
    -0.17
    enta
    -0.17
     hem
    -0.15
    enet
    -0.14
    ilis
    -0.14
     cand
    -0.14
    ewire
    -0.14
    æĹ¢
    -0.14
    eteria
    -0.14
    ducible
    -0.14
    POSITIVE LOGITS
    assin
    0.17
     traditional
    0.15
     numerous
    0.15
    ovna
    0.15
    velle
    0.15
     usual
    0.15
     recently
    0.14
     æħ
    0.14
    ICC
    0.14
     ern
    0.14
    Act Density 0.073%

    No Known Activations