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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases that imply ongoing action or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ott
    -0.17
    contin
    -0.16
     còn
    -0.16
    енз
    -0.16
    ola
    -0.16
    lant
    -0.15
    hya
    -0.15
     continuing
    -0.15
    _contin
    -0.15
    继ç»Ń
    -0.15
    POSITIVE LOGITS
    ä¸ĭåİ»
    0.21
     efforts
    0.20
     down
    0.19
     to
    0.18
     with
    0.18
     along
    0.17
    nings
    0.17
     momentum
    0.16
     dialog
    0.16
    ued
    0.16
    Act Density 0.054%

    No Known Activations