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

    Neuronpedia

    INDEX
    Explanations

    structured sequences and processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.84
    EDEFAULT
    -0.68
     nahilalakip
    -0.63
    ettbewer
    -0.57
    webElementGuid
    -0.57
     tratti
    -0.56
     sobra
    -0.53
     esiste
    -0.52
     bestaan
    -0.52
     محفوظة
    -0.52
    POSITIVE LOGITS
     chronologically
    0.67
    順番
    0.63
    逐
    0.62
    一遍
    0.61
     chronological
    0.59
     sequentially
    0.58
     slowly
    0.58
     từng
    0.57
     順
    0.56
    aufbau
    0.55
    Act Density 0.437%

    No Known Activations