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

    Neuronpedia

    INDEX
    Explanations

    different instances of "first" or "one" indicating a sequence or priority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iglia
    -0.17
    ylon
    -0.16
    imore
    -0.16
    agher
    -0.15
    кова
    -0.15
    浩
    -0.14
    ctal
    -0.14
    TECTED
    -0.14
    æĮ¯ãĤĬ
    -0.14
    inary
    -0.14
    POSITIVE LOGITS
    Ñĥка
    0.18
    abs
    0.15
    ForMember
    0.14
    urre
    0.14
    inde
    0.14
    ourn
    0.14
     multiplier
    0.14
     langs
    0.14
    cks
    0.13
     SPORT
    0.13
    Act Density 0.457%

    No Known Activations