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

    Neuronpedia

    INDEX
    Explanations

    the repetition of the word "again."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    future repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    başı
    -0.37
     negar
    -0.36
    fwrite
    -0.35
     anunciar
    -0.35
     Sprung
    -0.34
     vectorielles
    -0.34
    лання
    -0.33
    nologue
    -0.33
     invitamos
    -0.33
     niega
    -0.32
    POSITIVE LOGITS
    ValueStyle
    0.66
    存于互联网档案馆
    0.62
    ftagPool
    0.56
     محفوظة
    0.55
    原始内容存档于
    0.55
     وتسجيلات
    0.54
     snippetHide
    0.53
     again
    0.51
    Diweddarwch
    0.51
    mals
    0.50
    Act Density 0.006%

    No Known Activations