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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and structures within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referenties
    -0.76
    tonsoft
    -0.57
    Personensuche
    -0.57
    Халык
    -0.56
    himself
    -0.55
     Lưu
    -0.55
     مواليد
    -0.54
    orice
    -0.54
     autorytatywna
    -0.53
    EnableWeb
    -0.52
    POSITIVE LOGITS
     and
    0.65
     which
    0.55
    ThroughAttribute
    0.51
    存于互联网档案馆
    0.51
    Cyfeiriadau
    0.48
     للاسماء
    0.48
     arşivlendi
    0.47
    randomUUID
    0.47
    DebuggerNonUser
    0.47
    ciosa
    0.46
    Act Density 0.652%

    No Known Activations