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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the importance and relevance of factual statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enderror
    -0.46
    -0.43
     ویکی‌آمباردا
    -0.42
     but
    -0.41
    XmlSchema
    -0.39
     Gra
    -0.38
     altra
    -0.38
    AntiForgeryToken
    -0.35
     however
    -0.35
    キラ
    -0.35
    POSITIVE LOGITS
     sogar
    1.14
     addirittura
    1.11
     dokonce
    1.05
     zelfs
    1.02
     persino
    0.98
     even
    0.91
     навіть
    0.88
     nawet
    0.88
     jopa
    0.88
     даже
    0.87
    Act Density 0.442%

    No Known Activations