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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.62
    сторія
    -0.59
     censiti
    -0.51
    渍
    -0.51
    sière
    -0.50
     internetowa
    -0.50
     ведь
    -0.50
     onOptions
    -0.49
    الحياه
    -0.49
     چی
    -0.49
    POSITIVE LOGITS
    Clik
    0.73
    Билгалдахарш
    0.63
    otheby
    0.59
    oredCriteria
    0.58
     Arxiv
    0.55
    +:+
    0.55
    Autoritní
    0.55
    ]]]
    0.54
    DebuggerNonUser
    0.53
     HttpNotFound
    0.52
    Act Density 0.193%

    No Known Activations