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

    Neuronpedia

    INDEX
    Explanations

    end-of-turn markers in the text

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

    references and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zaamheid
    -0.40
    cripciones
    -0.36
     voork
    -0.34
     vermelhas
    -0.34
    XmlType
    -0.33
     kerjasama
    -0.31
     conhecimento
    -0.31
     çalış
    -0.31
     atve
    -0.30
    untung
    -0.29
    POSITIVE LOGITS
     GenerationType
    0.51
     initComponents
    0.49
     nonatomic
    0.48
    ंदीखरीदारी
    0.47
     دیکھیے
    0.47
     CanadaChoose
    0.46
     noDo
    0.46
     betweenstory
    0.45
    !*\
    0.45
    期刊论文
    0.45
    Act Density 0.148%

    No Known Activations