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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and financial terminology

    oai_token-act-pair · gemini-2.0-flash

    legal terminology and contract-related words

    np_token-act-pair-logits · gpt-4o-mini

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.70
    AsUp
    -0.63
    Życiorys
    -0.55
    ніципа
    -0.53
    нансо
    -0.53
     Schilling
    -0.52
    {!!
    -0.52
    +:+
    -0.52
    kloped
    -0.51
     OMITBAD
    -0.51
    POSITIVE LOGITS
     själva
    0.50
     ganha
    0.44
     ***!
    0.44
    BaseAdapter
    0.44
    🗳
    0.43
     reserved
    0.43
     dipende
    0.42
     themselves
    0.42
     can
    0.42
     próprios
    0.42
    Act Density 7.627%

    No Known Activations