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

    Neuronpedia

    INDEX
    Explanations

    terms related to duplication or imitation, particularly in performance and representation contexts

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

    "Similar", "double", "imperson", or "identical"

    np_acts-logits-general · gemini-2.0-flash

    likeness and duplication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.63
    SourceChecksum
    -0.63
     iprot
    -0.54
    GEBURTSDATUM
    -0.52
    tagHelperRunner
    -0.52
    ⓧ
    -0.51
     hadas
    -0.49
     Stellung
    -0.48
    BagConstraints
    -0.48
    CloseOperation
    -0.47
    POSITIVE LOGITS
     likeness
    0.70
     imitation
    0.67
     resemblance
    0.66
     imit
    0.66
     mimic
    0.65
     clone
    0.64
     Imit
    0.62
     replica
    0.61
     imitate
    0.61
     imperson
    0.60
    Act Density 0.415%

    No Known Activations