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

    Neuronpedia

    INDEX
    Explanations

    instances of text duplication or plagiarism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to copying and plagiarism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anthrop
    -0.76
    ving
    -0.71
    croft
    -0.71
    Dispatch
    -0.65
    ALE
    -0.63
    pora
    -0.63
     Sinai
    -0.63
     Redemption
    -0.62
    esa
    -0.60
    Parameter
    -0.60
    POSITIVE LOGITS
     copied
    1.30
     copying
    1.01
     copy
    0.93
     copies
    0.87
    chin
    0.84
     Copy
    0.82
     Gutenberg
    0.80
     paste
    0.78
    urally
    0.78
    smanship
    0.74
    Act Density 0.011%

    No Known Activations