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

    Neuronpedia

    INDEX
    Explanations

    keywords related to copying, duplicating, or replicating content

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reproduction and its processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rail
    -0.81
    arta
    -0.81
    ucket
    -0.72
    rah
    -0.71
    abb
    -0.71
    bara
    -0.70
    usher
    -0.69
    rug
    -0.69
    adin
    -0.69
    owder
    -0.67
    POSITIVE LOGITS
     reproduce
    1.45
     reprodu
    1.45
     reproduced
    1.23
     Reprodu
    1.05
     reproduction
    1.04
     copies
    0.80
     mosquit
    0.77
     specimen
    0.76
    ktop
    0.75
     Gutenberg
    0.74
    Act Density 0.010%

    No Known Activations