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

    Neuronpedia

    INDEX
    Explanations

    phrases related to copyright and licensing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goldman
    -0.72
     “
    -0.70
     Williams
    -0.67
    forums
    -0.65
     Hartman
    -0.63
     
    -0.62
    EnableWeb
    -0.61
     Wul
    -0.61
     ‘
    -0.60
    .”
    -0.60
    POSITIVE LOGITS
     copy
    2.57
    copy
    2.35
     Copy
    2.32
     copies
    2.31
     COPY
    2.29
    Copy
    2.23
     Copies
    2.10
     copying
    2.02
    COPY
    2.02
    copies
    2.00
    Act Density 0.096%

    No Known Activations