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

    Neuronpedia

    INDEX
    Explanations

    numerical data or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to performance metrics or comparisons in technology or equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÂŃ
    -0.57
     attendees
    -0.56
    oused
    -0.54
    Visit
    -0.54
    ombs
    -0.54
    Words
    -0.54
    Names
    -0.53
    Listen
    -0.53
    boarding
    -0.51
    ideshow
    -0.51
    POSITIVE LOGITS
     MUCH
    1.34
     slower
    1.18
     marginally
    1.13
     weaker
    1.10
     considerably
    1.09
     alot
    1.09
     slightly
    1.08
     faster
    1.04
     smoother
    1.01
     cheaper
    1.01
    Act Density 0.578%

    No Known Activations