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

    Neuronpedia

    INDEX
    Explanations

    central themes or primary ideas related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     main
    -0.19
     Main
    -0.19
     major
    -0.19
    Main
    -0.16
    main
    -0.15
     little
    -0.15
    urette
    -0.15
     Firm
    -0.15
     Major
    -0.14
    iktig
    -0.14
    POSITIVE LOGITS
    stay
    0.28
     driver
    0.22
     focus
    0.22
     thrust
    0.22
     drivers
    0.20
     focuses
    0.19
     concern
    0.19
     driving
    0.19
     reason
    0.19
     failing
    0.19
    Act Density 0.101%

    No Known Activations