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

    Neuronpedia

    INDEX
    Explanations

    references to educational or academic practices and research interests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Logistic
    -0.15
    elib
    -0.13
    legend
    -0.13
    éĢ¸
    -0.13
    ould
    -0.13
    idon
    -0.13
    ÙĨدÛĮ
    -0.13
     biologist
    -0.13
    amber
    -0.13
    avit
    -0.12
    POSITIVE LOGITS
     issues
    0.20
     applied
    0.18
     poil
    0.18
     policy
    0.18
    issues
    0.17
     intersection
    0.17
     mixed
    0.15
     Issues
    0.15
    Issues
    0.15
     ########.
    0.14
    Act Density 0.168%

    No Known Activations