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

    Neuronpedia

    INDEX
    Explanations

    references to API-related elements and issues in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ëĦ¤ìĿ´íĬ¸
    -0.16
    çļĦä¸Ģ个
    -0.14
    inside
    -0.14
    .scalablytyped
    -0.12
    ç·Ĵ
    -0.12
    ep
    -0.12
    amen
    -0.12
    vb
    -0.12
    ,},↵
    -0.12
    at
    -0.12
    POSITIVE LOGITS
     code
    0.21
     above
    0.19
     behaviour
    0.19
     returned
    0.17
     problem
    0.17
     /
    0.16
     behavior
    0.16
     .
    0.16
     output
    0.16
     provided
    0.16
    Act Density 0.400%

    No Known Activations