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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosa
    -0.15
    _eval
    -0.15
     operations
    -0.15
    ī´
    -0.15
     Thunder
    -0.14
    omid
    -0.14
    nton
    -0.14
    ega
    -0.14
    lege
    -0.14
    º«
    -0.14
    POSITIVE LOGITS
     blow
    0.25
     uniqueness
    0.20
     Blow
    0.19
     lifespan
    0.19
     existence
    0.19
     Lions
    0.19
     Ler
    0.18
    Lady
    0.18
     solutions
    0.18
     Solutions
    0.18
    Act Density 0.250%

    No Known Activations