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

    Neuronpedia

    INDEX
    Explanations

    references to data values and their manipulations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lik
    -0.17
    olon
    -0.17
    lip
    -0.17
    ly
    -0.15
    ol
    -0.15
    ross
    -0.15
    like
    -0.15
    umber
    -0.15
    ал
    -0.15
    tega
    -0.14
    POSITIVE LOGITS
    -added
    0.27
    åŁŁ
    0.21
    (forKey
    0.20
    entin
    0.19
    -nil
    0.19
    0.18
     propositions
    0.18
     proposition
    0.18
    =value
    0.18
    Animator
    0.17
    Act Density 0.076%

    No Known Activations