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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to popularity or prevalence trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cluye
    -0.56
    estacks
    -0.55
     كومونز
    -0.54
    PointerException
    -0.54
    apatalk
    -0.54
    MEET
    -0.54
    ParallelGroup
    -0.53
    rawDesc
    -0.52
    OfWork
    -0.52
    évaluateur
    -0.51
    POSITIVE LOGITS
     popularity
    1.81
     popular
    1.71
     Popularity
    1.68
    popular
    1.66
    Popularity
    1.55
    Popular
    1.55
     POPULAR
    1.54
    popularity
    1.51
     Popular
    1.46
     populer
    1.35
    Act Density 0.334%

    No Known Activations