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

    Neuronpedia

    INDEX
    Explanations

    references to sample datasets and their quality in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.61
     stadig
    -0.59
    出版年
    -0.57
    mechanism
    -0.55
    Bronnen
    -0.54
    :✨
    -0.53
     kommet
    -0.52
     mechanism
    -0.52
    iedenis
    -0.51
    Lugares
    -0.50
    POSITIVE LOGITS
     samples
    1.51
     sample
    1.40
    samples
    1.38
     Samples
    1.31
    sample
    1.26
    sampling
    1.19
     sampling
    1.19
    Samples
    1.19
    Sample
    1.19
     Sample
    1.17
    Act Density 0.191%

    No Known Activations