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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    исленность
    -0.69
    knock
    -0.68
     Hick
    -0.68
    LocalizedString
    -0.68
    stackrel
    -0.65
     Rick
    -0.64
    ########.
    -0.63
     koste
    -0.62
    зайн
    -0.62
    Rick
    -0.61
    POSITIVE LOGITS
     journal
    1.70
     Journal
    1.58
     Journals
    1.54
     JOURNAL
    1.54
     journals
    1.49
    JOURNAL
    1.48
    Journal
    1.47
    journal
    1.45
     journaling
    1.26
    journals
    1.06
    Act Density 0.071%

    No Known Activations