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
    ########.
    -0.85
    исленность
    -0.73
     Pickett
    -0.71
     AssemblyProduct
    -0.68
     Benny
    -0.68
    LocalizedString
    -0.68
    stackrel
    -0.67
    igshid
    -0.65
     ši
    -0.65
     Polak
    -0.65
    POSITIVE LOGITS
     Journal
    2.06
     journal
    2.04
    Journal
    1.88
     JOURNAL
    1.86
     Journals
    1.84
    journal
    1.81
     journals
    1.72
    JOURNAL
    1.71
     journaling
    1.47
    Jour
    1.41
    Act Density 0.056%

    No Known Activations