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

    Neuronpedia

    INDEX
    Explanations

    references to academic institutions and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.82
     AssemblyCulture
    -0.79
    ftagPool
    -0.79
     виправивши
    -0.77
    AndEndTag
    -0.75
     Erit
    -0.71
    ]")]
    -0.67
    Oneof
    -0.66
     EnglishChoose
    -0.65
    âce
    -0.65
    POSITIVE LOGITS
    ————————————————
    0.59
    μβρίου
    0.56
     University
    0.56
    ↵↵
    0.51
     officially
    0.50
     institutions
    0.48
     institution
    0.48
    erdings
    0.48
                                   
    0.47
     exclusively
    0.46
    Act Density 0.383%

    No Known Activations