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

    Neuronpedia

    INDEX
    Explanations

    key emotional moments and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    transQ
    -0.72
     AssemblyCompany
    -0.72
     snippetHide
    -0.69
     يتيمه
    -0.62
     comigo
    -0.58
    always
    -0.57
    RegressionTest
    -0.56
    ffilm
    -0.56
    出版年
    -0.56
     AssemblyCulture
    -0.54
    POSITIVE LOGITS
     asks
    0.75
     reveals
    0.75
     accidentally
    0.72
     angrily
    0.70
     learns
    0.69
     reveal
    0.67
     discovers
    0.66
     confesses
    0.66
     accuses
    0.65
     convinces
    0.65
    Act Density 0.561%

    No Known Activations