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

    Neuronpedia

    INDEX
    Explanations

    elements related to writing fake news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.87
     Meksiku
    -0.66
    nocześnie
    -0.60
    Hochspringen
    -0.59
    NameInMap
    -0.58
     callers
    -0.57
    esterday
    -0.56
    ViewImports
    -0.56
    tahui
    -0.56
    delwed
    -0.55
    POSITIVE LOGITS
     essay
    1.24
     essays
    1.13
     Essay
    1.07
     writing
    1.06
     assignment
    1.03
    Essay
    1.02
    essay
    0.96
     Essays
    0.95
     research
    0.94
     Writing
    0.94
    Act Density 0.244%

    No Known Activations