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

    Neuronpedia

    INDEX
    Explanations

    sentences that discuss the concept of fake news and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endast
    -0.72
     således
    -0.66
     comprendere
    -0.63
     iż
    -0.63
     tevens
    -0.62
     již
    -0.60
     pertanto
    -0.60
    maktadır
    -0.59
     lecz
    -0.58
     nyní
    -0.58
    POSITIVE LOGITS
     stuff
    0.95
     STUFF
    0.90
    everybody
    0.88
    Everybody
    0.87
    bigger
    0.85
     everybody
    0.83
     messed
    0.82
     thingy
    0.80
     scared
    0.79
     messing
    0.78
    Act Density 6.168%

    No Known Activations