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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and societal threats to democracy and public integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disparu
    -0.54
     виправивши
    -0.53
    pasti
    -0.53
    GetAxis
    -0.52
     bakgrund
    -0.52
     juiste
    -0.51
    sisten
    -0.48
    énu
    -0.48
    Personendaten
    -0.47
    alco
    -0.47
    POSITIVE LOGITS
    already
    0.98
     already
    0.95
     morale
    0.94
     fragile
    0.94
     reputations
    0.94
    好不容易
    0.93
     credibility
    0.91
     delicate
    0.89
     livelihoods
    0.89
     innocent
    0.87
    Act Density 0.675%

    No Known Activations