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

    Neuronpedia

    INDEX
    Explanations

    terms related to political contexts and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     politique
    -0.54
     política
    -0.49
     politiques
    -0.49
     políticas
    -0.48
     politiche
    -0.48
     politics
    -0.48
     politika
    -0.47
     BoxFit
    -0.47
     político
    -0.46
     politik
    -0.45
    POSITIVE LOGITS
     correctness
    0.56
     AssemblyCompany
    0.53
     parties
    0.47
     Parties
    0.47
     expediency
    0.45
     Correct
    0.44
     incorrect
    0.44
     party
    0.43
     дописавши
    0.41
    IsMutable
    0.41
    Act Density 0.118%

    No Known Activations