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

    Neuronpedia

    INDEX
    Explanations

    instances of communication about misleading information or propaganda

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.46
     produkter
    -0.46
    ftagPool
    -0.43
     celebrid
    -0.43
     Comprometido
    -0.41
     vym
    -0.40
     peindre
    -0.40
     jaula
    -0.40
     manguera
    -0.39
     kontakta
    -0.39
    POSITIVE LOGITS
     voters
    0.57
     viewers
    0.54
     readers
    0.52
     audiences
    0.52
     listeners
    0.52
     investors
    0.49
     audience
    0.45
     publics
    0.45
     shareholders
    0.44
     creditors
    0.43
    Act Density 0.516%

    No Known Activations