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

    Neuronpedia

    INDEX
    Explanations

    terms related to political themes and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     politics
    -0.56
    ChildScrollView
    -0.51
    IContainer
    -0.50
     Politics
    -0.50
    zeczy
    -0.50
     zapato
    -0.50
    chuga
    -0.49
    urious
    -0.49
    EDEFAULT
    -0.49
     política
    -0.48
    POSITIVE LOGITS
     correctness
    0.75
     parties
    0.69
     incorrect
    0.68
     correctes
    0.63
     scientist
    0.60
     prisoners
    0.60
     Prisoners
    0.60
     PARTIES
    0.60
     Parties
    0.60
     OnInit
    0.60
    Act Density 0.141%

    No Known Activations