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

    Neuronpedia

    INDEX
    Explanations

    content related to political criticism and accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Criticizing or disapproving of something

    np_acts-logits-general · gemini-2.0-flash

    criticism and challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.67
     fortunately
    -0.63
     luckily
    -0.62
     kasarigan
    -0.61
     thankfully
    -0.60
    fortunately
    -0.58
    espero
    -0.58
    unfortunately
    -0.57
    ViewFeatures
    -0.56
    Fortunately
    -0.55
    POSITIVE LOGITS
     proposed
    1.02
     decision
    0.97
     idea
    0.96
     actions
    0.93
     proposal
    0.92
     decisions
    0.90
     proposals
    0.89
    proposed
    0.85
     move
    0.83
    Proposed
    0.82
    Act Density 0.595%

    No Known Activations