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

    Neuronpedia

    INDEX
    Explanations

    instances of political criticism

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

    Labour policies and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.49
     residente
    -0.48
     saites
    -0.44
     Einfluß
    -0.44
    PreferredItem
    -0.43
     cará
    -0.42
     producciones
    -0.41
    jenigen
    -0.40
     Lightboxes
    -0.40
    woordig
    -0.40
    POSITIVE LOGITS
     crunch
    0.44
     recession
    0.42
     Prime
    0.41
     Labour
    0.41
     justification
    0.41
     orthodoxy
    0.40
    ñera
    0.39
     inflation
    0.38
     policy
    0.38
     Rousse
    0.38
    Act Density 0.025%

    No Known Activations