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

    Neuronpedia

    INDEX
    Explanations

    discussions related to political messages and accountability

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

    Sentences followed by "Instead"

    np_acts-logits-general · gemini-2.0-flash

    contrast and negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.72
    MigrationBuilder
    -0.64
    AddTagHelper
    -0.62
     uska
    -0.54
    !*\
    -0.52
     bois
    -0.52
     génération
    -0.50
    varer
    -0.49
     generation
    -0.48
     saites
    -0.48
    POSITIVE LOGITS
     Instead
    1.19
    Instead
    1.19
     instead
    1.14
    instead
    1.05
    tdessen
    1.04
     invece
    0.95
    vece
    0.90
     Alas
    0.81
     alas
    0.79
     Unfortunately
    0.74
    Act Density 0.313%

    No Known Activations