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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political conduct and campaign regulations

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

    prohibited conduct or affiliations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PA
    -0.32
     each
    -0.29
     
    -0.29
     …
    -0.28
     good
    -0.26
     CA
    -0.26
     faithful
    -0.26
     almost
    -0.26
     –
    -0.25
     many
    -0.25
    POSITIVE LOGITS
    MigrationBuilder
    0.85
    RenderAtEndOf
    0.81
     kasarigan
    0.81
    Personensuche
    0.78
    Hentet
    0.78
     queſto
    0.77
     дописавши
    0.77
     quelcon
    0.77
     rhestr
    0.75
     ſche
    0.75
    Act Density 0.070%

    No Known Activations