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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and cultural discourse

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

    ultimate peacemakeronline servicesweakened guardrailsunregulated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.46
     prawidł
    -0.42
     TextEditing
    -0.40
    uttosto
    -0.40
     réfrig
    -0.38
     trainer
    -0.38
    โรง
    -0.36
    ñores
    -0.36
     rembour
    -0.36
     équipement
    -0.36
    POSITIVE LOGITS
     EconPapers
    0.64
     становника
    0.55
     betweenstory
    0.52
    sizeCache
    0.50
     kasarigan
    0.48
    ंदीखरीदारी
    0.45
    xiety
    0.44
     itſelf
    0.42
     Alcott
    0.42
    addContainerGap
    0.41
    Act Density 0.108%

    No Known Activations