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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 336
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Torrent
    -0.70
     Mechdragon
    -0.67
     Viz
    -0.63
    ion
    -0.63
    lov
    -0.59
     Jackets
    -0.58
     Brut
    -0.57
     Amir
    -0.57
    mith
    -0.57
     Pedro
    -0.57
    POSITIVE LOGITS
    sie
    0.63
    analy
    0.62
    okes
    0.61
    ruit
    0.61
    entity
    0.60
    ��
    0.59
    yg
    0.58
    opot
    0.58
    OHN
    0.57
    Cola
    0.57
    Activations Density 1.297%

    No Known Activations