© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 570
    Prev
    Next
    INDEX
    Explanations

    locations within a specified context, particularly buildings and addresses

    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
     trusts
    -0.68
    igi
    -0.65
     blames
    -0.64
     deficient
    -0.63
    orate
    -0.63
     dwarf
    -0.62
     failing
    -0.60
     discretionary
    -0.60
     refuse
    -0.60
     credits
    -0.59
    POSITIVE LOGITS
     Oral
    0.72
    auntlet
    0.69
     Samson
    0.67
    schild
    0.66
     Ammunition
    0.66
    leans
    0.65
     Sailor
    0.65
    ubis
    0.64
    estern
    0.63
    uple
    0.63
    Activations Density 0.084%

    No Known Activations