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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1173
    Prev
    Next
    INDEX
    Explanations

    references to geographical directions, particularly "east" and "west."

    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
    zzle
    -0.81
    edin
    -0.69
     Photos
    -0.68
     Thumbnails
    -0.68
     Ads
    -0.66
    apixel
    -0.66
    gin
    -0.66
    ilial
    -0.65
    quished
    -0.64
    eteria
    -0.62
    POSITIVE LOGITS
    miss
    0.76
     coast
    0.66
     coasts
    0.64
    quality
    0.64
    verages
    0.63
    bound
    0.62
     probable
    0.61
     counties
    0.60
    usa
    0.60
    etheless
    0.60
    Activations Density 0.019%

    No Known Activations