© 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. 1303
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing distinction or negation between different subjects or concepts

    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
    leans
    -0.76
    ery
    -0.74
    roo
    -0.71
    nery
    -0.71
    ERY
    -0.68
    INGTON
    -0.68
    mins
    -0.67
    WR
    -0.66
    FA
    -0.65
    =#
    -0.63
    POSITIVE LOGITS
    pires
    0.83
     majesty
    0.69
     ceilings
    0.66
    alore
    0.66
    bledon
    0.65
     foes
    0.64
     rivalry
    0.63
     derby
    0.63
     Lisbon
    0.62
     ceiling
    0.62
    Activations Density 0.071%

    No Known Activations