© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    expressions related to finding the desired balance or solution

    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
    enz
    -0.81
    Pres
    -0.68
    furt
    -0.65
    enser
    -0.63
    bill
    -0.62
    iaries
    -0.61
    ></
    -0.60
    enance
    -0.60
    />
    -0.60
    cedented
    -0.60
    POSITIVE LOGITS
     Nicarag
    0.81
     curtain
    0.77
     pillar
    0.70
     lightsaber
    0.66
     shield
    0.65
     backbone
    0.62
    prus
    0.62
     dagger
    0.61
     Angola
    0.61
     cue
    0.60
    Activations Density 0.123%

    No Known Activations