© 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. 1200
    Prev
    Next
    INDEX
    Explanations

    sentences that convey finality or completion

    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
     candidacy
    -0.75
     footing
    -0.69
     captcha
    -0.69
     millennium
    -0.69
    thood
    -0.68
    cyclopedia
    -0.68
    vertisement
    -0.68
     anonymity
    -0.66
    ドラ
    -0.66
    porter
    -0.65
    POSITIVE LOGITS
    ↵
    1.02
     Below
    0.90
    ↵↵
    0.85
     Scroll
    0.73
     Luckily
    0.73
    <|endoftext|>
    0.71
    [/
    0.69
     Yep
    0.69
     Afterwards
    0.68
    Below
    0.68
    Activations Density 0.656%

    No Known Activations