© 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. 568
    Prev
    Next
    INDEX
    Explanations

    calls to action related to website engagement and subscription

    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
    yip
    -0.66
     bells
    -0.65
     leaflets
    -0.64
     interceptions
    -0.59
    oleon
    -0.58
     Flo
    -0.57
     Landing
    -0.56
     Puzzles
    -0.55
     subtitles
    -0.55
     bombers
    -0.54
    POSITIVE LOGITS
    pent
    0.70
    ��
    0.67
    ame
    0.67
    actionDate
    0.64
    spec
    0.63
    ��極
    0.63
    APD
    0.62
    advertisement
    0.62
    enei
    0.61
    orate
    0.60
    Activations Density 0.009%

    No Known Activations