© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2749
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases relating to small or simple actions 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
    anwhile
    -0.70
    eneg
    -0.66
    fleet
    -0.65
    bley
    -0.63
     Rampage
    -0.63
    steen
    -0.62
    akings
    -0.62
    lycer
    -0.62
     Earthqu
    -0.61
    姫
    -0.61
    POSITIVE LOGITS
    unc
    0.75
    ctory
    0.74
     ineffective
    0.71
     unob
    0.67
     ignorant
    0.67
     bald
    0.66
     unsur
    0.66
     harmless
    0.65
     untrue
    0.65
    Filename
    0.65
    Activations Density 0.166%

    No Known Activations