© 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. 2338
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences and symbols commonly associated with online identifiers or social media handles

    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
     Amid
    -0.65
     Loyal
    -0.64
     Dare
    -0.63
     Raid
    -0.61
     Icar
    -0.61
     Jihad
    -0.60
     boundary
    -0.60
     indust
    -0.59
     Sach
    -0.59
     Curiosity
    -0.59
    POSITIVE LOGITS
    GM
    0.92
    GG
    0.90
    ISA
    0.89
    HR
    0.89
    WA
    0.88
    GV
    0.87
    EY
    0.86
    WM
    0.85
    URES
    0.84
    LO
    0.83
    Activations Density 0.028%

    No Known Activations