© 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. 2027
    Prev
    Next
    INDEX
    Explanations

    alphanumeric identifiers or codes associated with usernames or account 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
     Left
    -0.73
     Cape
    -0.72
     Provision
    -0.72
     Nare
    -0.71
     Remastered
    -0.71
     Confederate
    -0.70
     Conce
    -0.70
     Newtown
    -0.69
     Aber
    -0.69
     Fug
    -0.68
    POSITIVE LOGITS
    LO
    1.09
    RFC
    1.02
    GV
    1.01
    AZ
    1.00
    Ru
    1.00
    CI
    1.00
    jl
    0.99
    MAT
    0.98
    LV
    0.96
    GG
    0.96
    Activations Density 0.027%

    No Known Activations