© 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. 1414
    Prev
    Next
    INDEX
    Explanations

    aspects related to lists or enumerations

    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
     Liberties
    -0.58
    izen
    -0.55
    estern
    -0.55
    ategor
    -0.53
     Decay
    -0.53
    enary
    -0.52
    Detailed
    -0.52
    astical
    -0.50
    ktop
    -0.50
    izons
    -0.50
    POSITIVE LOGITS
    maybe
    0.65
    sort
    0.59
     luckily
    0.59
     congr
    0.58
     fortunately
    0.57
    they
    0.57
    although
    0.57
    just
    0.56
    either
    0.55
    replace
    0.54
    Activations Density 0.116%

    No Known Activations