© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing methods or means of achieving something

    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
    exclusive
    -0.80
    versely
    -0.78
     conclud
    -0.71
    appropriately
    -0.70
    cientious
    -0.70
    CLA
    -0.69
    noticed
    -0.68
     contrace
    -0.68
    gently
    -0.66
     muse
    -0.66
    POSITIVE LOGITS
     Towns
    0.71
     Situation
    0.68
     Filip
    0.66
     humans
    0.65
     deputies
    0.65
     anyone
    0.65
     Ars
    0.64
     others
    0.63
     rid
    0.62
     newcomers
    0.60
    Activations Density 0.020%

    No Known Activations