© 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. 1888
    Prev
    Next
    INDEX
    Explanations

    instances of the word "following" in various forms

    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
     �
    -0.72
    �
    -0.67
    イト
    -0.65
    gans
    -0.65
    uders
    -0.63
    �
    -0.62
    strip
    -0.61
     comprom
    -0.60
    quickShipAvailable
    -0.59
    things
    -0.59
    POSITIVE LOGITS
    lihood
    0.69
    UGE
    0.67
    eus
    0.67
     sightings
    0.61
     Hague
    0.61
    upon
    0.59
     assurances
    0.59
    actory
    0.59
    eenth
    0.58
    yss
    0.58
    Activations Density 0.034%

    No Known Activations