© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1244
    Prev
    Next
    INDEX
    Explanations

    words related to recommendations and suggestions

    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
     Pastebin
    -0.99
     partName
    -0.97
    info
    -0.80
    ierrez
    -0.78
    ヴァ
    -0.73
    INFO
    -0.71
    ERROR
    -0.71
    VIDEO
    -0.69
    STAT
    -0.69
    VALUE
    -0.69
    POSITIVE LOGITS
     constructing
    0.92
     designing
    0.89
     marrying
    0.88
     repairing
    0.86
     disband
    0.85
     creating
    0.83
     suspending
    0.81
     treating
    0.81
     placing
    0.80
     forming
    0.80
    Activations Density 0.114%

    No Known Activations