© 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. 1222
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases introducing additional information or clarifications

    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
    NetMessage
    -0.78
    cano
    -0.72
    uca
    -0.71
    uch
    -0.68
    nia
    -0.66
    ��
    -0.66
    Untitled
    -0.65
    anting
    -0.65
    �
    -0.64
    icas
    -0.64
    POSITIVE LOGITS
     equals
    1.10
     mirrors
    0.83
     amounts
    0.78
     sounds
    0.75
     rivals
    0.75
     speaks
    0.73
     glances
    0.69
     corresponds
    0.69
     hints
    0.69
     translates
    0.68
    Activations Density 0.059%

    No Known Activations