© 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. 1095
    Prev
    Next
    INDEX
    Explanations

    unusual characters or formatting elements in the text

    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
    istically
    -0.27
    bing
    -0.25
    iaries
    -0.25
     dunno
    -0.24
    vity
    -0.24
    seys
    -0.24
     slideshow
    -0.23
    PDATE
    -0.23
    lees
    -0.22
    stakes
    -0.22
    POSITIVE LOGITS
    aminer
    0.29
    ":[
    0.28
    76561
    0.26
    lishes
    0.25
    accompan
    0.25
    coord
    0.25
     Azerb
    0.25
    ���
    0.25
    ":[{"
    0.24
    ��
    0.23
    Activations Density 0.921%

    No Known Activations