© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 495
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Many" that suggest a large quantity or consensus

    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
    illus
    -0.73
    OX
    -0.72
    ctrl
    -0.71
    ciation
    -0.67
    ieft
    -0.65
    uyomi
    -0.63
    oleon
    -0.61
    ISION
    -0.58
     Osiris
    -0.58
     ().
    -0.58
    POSITIVE LOGITS
     summers
    0.81
     readers
    0.79
     reviewers
    0.77
     times
    0.75
     critics
    0.71
     drafts
    0.71
     commentators
    0.71
     writers
    0.70
     observers
    0.70
     years
    0.70
    Activations Density 0.080%

    No Known Activations