© 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. 1005
    Prev
    Next
    INDEX
    Explanations

    the phrase "a long time"

    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
    andro
    -0.65
    ガ
    -0.64
    _>
    -0.62
     Wolfgang
    -0.61
     speeds
    -0.60
     gifted
    -0.60
     Imran
    -0.60
    DOWN
    -0.59
     miracles
    -0.58
     Webster
    -0.58
    POSITIVE LOGITS
    iaries
    0.80
    enough
    0.75
    lat
    0.73
    fort
    0.72
    elta
    0.71
    rama
    0.70
    д
    0.69
     dilig
    0.69
    fortable
    0.68
    otted
    0.67
    Activations Density 0.016%

    No Known Activations