© 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. 1182
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements related to weight and mass

    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
     elect
    -0.73
     summers
    -0.66
    utm
    -0.65
     shovel
    -0.62
     stun
    -0.61
     ru
    -0.61
    yo
    -0.60
    -|
    -0.59
     restruct
    -0.57
     hydra
    -0.57
    POSITIVE LOGITS
    ��
    0.86
    eways
    0.81
    ciation
    0.74
    xual
    0.70
    ially
    0.70
    ersen
    0.69
    ival
    0.69
    iety
    0.69
    ciating
    0.67
    SHIP
    0.66
    Activations Density 0.204%

    No Known Activations