© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 703
    Prev
    Next
    INDEX
    Explanations

    phrases indicating measurements or descriptions of areas and dimensions

    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
    �
    -0.70
    ��
    -0.69
    endon
    -0.68
     Directions
    -0.65
    OTAL
    -0.65
    monds
    -0.65
    chlor
    -0.65
    ��
    -0.64
    verages
    -0.64
    Guide
    -0.64
    POSITIVE LOGITS
     fodder
    0.69
     Unle
    0.69
     Ivory
    0.65
    munition
    0.65
     ammunition
    0.64
     Metatron
    0.64
     ammo
    0.64
     vomit
    0.63
    ONY
    0.63
    onite
    0.62
    Activations Density 0.063%

    No Known Activations