Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 9-TRES-DC
    5. 629
    Prev
    Next
    INDEX
    Explanations

    references to specifications and components of technical equipment

    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
    SPONSORED
    -0.74
    ald
    -0.73
    dayName
    -0.68
    pedia
    -0.66
    ACP
    -0.66
    PsyNetMessage
    -0.66
    armed
    -0.66
    alls
    -0.64
    AIDS
    -0.63
    writing
    -0.62
    POSITIVE LOGITS
    iage
    0.66
     destro
    0.63
     vari
    0.61
     Fres
    0.61
    iba
    0.60
     drilled
    0.59
     Maver
    0.59
     solvent
    0.58
     surg
    0.58
     Siem
    0.57
    Activations Density 0.158%

    No Known Activations