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. 8-TRES-DC
    5. 128
    Prev
    Next
    INDEX
    Explanations

    key terms related to various types of structures and settings

    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
     dstg
    -0.77
    actionDate
    -0.60
    OPLE
    -0.58
    umm
    -0.57
    cerning
    -0.56
     moreover
    -0.55
    course
    -0.52
    oldown
    -0.52
    ouver
    -0.52
    bil
    -0.51
    POSITIVE LOGITS
     Inquisition
    0.67
    ther
    0.63
     subp
    0.60
     affiliate
    0.56
    enburg
    0.55
     characterization
    0.54
     Pirate
    0.53
    cknow
    0.53
     Feld
    0.52
     takedown
    0.52
    Activations Density 0.196%

    No Known Activations