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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 371
    Prev
    Next
    INDEX
    Explanations

    statements or claims made in reports or articles

    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
     tremend
    -0.66
    ldom
    -0.64
     brill
    -0.63
     Peb
    -0.59
    iquid
    -0.59
     Screw
    -0.58
     babe
    -0.58
     infancy
    -0.58
     tide
    -0.57
    aucuses
    -0.56
    POSITIVE LOGITS
    Downloadha
    0.95
    ={
    0.77
     said
    0.76
     alleges
    0.73
    Wikipedia
    0.72
     says
    0.71
     commented
    0.71
     asserts
    0.71
     writes
    0.71
     According
    0.70
    Activations Density 0.806%

    No Known Activations