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. 216
    Prev
    Next
    INDEX
    Explanations

    statements expressing doubt or skepticism about claims and predictions

    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
    olon
    -0.90
    ioch
    -0.88
    orsi
    -0.78
    ankind
    -0.78
    forth
    -0.74
    married
    -0.69
    icycle
    -0.69
    iami
    -0.68
    TPS
    -0.68
    gradation
    -0.67
    POSITIVE LOGITS
     unfounded
    1.07
     inaccurate
    1.07
     accurate
    1.03
     erroneous
    1.03
     incorrect
    1.02
     untrue
    1.01
     outlandish
    0.95
     miscon
    0.91
     false
    0.90
     exaggerated
    0.90
    Activations Density 0.323%

    No Known Activations