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. 183
    Prev
    Next
    INDEX
    Explanations

    words or prefixes related to negation or reversal, particularly those starting with "un."

    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
    �
    -0.74
    orate
    -0.73
     superhuman
    -0.62
     unpop
    -0.61
     uncontrolled
    -0.60
     mathemat
    -0.59
    oured
    -0.59
     Dian
    -0.59
     unden
    -0.58
     submerged
    -0.58
    POSITIVE LOGITS
    readable
    0.87
    nikov
    0.86
    interested
    0.86
    loading
    0.85
    miss
    0.84
    rave
    0.84
    rival
    0.83
    needed
    0.82
    paralle
    0.82
    break
    0.80
    Activations Density 0.015%

    No Known Activations