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. 300
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or importance

    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
    ailability
    -0.88
    uffle
    -0.66
    ONSORED
    -0.58
    results
    -0.57
     Boom
    -0.57
    iqueness
    -0.55
     soared
    -0.55
    ��
    -0.55
     similarities
    -0.55
    PASS
    -0.55
    POSITIVE LOGITS
    arat
    0.76
    ,
    0.74
     dstg
    0.69
     UNCLASSIFIED
    0.64
    �
    0.61
     –
    0.60
     Guant
    0.60
    ?:
    0.58
    les
    0.58
    ional
    0.57
    Activations Density 0.055%

    No Known Activations