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. 150
    Prev
    Next
    INDEX
    Explanations

    the concept of persistence or continuity in various contexts

    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
     Brune
    -0.76
    onga
    -0.75
    �
    -0.71
    ��
    -0.70
    irement
    -0.70
    uyomi
    -0.68
    idays
    -0.67
    izons
    -0.66
     GOODMAN
    -0.65
    fts
    -0.64
    POSITIVE LOGITS
     inconvenient
    0.75
     useful
    0.73
     happening
    0.72
     worthwhile
    0.71
     helpful
    0.70
     alive
    0.69
     incomprehensible
    0.69
     interesting
    0.67
     valuable
    0.66
     unreliable
    0.66
    Activations Density 0.047%

    No Known Activations