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. 48
    Prev
    Next
    INDEX
    Explanations

    the word "One" indicating singular entities or important points in a discussion

    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
    ��
    -0.77
    _-
    -0.71
    sembly
    -0.70
    nesday
    -0.68
     Ago
    -0.67
    imar
    -0.65
    ometimes
    -0.65
    aign
    -0.65
    icles
    -0.64
    [/
    -0.64
    POSITIVE LOGITS
     motivation
    0.78
     obstacle
    0.77
     possibility
    0.73
     impossibility
    0.70
     indication
    0.69
     circumstance
    0.68
     organization
    0.68
     source
    0.67
     motivations
    0.66
     complication
    0.65
    Activations Density 0.046%

    No Known Activations