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. 350
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "after" indicating events or actions following a prior situation

    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
    ogo
    -0.91
    ortium
    -0.78
    oire
    -0.76
    home
    -0.74
    ogun
    -0.74
    anded
    -0.74
     Flavoring
    -0.74
    orget
    -0.71
    inventory
    -0.70
    三
    -0.69
    POSITIVE LOGITS
     disclosure
    0.77
     unfavorable
    0.77
     disclosing
    0.75
     spotting
    0.71
     defeat
    0.71
     word
    0.69
     RCMP
    0.66
     deciding
    0.66
     admitting
    0.64
     reports
    0.63
    Activations Density 0.044%

    No Known Activations