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. 91
    Prev
    Next
    INDEX
    Explanations

    requests for public information regarding an investigation or crime

    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
     Paste
    -0.81
    legraph
    -0.70
     Turk
    -0.69
     Mehran
    -0.68
    uyomi
    -0.68
     countdown
    -0.67
     Runes
    -0.66
     theat
    -0.62
    illac
    -0.62
     Genius
    -0.61
    POSITIVE LOGITS
    Child
    0.76
    SourceFile
    0.75
     Families
    0.74
    Call
    0.73
    SN
    0.69
    REF
    0.68
    esh
    0.67
    coming
    0.67
    eared
    0.65
    atern
    0.65
    Activations Density 0.033%

    No Known Activations