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. 209
    Prev
    Next
    INDEX
    Explanations

    references to specific names or titles in a whimsical context

    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
    _
    -1.40
    Hy
    -1.14
    Si
    -1.13
    Dec
    -1.13
    Round
    -1.12
    Shut
    -1.12
    Phys
    -1.09
    Names
    -1.09
    Effect
    -1.08
    Balance
    -1.07
    POSITIVE LOGITS
     Gloria
    0.81
     GN
    0.67
     Hover
    0.65
     NC
    0.64
     Tinder
    0.64
     Grind
    0.64
     Brett
    0.64
     marks
    0.64
     Loren
    0.64
     Jill
    0.63
    Activations Density 1.116%

    No Known Activations