© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 829
    Prev
    Next
    INDEX
    Explanations

    parts of words that contain the letter 'p'

    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
     Knot
    -0.81
     coli
    -0.72
    ties
    -0.70
     GTA
    -0.69
    cephal
    -0.67
    chal
    -0.65
     Terminator
    -0.63
    clus
    -0.63
     Stra
    -0.62
     starters
    -0.61
    POSITIVE LOGITS
    ooks
    1.18
    ipp
    1.14
    ollen
    1.11
    umping
    1.06
    ammy
    1.04
    orp
    1.03
    itty
    1.03
    utch
    1.03
    orne
    1.03
    umper
    1.02
    Activations Density 0.576%

    No Known Activations