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. 130
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences that provide instructions or prompts

    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
     Palestin
    -0.75
     PRO
    -0.66
     Garfield
    -0.64
     Palest
    -0.63
     discrep
    -0.62
    田
    -0.61
     Amon
    -0.59
     Abu
    -0.59
     Lith
    -0.58
    omething
    -0.58
    POSITIVE LOGITS
     checkout
    0.70
    う
    0.68
    eways
    0.65
    ECTION
    0.65
    issance
    0.64
    osta
    0.63
    illac
    0.63
     viewed
    0.63
    icators
    0.63
    vis
    0.61
    Activations Density 0.041%

    No Known Activations