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. 276
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate adaptations or sources of inspiration for films or stories

    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
     externalToEVAOnly
    -0.78
    rawdownloadcloneembedreportprint
    -0.77
    ⓘ
    -0.76
    cffffcc
    -0.70
     lia
    -0.69
    ALTH
    -0.65
     intervene
    -0.65
    !--
    -0.64
     UNCLASSIFIED
    -0.64
    itud
    -0.62
    POSITIVE LOGITS
    beard
    0.86
     Edison
    0.74
     Siber
    0.68
    andise
    0.67
    udo
    0.61
    elsen
    0.61
     STAR
    0.60
     Sears
    0.60
     Latvia
    0.59
     Rule
    0.59
    Activations Density 0.128%

    No Known Activations