© 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. 702
    Prev
    Next
    INDEX
    Explanations

    phrases that inquire about the reasons or justifications behind concepts

    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
    hyde
    -1.06
    �醒
    -0.88
    作
    -0.85
    ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ
    -0.84
    atown
    -0.83
    ゴン
    -0.80
    illin
    -0.80
    emonic
    -0.80
    utical
    -0.79
    emort
    -0.79
    POSITIVE LOGITS
     thou
    0.64
     humour
    0.60
     allowed
    0.59
     we
    0.57
     Britons
    0.57
     appreciated
    0.56
     tanks
    0.55
     lucky
    0.55
    [/
    0.55
     obliged
    0.54
    Activations Density 0.027%

    No Known Activations