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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2164
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Nat" or related variations

    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
     attest
    -0.62
     oper
    -0.59
     entertain
    -0.59
     revel
    -0.58
     absor
    -0.57
     belie
    -0.56
    sie
    -0.55
     sector
    -0.55
     shape
    -0.55
     adequ
    -0.54
    POSITIVE LOGITS
    acha
    0.79
    uncture
    0.74
    gage
    0.68
    asma
    0.67
    ERAL
    0.66
    ounces
    0.66
    ザ
    0.66
    �
    0.66
    ��
    0.64
    uchin
    0.64
    Activations Density 0.013%

    No Known Activations