© 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. 1654
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases that include the word "not" in a negating context

    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
    hess
    -0.86
    afort
    -0.84
    ippi
    -0.75
    aci
    -0.75
    ↑
    -0.75
    auldron
    -0.73
    ongyang
    -0.72
    MpServer
    -0.72
    iability
    -0.72
    ��
    -0.71
    POSITIVE LOGITS
    plot
    0.62
     lightly
    0.61
     attendant
    0.59
     openly
    0.59
    neys
    0.59
    bright
    0.58
     Commerce
    0.56
    ster
    0.56
     accommodating
    0.56
     thousand
    0.55
    Activations Density 0.027%

    No Known Activations