© 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. 1471
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of negation or contradiction

    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
    tion
    -0.77
    lez
    -0.69
    effects
    -0.68
    VERSION
    -0.67
    wolves
    -0.66
    arc
    -0.66
    liners
    -0.66
    vertising
    -0.65
    tips
    -0.64
     sidx
    -0.64
    POSITIVE LOGITS
     flawless
    0.68
     insur
    0.66
     unheard
    0.64
     extinguished
    0.63
     gru
    0.62
     helpless
    0.62
     Sustainable
    0.62
     identical
    0.61
     unparalleled
    0.61
     universal
    0.61
    Activations Density 0.221%

    No Known Activations