© 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. 2270
    Prev
    Next
    INDEX
    Explanations

    statements addressing misconceptions or false beliefs about various social issues

    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
     Citation
    -0.74
    hof
    -0.68
    sted
    -0.68
     サーティワン
    -0.68
     DRAG
    -0.65
    glers
    -0.64
    ��極
    -0.64
     Reference
    -0.63
     Timeline
    -0.62
     Horizons
    -0.61
    POSITIVE LOGITS
     tranquil
    0.71
     sterile
    0.70
     sinful
    0.69
     shameful
    0.68
     delinquent
    0.66
     meaningless
    0.66
     necessary
    0.65
     insol
    0.65
     harmless
    0.65
     finer
    0.65
    Activations Density 0.620%

    No Known Activations