© 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. 1992
    Prev
    Next
    INDEX
    Explanations

    phrases that express personal feelings or comparisons using the word "feel like."

    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
    othal
    -0.82
    urus
    -0.75
    OSE
    -0.72
    ACTED
    -0.70
    ure
    -0.70
    assies
    -0.70
    ounded
    -0.69
     Laksh
    -0.65
    osed
    -0.65
    entimes
    -0.65
    POSITIVE LOGITS
     Continued
    0.63
     sticking
    0.62
     Unified
    0.61
     Selling
    0.60
     inclusion
    0.59
    bid
    0.57
     bearer
    0.57
     Channel
    0.56
     admitting
    0.56
     continuing
    0.56
    Activations Density 0.021%

    No Known Activations