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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 977
    Prev
    Next
    INDEX
    Explanations

    expressions related to growth or changes in numerical values

    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
    earable
    -0.71
     Fault
    -0.66
    umbn
    -0.64
    anca
    -0.62
     exclusion
    -0.59
    warts
    -0.59
    haps
    -0.58
     stunts
    -0.55
    rompt
    -0.55
    resents
    -0.55
    POSITIVE LOGITS
    to
    0.90
     gradually
    0.75
     accordingly
    0.75
    ovsky
    0.74
    eson
    0.73
     drastically
    0.73
     to
    0.72
     tremendously
    0.67
     thous
    0.67
     dramatically
    0.65
    Activations Density 0.173%

    No Known Activations