© 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. 2732
    Prev
    Next
    INDEX
    Explanations

    elements of human interactions and relationships

    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
    aeda
    -0.66
    aceous
    -0.64
    erity
    -0.62
     Seym
    -0.62
    aneous
    -0.60
     Heist
    -0.59
    戦
    -0.59
     Nort
    -0.59
    �
    -0.58
    ITCH
    -0.57
    POSITIVE LOGITS
     performs
    1.12
     has
    1.10
     seeks
    1.03
     collects
    1.03
     achieves
    1.02
     conducts
    1.02
     pays
    1.02
     gives
    1.01
     does
    1.00
     delivers
    1.00
    Activations Density 1.683%

    No Known Activations