© 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. 1994
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences with superlatives

    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
     disproportion
    -0.78
    urances
    -0.71
     mockery
    -0.65
    binary
    -0.61
    cone
    -0.61
    interstitial
    -0.59
    secret
    -0.58
     suspic
    -0.58
    idental
    -0.58
    tiny
    -0.58
    POSITIVE LOGITS
    hester
    0.80
     ever
    0.71
    cki
    0.68
    plin
    0.68
    iser
    0.67
     dated
    0.64
    herty
    0.64
    hene
    0.64
    ffer
    0.61
    rade
    0.61
    Activations Density 0.032%

    No Known Activations