© 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. 2426
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns indicating direct interaction or connection

    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
    BuyableInstoreAndOnline
    -0.71
     Fighters
    -0.66
    yang
    -0.62
     booked
    -0.60
     Croat
    -0.59
     Hin
    -0.59
     Clintons
    -0.58
     confir
    -0.58
     Lov
    -0.58
    oops
    -0.58
    POSITIVE LOGITS
    sworth
    0.84
    iously
    0.73
    imental
    0.69
    iver
    0.66
    iger
    0.66
    wrapper
    0.65
    iple
    0.65
    riage
    0.64
    cape
    0.63
    omnia
    0.63
    Activations Density 0.156%

    No Known Activations