© 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. 1785
    Prev
    Next
    INDEX
    Explanations

    occurrences of discourse markers and transitional phrases in conversation

    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
    charges
    -0.82
    vati
    -0.75
    conduct
    -0.73
    stood
    -0.71
    デ
    -0.70
    Pokémon
    -0.67
    ment
    -0.66
    lement
    -0.65
    gets
    -0.65
    votes
    -0.64
    POSITIVE LOGITS
    igue
    0.64
     roller
    0.62
    orp
    0.61
     Helm
    0.59
     Warden
    0.58
    emort
    0.58
     Grip
    0.58
    aeus
    0.57
     standout
    0.56
    amar
    0.56
    Activations Density 0.374%

    No Known Activations