© 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. 2771
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate cause and effect relationships, particularly involving the phrase "due in large part to."

    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
    lihood
    -0.73
    entin
    -0.69
    lain
    -0.64
    enhagen
    -0.63
     Collider
    -0.63
    glas
    -0.62
     Canal
    -0.62
    ractor
    -0.61
    SHIP
    -0.60
    psey
    -0.60
    POSITIVE LOGITS
    Bec
    0.70
    apt
    0.69
     part
    0.64
     kind
    0.63
    onga
    0.62
     situ
    0.62
    iew
    0.62
    seys
    0.61
    isf
    0.61
     unison
    0.61
    Activations Density 0.111%

    No Known Activations