© 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. 2108
    Prev
    Next
    INDEX
    Explanations

    instances of the word "try" or its variations in different contexts

    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
     ty
    -0.68
     compet
    -0.64
    phot
    -0.63
    ideos
    -0.60
    ournal
    -0.59
     Compet
    -0.58
    ouched
    -0.58
    Û
    -0.57
     Frenchman
    -0.57
    wx
    -0.56
    POSITIVE LOGITS
     definition
    0.68
    END
    0.66
    ends
    0.65
    alter
    0.64
    umption
    0.63
    ett
    0.62
    achi
    0.61
    ウ
    0.59
    iting
    0.59
    �
    0.59
    Activations Density 0.033%

    No Known Activations