© 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. 2048
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing commitment or persistence

    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
    hower
    -0.73
    �
    -0.69
     Reincarn
    -0.68
    �
    -0.68
    println
    -0.67
    artifacts
    -0.66
     Unleashed
    -0.65
    �
    -0.65
    xit
    -0.64
    ウス
    -0.63
    POSITIVE LOGITS
    essen
    0.69
     STUD
    0.68
     Moz
    0.67
    ocal
    0.64
    ued
    0.63
     Fein
    0.62
     Eliot
    0.61
    iqu
    0.60
     assessed
    0.59
    oi
    0.59
    Activations Density 0.068%

    No Known Activations