© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3058
    Prev
    Next
    INDEX
    Explanations

    repeated phrases indicating attempts or efforts

    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
    MENTS
    -0.65
    ters
    -0.65
     careless
    -0.64
    sonian
    -0.63
    brance
    -0.63
     complaining
    -0.61
    nov
    -0.61
     Protective
    -0.61
    ranged
    -0.60
    hid
    -0.60
    POSITIVE LOGITS
     censor
    0.77
    ilet
    0.74
     remake
    0.72
     enact
    0.71
     compel
    0.69
    igure
    0.68
    wire
    0.68
    umper
    0.68
    bring
    0.66
    ady
    0.66
    Activations Density 0.086%

    No Known Activations