© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 664
    Prev
    Next
    INDEX
    Explanations

    instances of the word "does" along with phrases describing effective performance or results

    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
     Be
    -0.68
     BE
    -0.66
    being
    -0.60
    ICES
    -0.57
    icas
    -0.56
    isson
    -0.56
    accompanied
    -0.55
    anguard
    -0.55
    Parameters
    -0.54
    ivia
    -0.54
    POSITIVE LOGITS
     chores
    0.82
     calculations
    0.77
    vet
    0.76
     job
    0.73
     rounds
    0.70
     impressions
    0.69
    pez
    0.69
    nery
    0.67
    mean
    0.67
     grunt
    0.66
    Activations Density 0.790%

    No Known Activations