Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 412
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I"

    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
     autonom
    -0.70
     escal
    -0.67
     ign
    -0.66
     voic
    -0.62
     rept
    -0.62
    netflix
    -0.61
     obsolete
    -0.61
     repe
    -0.60
     hog
    -0.60
     torches
    -0.59
    POSITIVE LOGITS
    deals
    0.97
    AAF
    0.84
    LY
    0.82
    CT
    0.81
    vey
    0.79
     Corinthians
    0.78
    ATA
    0.78
    747
    0.77
    960
    0.77
    Activity
    0.76
    Activations Density 0.041%

    No Known Activations