© 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. 3268
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the creation or generation of ideas

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    IRO
    -0.80
    ibel
    -0.78
    */(
    -0.77
    ENCE
    -0.76
    ossession
    -0.74
    ESSION
    -0.73
    ��
    -0.73
    acia
    -0.72
    thood
    -0.71
    ;;;;;;;;;;;;
    -0.70
    POSITIVE LOGITS
     excuses
    0.84
     clever
    0.75
     compelling
    0.74
     exhaustive
    0.74
     ingenious
    0.72
     prerequisite
    0.71
     inexpensive
    0.69
     guarantees
    0.69
     alternatives
    0.68
     tempt
    0.68
    Activations Density 0.132%

    No Known Activations