© 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. 3231
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remove" and its variations in the context of eliminating something

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ğ
    -0.79
    ��
    -0.78
    王
    -0.72
    wx
    -0.72
    ーン
    -0.71
    hyde
    -0.70
    sonian
    -0.70
    ��
    -0.70
    haus
    -0.69
    azo
    -0.68
    POSITIVE LOGITS
    ebted
    0.78
     barriers
    0.68
     traces
    0.67
     expiration
    0.65
     potency
    0.65
     cooldown
    0.65
     obstacles
    0.63
     difficulty
    0.63
     goodness
    0.63
     veins
    0.62
    Activations Density 0.051%

    No Known Activations