© 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. 3280
    Prev
    Next
    INDEX
    Explanations

    phrases indicating occurrences or incidents

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    wagen
    -0.80
    aults
    -0.67
     Lights
    -0.67
    ategories
    -0.66
    SPONSORED
    -0.66
    ��
    -0.66
    ategy
    -0.64
    VPN
    -0.64
    icion
    -0.62
     outweigh
    -0.61
    POSITIVE LOGITS
     place
    0.93
    place
    0.89
     aim
    0.76
    arching
    0.74
     care
    0.67
     arsenic
    0.61
     advantage
    0.60
    leasing
    0.59
     Suffolk
    0.58
     places
    0.58
    Activations Density 0.031%

    No Known Activations