© 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. 3095
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'on' in statistical or numerical contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Gleaming
    -0.68
     bask
    -0.67
     suffice
    -0.66
    aneers
    -0.65
    hov
    -0.63
    eah
    -0.61
    姫
    -0.60
     skyrocket
    -0.59
     tomat
    -0.58
    shown
    -0.57
    POSITIVE LOGITS
    emonic
    0.68
    shore
    0.68
    inqu
    0.66
    ially
    0.65
    stration
    0.62
    ials
    0.62
    LY
    0.60
    iku
    0.59
    Guard
    0.59
    Line
    0.59
    Activations Density 0.095%

    No Known Activations