© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    promotional content related to subscriptions and numbers of free trials or actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    anian
    -0.75
     hindsight
    -0.64
     Cannon
    -0.64
     Transgender
    -0.64
    pers
    -0.63
    irst
    -0.63
    iasis
    -0.61
     pend
    -0.60
     Fallen
    -0.60
     Logged
    -0.58
    POSITIVE LOGITS
     sidx
    0.73
     safeguards
    0.72
     assures
    0.71
     preserves
    0.69
     previews
    0.69
     constraints
    0.68
     stamps
    0.68
    ニ
    0.67
    amaz
    0.66
     guarantees
    0.66
    Activations Density 0.049%

    No Known Activations