© 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. 3234
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to investigations and monitoring

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ◼
    -0.85
    BuyableInstoreAndOnline
    -0.84
    Missing
    -0.73
    Roaming
    -0.72
    untled
    -0.71
    amaz
    -0.68
     earthqu
    -0.68
    Interstitial
    -0.68
    laus
    -0.67
     toppled
    -0.64
    POSITIVE LOGITS
    ocal
    0.76
    eto
    0.69
    iger
    0.64
    berto
    0.63
     Conduct
    0.63
     conducts
    0.61
     acted
    0.61
     reasoned
    0.60
     PU
    0.60
    upon
    0.59
    Activations Density 0.511%

    No Known Activations