© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2733
    Prev
    Next
    INDEX
    Explanations

    references to casualties or fatalities in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ���
    -0.75
    scribe
    -0.70
    nesday
    -0.68
    liam
    -0.64
    ciating
    -0.63
    sburg
    -0.62
    pled
    -0.60
     Pole
    -0.59
     UCHIJ
    -0.59
    minist
    -0.57
    POSITIVE LOGITS
    aina
    0.83
    ancial
    0.68
    hyd
    0.66
    ahn
    0.64
     adrenaline
    0.64
    neum
    0.61
     survived
    0.61
    rophic
    0.61
    feel
    0.61
     amen
    0.58
    Activations Density 0.095%

    No Known Activations