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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating violent actions occurring in a continuous context

    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
     Ambro
    -0.82
     Random
    -0.64
     Genocide
    -0.62
     Ukrain
    -0.62
    ウス
    -0.60
     Verd
    -0.59
     Rye
    -0.58
     Pwr
    -0.58
     Canaver
    -0.58
     Clever
    -0.57
    POSITIVE LOGITS
     jour
    0.81
     serving
    0.76
    carry
    0.71
     enjoying
    0.66
    ploy
    0.66
    GO
    0.65
     esc
    0.64
    oping
    0.63
     bicy
    0.63
     stationed
    0.63
    Activations Density 0.026%

    No Known Activations