© 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. 2400
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating locations or contexts related to terrorism and conflict

    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
    DragonMagazine
    -0.89
    externalActionCode
    -0.79
    azon
    -0.76
    quartered
    -0.74
    apse
    -0.72
    pora
    -0.72
    gradient
    -0.71
    zai
    -0.69
    akov
    -0.69
    NetMessage
    -0.68
    POSITIVE LOGITS
     Outer
    0.79
     Howe
    0.73
     Courtney
    0.73
     Tess
    0.64
     England
    0.63
     Dick
    0.63
     Isle
    0.63
     Barb
    0.62
     Mic
    0.62
     Damon
    0.61
    Activations Density 0.181%

    No Known Activations