© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 985
    Prev
    Next
    INDEX
    Explanations

    references to fighting or battling against various adversaries

    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
     Carrie
    -0.70
    Sensor
    -0.70
    ullivan
    -0.67
    LR
    -0.63
     Mechdragon
    -0.62
     Bowl
    -0.61
     Cannon
    -0.60
    �
    -0.60
     HER
    -0.60
     Miss
    -0.60
    POSITIVE LOGITS
    outher
    0.70
     pursu
    0.69
    nesday
    0.66
     disapp
    0.66
     appe
    0.65
    accompan
    0.64
    oresc
    0.63
     repent
    0.63
     beck
    0.63
     eyed
    0.62
    Activations Density 0.327%

    No Known Activations