Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 423
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of vigilance or monitoring

    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
    */(
    -0.72
    agents
    -0.68
    authorized
    -0.63
     overr
    -0.62
    ertodd
    -0.61
    orsi
    -0.60
    orship
    -0.58
    agent
    -0.58
    hof
    -0.58
    otte
    -0.58
    POSITIVE LOGITS
     calm
    0.86
     lookout
    0.77
     quiet
    0.74
     eye
    0.72
     lid
    0.68
    pell
    0.68
     watch
    0.68
     Calm
    0.65
     sense
    0.63
     Yuan
    0.63
    Activations Density 0.012%

    No Known Activations