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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 380
    Prev
    Next
    INDEX
    Explanations

    phrases related to suspicion or underlying control

    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
    Rating
    -0.80
    sts
    -0.75
    oria
    -0.72
     diplomacy
    -0.66
    ggles
    -0.65
    rative
    -0.63
    staking
    -0.63
    バ
    -0.62
    Operation
    -0.61
     agitation
    -0.61
    POSITIVE LOGITS
     overlooking
    0.70
     clothed
    0.68
     mocked
    0.67
     exploited
    0.67
     tasked
    0.67
     flanked
    0.66
     (%)
    0.66
     vulnerable
    0.65
     surrounded
    0.64
     ignored
    0.64
    Activations Density 1.704%

    No Known Activations