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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 802
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the condition or status of individuals or groups

    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
    afety
    -0.78
    urable
    -0.73
    idity
    -0.72
    iosyncr
    -0.70
    ormal
    -0.69
    earchers
    -0.69
    ibilities
    -0.69
    ounter
    -0.68
    uctor
    -0.68
    earance
    -0.68
    POSITIVE LOGITS
     wielding
    0.83
     contemplating
    0.83
     considering
    0.80
     thinking
    0.72
    龍契士
    0.70
     constructing
    0.70
     experimenting
    0.70
     learning
    0.69
     acquainted
    0.66
     donating
    0.64
    Activations Density 0.220%

    No Known Activations