© 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. 1075
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize sharing and connection with others

    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
     TAMADRA
    -0.87
    ItemTracker
    -0.84
    ァ
    -0.80
     [+
    -0.80
    セ
    -0.78
    �
    -0.73
    ital
    -0.70
     Parenthood
    -0.69
    Untitled
    -0.68
    66666666
    -0.67
    POSITIVE LOGITS
     others
    0.87
     colleagues
    0.79
     patience
    0.75
    zing
    0.75
     pals
    0.70
     friends
    0.68
     saints
    0.67
    zes
    0.67
     attentive
    0.64
    inent
    0.64
    Activations Density 0.101%

    No Known Activations