© 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. 691
    Prev
    Next
    INDEX
    Explanations

    personal expressions of identity and emotions

    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
    ership
    -0.78
    eways
    -0.69
    ilk
    -0.69
    yles
    -0.67
     fray
    -0.67
    ipment
    -0.67
     Carbuncle
    -0.65
     Fail
    -0.65
    ibrary
    -0.64
    ゴン
    -0.63
    POSITIVE LOGITS
     confident
    0.99
     hopeful
    0.96
     grateful
    0.94
     thankful
    0.92
     aware
    0.91
     proud
    0.88
     entitled
    0.87
     glad
    0.86
     committed
    0.85
     happy
    0.84
    Activations Density 0.128%

    No Known Activations