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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 9-TRES-DC
    5. 604
    Prev
    Next
    INDEX
    Explanations

    themes related to emotional experiences and reactions

    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
    ���
    -1.01
     Kell
    -0.77
    �
    -0.74
     Ski
    -0.73
     Printed
    -0.72
    ricular
    -0.71
     Meteor
    -0.70
    SI
    -0.70
    ��極
    -0.69
     Kenn
    -0.69
    POSITIVE LOGITS
     determination
    0.90
     consensus
    0.90
     accountability
    0.89
     acceptance
    0.88
     certainty
    0.86
     fairness
    0.85
     controversy
    0.83
     disagreement
    0.83
     empowerment
    0.83
     possibility
    0.83
    Activations Density 0.275%

    No Known Activations