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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2161
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to important principles or takeaways in a discussion or analysis

    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
     landfall
    -0.90
    ��
    -0.89
     raft
    -0.85
     spir
    -0.83
     prosec
    -0.82
     glac
    -0.81
     casc
    -0.79
     populated
    -0.77
     migr
    -0.76
     crus
    -0.76
    POSITIVE LOGITS
    Most
    1.28
    Quite
    1.25
    Regardless
    1.22
    Anyone
    1.21
    Personally
    1.21
    Another
    1.21
    Even
    1.20
    While
    1.19
    Keeping
    1.19
    Being
    1.19
    Activations Density 0.123%

    No Known Activations