© 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. 764
    Prev
    Next
    INDEX
    Explanations

    comparisons of similarity between different subjects or entities

    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
    agues
    -0.63
    xtap
    -0.63
    eni
    -0.62
     caliber
    -0.58
    riel
    -0.58
     Overt
    -0.58
    �
    -0.57
    aris
    -0.57
    irs
    -0.57
    vier
    -0.57
    POSITIVE LOGITS
     those
    1.19
    those
    1.02
    that
    0.94
     that
    0.93
     Those
    0.93
    Those
    0.85
     That
    0.84
    That
    0.81
     ours
    0.80
     THAT
    0.72
    Activations Density 0.809%

    No Known Activations