© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1251
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation that indicate relationships between concepts

    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
    ignt
    -0.93
    dropping
    -0.72
    missing
    -0.71
    ueless
    -0.69
    chemical
    -0.67
    certain
    -0.63
    zero
    -0.63
    inarily
    -0.63
    wrong
    -0.61
    020
    -0.61
    POSITIVE LOGITS
     paycheck
    0.72
    ega
    0.61
     enlist
    0.61
     inst
    0.59
     reconc
    0.59
     careers
    0.58
     allegiance
    0.58
    nings
    0.57
    Synopsis
    0.56
     patriotism
    0.54
    Activations Density 0.254%

    No Known Activations