© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 2515
    Prev
    Next
    INDEX
    Explanations

    references to influential figures and concepts in philosophy and culture

    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
     Huss
    -0.67
    vine
    -0.65
    sale
    -0.63
     Inquis
    -0.61
     Crusade
    -0.60
    =-=-=-=-
    -0.59
    frames
    -0.59
    geries
    -0.58
    ville
    -0.57
     Exodus
    -0.57
    POSITIVE LOGITS
    yan
    0.76
    agonal
    0.75
    agram
    0.70
    ovan
    0.68
    �醒
    0.67
    iri
    0.67
    qqa
    0.67
    ��
    0.65
    SourceFile
    0.64
    odan
    0.64
    Activations Density 1.149%

    No Known Activations