© 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. 1812
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific letters and short prepositions in the text

    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
    urat
    -0.67
     marrow
    -0.62
    uner
    -0.61
    neum
    -0.61
    forced
    -0.60
     lap
    -0.59
    �
    -0.59
    ニ
    -0.58
    rice
    -0.58
    uyomi
    -0.57
    POSITIVE LOGITS
    ivas
    0.72
    os
    0.72
    INC
    0.71
    out
    0.65
     opio
    0.64
     out
    0.62
    ois
    0.61
    outside
    0.61
     outs
    0.60
    icism
    0.59
    Activations Density 1.265%

    No Known Activations