© 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. 2097
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation usage, specifically commas

    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
    atana
    -0.78
    hal
    -0.74
    aho
    -0.72
    arate
    -0.71
    umbs
    -0.67
    ito
    -0.66
    inea
    -0.66
    inx
    -0.65
    tt
    -0.64
    iki
    -0.64
    POSITIVE LOGITS
     namely
    0.67
     majorities
    0.67
     meanwhile
    0.67
     preferably
    0.66
     behavi
    0.66
     moreover
    0.65
     totality
    0.64
    ////////////////////////////////
    0.61
     foregoing
    0.60
     beware
    0.60
    Activations Density 0.201%

    No Known Activations