© 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. 1698
    Prev
    Next
    INDEX
    Explanations

    occurrences of commas indicating lists or separate clauses in sentences

    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
    龍契士
    -0.71
    redo
    -0.68
    mma
    -0.68
    ��
    -0.67
    mad
    -0.63
    fre
    -0.62
    goo
    -0.61
    OE
    -0.60
    CCC
    -0.59
    ��
    -0.59
    POSITIVE LOGITS
     shares
    0.88
     insists
    0.84
     receives
    0.83
     relates
    0.81
     claims
    0.81
     wears
    0.81
     uses
    0.80
     believes
    0.78
     acknowledges
    0.77
     maintains
    0.76
    Activations Density 0.111%

    No Known Activations