© 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. 1591
    Prev
    Next
    INDEX
    Explanations

    clauses and phrases that indicate conditions or restrictions

    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
     Paste
    -0.70
     Reach
    -0.69
     Banner
    -0.67
    Charges
    -0.66
     Trigger
    -0.65
    �
    -0.64
     sidx
    -0.63
     Kik
    -0.62
     Danger
    -0.61
    Magikarp
    -0.59
    POSITIVE LOGITS
    whatever
    0.85
    led
    0.74
     namely
    0.71
    withstanding
    0.70
    odd
    0.70
    while
    0.68
    odies
    0.67
    rather
    0.67
    together
    0.66
    provided
    0.66
    Activations Density 0.360%

    No Known Activations