© 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. 1932
    Prev
    Next
    INDEX
    Explanations

    instances of refusal or non-compliance in situations involving coercion

    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
    rawdownloadcloneembedreportprint
    -0.74
     tarn
    -0.72
     Uz
    -0.67
     intersect
    -0.66
     erupted
    -0.61
     malls
    -0.61
     sensed
    -0.61
     paved
    -0.58
     rift
    -0.57
     rocked
    -0.56
    POSITIVE LOGITS
    erer
    0.69
    hetti
    0.68
    wait
    0.65
    WARD
    0.64
    Grade
    0.63
    geries
    0.63
     CPR
    0.62
    Artist
    0.61
    ause
    0.60
    uid
    0.60
    Activations Density 0.243%

    No Known Activations