© 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. 1638
    Prev
    Next
    INDEX
    Explanations

    instances of the word "no" and related expressions of refusal or negation

    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
    pired
    -0.78
    acted
    -0.70
    ndra
    -0.68
    hovah
    -0.68
    ]),
    -0.66
    gettable
    -0.66
    accompan
    -0.66
    igure
    -0.65
    astical
    -0.64
    MSN
    -0.64
    POSITIVE LOGITS
     corrections
    0.68
    OB
    0.61
     cent
    0.61
    utt
    0.58
    ️
    0.57
     Cort
    0.57
     hoping
    0.55
    onet
    0.54
     trusting
    0.54
     Higher
    0.54
    Activations Density 0.163%

    No Known Activations