© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 984
    Prev
    Next
    INDEX
    Explanations

    the word "isn't" in various forms to emphasize 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
    lace
    -0.77
     *)
    -0.76
    leon
    -0.74
     Nare
    -0.72
    agos
    -0.71
    neau
    -0.69
    ourt
    -0.67
    riv
    -0.66
    jar
    -0.66
     Rosenstein
    -0.66
    POSITIVE LOGITS
     exha
    0.83
     crazy
    0.74
     unprecedented
    0.74
     unheard
    0.73
     exhaustive
    0.68
    userc
    0.68
    EVA
    0.65
     unseen
    0.63
     pse
    0.63
     undermin
    0.63
    Activations Density 0.023%

    No Known Activations