© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 995
    Prev
    Next
    INDEX
    Explanations

    questions framed as hypotheticals

    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
     effected
    -0.65
    govtrack
    -0.63
     reper
    -0.61
     embr
    -0.61
    grave
    -0.60
    essen
    -0.60
    SPONSORED
    -0.59
     destro
    -0.59
     lapse
    -0.59
     behav
    -0.58
    POSITIVE LOGITS
     Hog
    0.64
    ANY
    0.63
     anyone
    0.63
     Sexy
    0.63
    ween
    0.61
    �
    0.61
     Imper
    0.60
     Bie
    0.60
    YL
    0.59
     Younger
    0.59
    Activations Density 0.015%

    No Known Activations