© 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. 1284
    Prev
    Next
    INDEX
    Explanations

    references to romantic relationships or couples

    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
     POV
    -0.75
    Down
    -0.65
    Dri
    -0.63
    ITAL
    -0.62
     headlights
    -0.62
     Targ
    -0.61
    Ess
    -0.61
     Consent
    -0.60
    edin
    -0.59
    Interest
    -0.59
    POSITIVE LOGITS
    senal
    0.89
    aughtered
    0.79
    uggest
    0.74
     Meow
    0.70
    arent
    0.63
    raq
    0.63
    daq
    0.63
     Ranked
    0.63
    uctions
    0.63
    anqu
    0.63
    Activations Density 0.031%

    No Known Activations