© 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. 530
    Prev
    Next
    INDEX
    Explanations

    expressions of love and affection

    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
     Rubin
    -0.67
     Slav
    -0.66
     Chero
    -0.65
     obscurity
    -0.64
     dusty
    -0.64
     vacant
    -0.61
     Entered
    -0.61
     Zamb
    -0.61
     Technician
    -0.60
     pristine
    -0.60
    POSITIVE LOGITS
    ヴ
    0.85
     Pwr
    0.80
    ティ
    0.77
    pecially
    0.74
    uper
    0.73
    ffer
    0.73
    龍喚士
    0.72
    CLAIM
    0.72
    ーク
    0.71
     enough
    0.70
    Activations Density 0.404%

    No Known Activations