© 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. 1082
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscription and newsletter sign-ups

    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
     pause
    -0.74
     renewed
    -0.71
    porary
    -0.68
     unexpectedly
    -0.68
     setbacks
    -0.66
     une
    -0.66
     reversal
    -0.65
     departures
    -0.65
     durable
    -0.64
     unexpected
    -0.64
    POSITIVE LOGITS
    ��
    0.74
    bos
    0.69
     Ivy
    0.69
    odon
    0.66
     Babylon
    0.65
     Thur
    0.61
     Sturgeon
    0.61
     Tibet
    0.61
     Swordsman
    0.60
    argon
    0.58
    Activations Density 0.007%

    No Known Activations