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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1995
    Prev
    Next
    INDEX
    Explanations

    statements regarding regulations or penalties related to permits and compliance

    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
     disasters
    -0.69
     Fuk
    -0.66
     Chrys
    -0.63
    traumatic
    -0.61
     cleaners
    -0.60
     disastrous
    -0.59
    productive
    -0.58
     earthquakes
    -0.58
    youtu
    -0.58
    cephal
    -0.57
    POSITIVE LOGITS
     automatically
    0.75
     waive
    0.71
    ][/
    0.68
    subject
    0.68
     additionally
    0.66
     receive
    0.66
    ogie
    0.65
     afforded
    0.65
     theoretically
    0.64
     aloud
    0.64
    Activations Density 0.290%

    No Known Activations