© 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. 2087
    Prev
    Next
    INDEX
    Explanations

    terms related to avoiding detection or circumventing restrictions

    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
    faced
    -0.68
    night
    -0.67
    bell
    -0.67
    ById
    -0.65
    ------
    -0.64
    ls
    -0.64
    inis
    -0.62
    opsis
    -0.61
    KK
    -0.61
    NN
    -0.60
    POSITIVE LOGITS
     restraints
    0.75
     checks
    0.69
     prohibitions
    0.66
     Standards
    0.66
    agall
    0.65
     permissible
    0.64
     handcuffs
    0.64
    ancer
    0.64
    escription
    0.64
    Downloadha
    0.64
    Activations Density 0.087%

    No Known Activations