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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 665
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a focus on ensuring accountability or 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
    vertisement
    -0.78
     pione
    -0.77
    apeake
    -0.74
    ivery
    -0.74
    icient
    -0.73
    arlane
    -0.72
    ailable
    -0.71
    aired
    -0.71
    anship
    -0.71
    ngth
    -0.70
    POSITIVE LOGITS
     nothing
    0.70
    no
    0.68
     atheism
    0.67
     no
    0.65
     neither
    0.65
     prayers
    0.64
     atheists
    0.64
     minors
    0.63
     foreigners
    0.62
     loopholes
    0.62
    Activations Density 0.068%

    No Known Activations