© 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. 483
    Prev
    Next
    INDEX
    Explanations

    instances of criticism, particularly related to political figures and their actions

    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
    oided
    -0.92
     piercing
    -0.68
     cheek
    -0.67
    inyl
    -0.65
     circum
    -0.65
     shaving
    -0.64
     ballistic
    -0.64
     shave
    -0.64
    phthal
    -0.63
     mouth
    -0.63
    POSITIVE LOGITS
     immigrants
    0.83
     Hait
    0.80
     Sandra
    0.80
    onda
    0.77
     Imran
    0.76
     migrants
    0.74
     Mexicans
    0.73
     Hispanics
    0.71
     GOODMAN
    0.71
     rapists
    0.70
    Activations Density 0.328%

    No Known Activations