© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 928
    Prev
    Next
    INDEX
    Explanations

    references to Donald Trump and his 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
    */(
    -0.74
     Thumbnails
    -0.67
     Oo
    -0.65
    NESS
    -0.65
    Released
    -0.64
     ILCS
    -0.64
    igslist
    -0.63
    leys
    -0.62
    xual
    -0.62
    ═
    -0.62
    POSITIVE LOGITS
    ena
    0.68
    ctic
    0.65
    fal
    0.62
    mid
    0.61
     lofty
    0.60
     dire
    0.60
    jah
    0.60
     chant
    0.59
    colm
    0.59
     prolific
    0.59
    Activations Density 0.096%

    No Known Activations