Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 390
    Prev
    Next
    INDEX
    Explanations

    references to the name "Taft."

    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
    oir
    -0.85
    gc
    -0.79
    fu
    -0.77
    bors
    -0.73
    fw
    -0.71
    monds
    -0.70
    roe
    -0.69
    oku
    -0.67
    tes
    -0.67
    mas
    -0.67
    POSITIVE LOGITS
    hess
    0.79
    xton
    0.75
    esthesia
    0.67
    ub
    0.64
     metic
    0.61
    existence
    0.60
    DOS
    0.60
    htaking
    0.59
    verty
    0.59
    ebook
    0.59
    Activations Density 0.048%

    No Known Activations