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. 393
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a period

    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
    quit
    -0.78
    culus
    -0.75
    usalem
    -0.73
     nep
    -0.73
     dup
    -0.73
     coh
    -0.64
    morrow
    -0.64
    country
    -0.63
    prime
    -0.63
    ascus
    -0.63
    POSITIVE LOGITS
     Among
    0.89
     They
    0.85
     These
    0.84
     Dreams
    0.81
     Their
    0.81
     Being
    0.80
     Through
    0.80
     Such
    0.80
     Taken
    0.80
    士
    0.77
    Activations Density 0.635%

    No Known Activations