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. 389
    Prev
    Next
    INDEX
    Explanations

    the word "but" in various contexts

    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
     Berger
    -0.66
     antic
    -0.63
     Mandela
    -0.63
     Brett
    -0.63
     Holocaust
    -0.62
     Patri
    -0.62
     lies
    -0.62
     Rover
    -0.61
     ???
    -0.59
     Roose
    -0.58
    POSITIVE LOGITS
    sts
    0.99
    term
    0.95
    chery
    0.89
    tes
    0.89
    chel
    0.88
    Reviewer
    0.88
    chers
    0.87
    chie
    0.86
    aceous
    0.84
    ters
    0.84
    Activations Density 0.063%

    No Known Activations