© 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. 725
    Prev
    Next
    INDEX
    Explanations

    the letter 'Y'

    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
     prevail
    -0.66
     Leadership
    -0.60
     Puppet
    -0.59
     rest
    -0.59
     Rational
    -0.57
     Stronghold
    -0.57
     rested
    -0.56
     REST
    -0.55
     Republic
    -0.55
    gemony
    -0.55
    POSITIVE LOGITS
    ellen
    0.95
    ves
    0.87
    ells
    0.85
    ield
    0.83
    vette
    0.83
    enne
    0.79
    ahoo
    0.78
    elling
    0.78
    annis
    0.78
    ELL
    0.77
    Activations Density 0.017%

    No Known Activations