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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 529
    Prev
    Next
    INDEX
    Explanations

    statements involving numerical predictions or assessments

    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
    Els
    -0.73
     LOT
    -0.66
    ��
    -0.63
    uyomi
    -0.62
    OTOS
    -0.62
    aer
    -0.62
    ISA
    -0.61
    GBT
    -0.61
     Hastings
    -0.59
    METHOD
    -0.59
    POSITIVE LOGITS
    iah
    0.75
    icut
    0.73
    idents
    0.72
    itivity
    0.68
    ufact
    0.67
     transported
    0.66
    prints
    0.66
    producing
    0.65
    produced
    0.63
    estate
    0.62
    Activations Density 0.036%

    No Known Activations