© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1001
    Prev
    Next
    INDEX
    Explanations

    statements about difficulty or challenges

    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
     myster
    -0.73
     ambig
    -0.67
     cue
    -0.64
     ambiguity
    -0.63
     opio
    -0.63
     surprise
    -0.62
     unwelcome
    -0.62
     dawn
    -0.62
    likely
    -0.62
    skip
    -0.61
    POSITIVE LOGITS
    ourt
    0.77
    ript
    0.75
     �
    0.74
    avage
    0.71
     ([
    0.70
    oby
    0.68
     [
    0.66
    ucket
    0.66
    eca
    0.65
    endment
    0.65
    Activations Density 0.258%

    No Known Activations