© 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. 1080
    Prev
    Next
    INDEX
    Explanations

    instances of assertion and proof of ability or performance

    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
     explos
    -0.69
    oop
    -0.67
    bath
    -0.65
    abre
    -0.64
    spl
    -0.63
    arella
    -0.62
     amuse
    -0.61
    atum
    -0.61
     tyrann
    -0.60
    liest
    -0.59
    POSITIVE LOGITS
     comprom
    0.74
     Ud
    0.71
    legates
    0.70
    channelAvailability
    0.68
     Cortana
    0.68
    cius
    0.66
    iciary
    0.63
    CRIP
    0.63
     moderators
    0.63
    vern
    0.63
    Activations Density 0.138%

    No Known Activations