© 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. 447
    Prev
    Next
    INDEX
    Explanations

    instances of a specific character or symbol

    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
     crosses
    -0.78
     alters
    -0.71
     persists
    -0.71
     unfolds
    -0.70
     violates
    -0.68
     separates
    -0.68
     emerges
    -0.68
     arises
    -0.67
     shakes
    -0.66
     evolves
    -0.65
    POSITIVE LOGITS
    bsite
    0.80
    lia
    0.77
    ahime
    0.77
    igh
    0.74
    ll
    0.74
    vre
    0.73
    vr
    0.70
    cest
    0.68
    �
    0.67
    ths
    0.66
    Activations Density 0.204%

    No Known Activations