© 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. 1292
    Prev
    Next
    INDEX
    Explanations

    the presence of special characters or symbols

    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
    rir
    -0.65
     sadly
    -0.65
    istani
    -0.64
     conform
    -0.62
    aneously
    -0.62
    ANE
    -0.61
    istrate
    -0.61
     rightfully
    -0.60
    itters
    -0.60
     Dragonbound
    -0.59
    POSITIVE LOGITS
    ��
    0.78
    ��
    0.72
    dding
    0.69
    �
    0.69
     Sting
    0.69
    vern
    0.68
     Bet
    0.68
    �
    0.68
    �
    0.66
    cking
    0.66
    Activations Density 0.090%

    No Known Activations