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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 732
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Ble."

    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
    shire
    -0.81
    stone
    -0.74
    onomy
    -0.70
    icularly
    -0.68
    oran
    -0.68
    oco
    -0.68
     Affairs
    -0.67
    inas
    -0.66
    stones
    -0.64
    hall
    -0.64
    POSITIVE LOGITS
    ciating
    0.89
    eping
    0.86
    eking
    0.84
    eker
    0.83
    AKING
    0.81
    eks
    0.76
    phant
    0.72
    vice
    0.71
    krit
    0.70
    eper
    0.70
    Activations Density 0.046%

    No Known Activations