Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 593
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "chance."

    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
     Weeks
    -0.73
    heit
    -0.72
    enza
    -0.68
    vy
    -0.66
    udi
    -0.65
    ocally
    -0.64
     maximal
    -0.63
    enthal
    -0.62
    onis
    -0.62
    verson
    -0.61
    POSITIVE LOGITS
    ケ
    0.64
    icles
    0.63
    iest
    0.63
    ific
    0.63
     avenue
    0.62
    SELECT
    0.61
    idad
    0.60
     toget
    0.59
    ology
    0.59
    rito
    0.59
    Activations Density 0.026%

    No Known Activations