© 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. 700
    Prev
    Next
    INDEX
    Explanations

    repetitions of the phrase "up to" in various contexts

    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
     sugg
    -0.79
    recomm
    -0.73
     subsequ
    -0.70
    ァ
    -0.68
     oun
    -0.68
     proble
    -0.66
     requirements
    -0.66
    archives
    -0.64
    ously
    -0.64
    ️
    -0.64
    POSITIVE LOGITS
    each
    0.71
     Genius
    0.66
     each
    0.65
    OY
    0.63
    jiang
    0.63
    hover
    0.63
    uction
    0.62
    players
    0.61
    awaru
    0.60
    ochet
    0.60
    Activations Density 0.037%

    No Known Activations