© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 872
    Prev
    Next
    INDEX
    Explanations

    the phrase "I do" 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
    ゴン
    -0.93
    hovah
    -0.89
    龍契士
    -0.88
    ウス
    -0.84
    alkyrie
    -0.79
    Leader
    -0.77
    �
    -0.76
    wolf
    -0.76
    raltar
    -0.72
    Dash
    -0.70
    POSITIVE LOGITS
     intend
    0.86
    zed
    0.78
    oms
    0.76
     want
    0.75
     owe
    0.74
     WANT
    0.73
     intends
    0.73
     wonders
    0.72
     hereby
    0.70
     expects
    0.70
    Activations Density 0.039%

    No Known Activations