© 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. 666
    Prev
    Next
    INDEX
    Explanations

    complete sentences or statements

    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
    htaking
    -0.79
    ike
    -0.73
     wrought
    -0.70
     outrageous
    -0.68
    �
    -0.66
     outlandish
    -0.64
     appalling
    -0.62
     wond
    -0.62
     bullish
    -0.60
     eleph
    -0.60
    POSITIVE LOGITS
     Expend
    0.83
     Important
    0.81
     Pupp
    0.81
     Conversely
    0.80
     Being
    0.80
     Taste
    0.79
     Ply
    0.79
     Giving
    0.78
     Start
    0.78
     Always
    0.78
    Activations Density 0.383%

    No Known Activations