© 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. 722
    Prev
    Next
    INDEX
    Explanations

    conditional statements beginning with "If."

    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
    icycle
    -0.87
    senal
    -0.74
    ucc
    -0.71
    tesy
    -0.68
    otion
    -0.66
     Citation
    -0.66
    )].
    -0.64
    Builder
    -0.63
    blog
    -0.62
    conom
    -0.61
    POSITIVE LOGITS
     true
    0.84
     successful
    0.78
    true
    0.78
     nothing
    0.77
     jurors
    0.70
    Done
    0.68
    fy
    0.68
     positive
    0.66
     truthful
    0.65
     truths
    0.65
    Activations Density 0.058%

    No Known Activations