© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1094
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest instruction or guidance

    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
    ingen
    -0.78
     CVE
    -0.65
    abouts
    -0.64
    oys
    -0.64
    Feature
    -0.63
    prototype
    -0.62
    Rating
    -0.61
     bombshell
    -0.60
    Trend
    -0.60
    landish
    -0.60
    POSITIVE LOGITS
     breathe
    0.74
     infl
    0.66
    aced
    0.64
     adherent
    0.62
     ejected
    0.61
    ield
    0.60
    ��
    0.60
     tolerate
    0.60
     convert
    0.60
    orter
    0.59
    Activations Density 0.101%

    No Known Activations