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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2054
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate financial considerations and logical reasoning

    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
    phrine
    -0.61
     Frag
    -0.60
    etics
    -0.58
     suffice
    -0.58
     unde
    -0.57
     derog
    -0.56
     chatter
    -0.56
     fac
    -0.55
     pesky
    -0.54
     clip
    -0.54
    POSITIVE LOGITS
    sure
    0.84
     sure
    0.72
    assing
    0.72
     pilgr
    0.71
     landfall
    0.70
    tu
    0.69
    hift
    0.68
    eday
    0.65
    �
    0.65
    iss
    0.65
    Activations Density 1.327%

    No Known Activations