© 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. 1495
    Prev
    Next
    INDEX
    Explanations

    inquiries or questions posed in a text

    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
     lieu
    -0.64
    hetic
    -0.64
    ior
    -0.64
    oxin
    -0.63
    oku
    -0.62
    ainment
    -0.61
    hetically
    -0.60
    IOR
    -0.60
     unbeliev
    -0.59
    ested
    -0.58
    POSITIVE LOGITS
     Does
    0.90
     Are
    0.86
     Why
    0.83
    Does
    0.83
    Are
    0.82
     Should
    0.82
    Why
    0.75
    Can
    0.75
     Who
    0.75
     Is
    0.73
    Activations Density 0.045%

    No Known Activations