© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limits or maximum thresholds

    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
     omit
    -0.74
     substitutes
    -0.66
    ğ
    -0.66
     simply
    -0.65
     miscon
    -0.65
    ´
    -0.63
     ignores
    -0.62
    soever
    -0.62
     mis
    -0.61
    zanne
    -0.61
    POSITIVE LOGITS
    clerosis
    0.76
    saw
    0.73
    unity
    0.69
    enhagen
    0.68
    division
    0.66
    rium
    0.63
     Nationals
    0.63
    urses
    0.62
     Eternity
    0.62
    restling
    0.62
    Activations Density 0.050%

    No Known Activations