© 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. 2729
    Prev
    Next
    INDEX
    Explanations

    expressions of novelty or experiences that have never occurred before

    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
     flourish
    -0.80
     prevail
    -0.74
     widening
    -0.74
     intensify
    -0.73
     declaration
    -0.71
     continuation
    -0.71
     abound
    -0.70
     narrowing
    -0.70
     intens
    -0.69
     widen
    -0.69
    POSITIVE LOGITS
     heard
    0.96
     ridden
    0.95
     slept
    0.89
     witnessed
    0.86
     watched
    0.84
     Heard
    0.84
    lost
    0.82
     gotten
    0.82
     seen
    0.80
    �
    0.79
    Activations Density 0.047%

    No Known Activations