© 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. 2913
    Prev
    Next
    INDEX
    Explanations

    expressions related to causing or leading to significant events or impacts

    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
    ramids
    -0.82
    ゼウス
    -0.76
    kas
    -0.68
    miah
    -0.66
    uted
    -0.65
    ベ
    -0.64
    dimensional
    -0.64
    mini
    -0.63
    selves
    -0.63
    ée
    -0.63
    POSITIVE LOGITS
     observers
    1.04
     analysts
    0.92
     readers
    0.91
     critics
    0.88
     commentators
    0.85
     viewers
    0.85
     skeptics
    0.84
     commenters
    0.82
     pundits
    0.80
     advocates
    0.79
    Activations Density 0.210%

    No Known Activations