© 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. 1689
    Prev
    Next
    INDEX
    Explanations

    expressions emphasizing a lack of necessity or requirements

    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
    ene
    -0.78
    kept
    -0.74
    iar
    -0.69
    ounters
    -0.68
    onet
    -0.65
    redit
    -0.65
    subject
    -0.65
    ━
    -0.65
    ables
    -0.65
    onomy
    -0.64
    POSITIVE LOGITS
     Rescue
    0.77
    cially
    0.75
     revive
    0.66
     special
    0.65
     miraculous
    0.64
     rush
    0.64
     Gold
    0.63
     costly
    0.62
     elabor
    0.62
     fancy
    0.62
    Activations Density 0.026%

    No Known Activations