© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 486
    Prev
    Next
    INDEX
    Explanations

    negative contractions indicating negation or absence

    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
    lance
    -0.95
    place
    -0.82
    ANCE
    -0.78
     Cheong
    -0.72
    leon
    -0.72
    lement
    -0.72
    wake
    -0.71
    prototype
    -0.71
    framework
    -0.70
    lihood
    -0.68
    POSITIVE LOGITS
     penetrating
    0.82
     progressing
    0.80
    �
    0.75
     constrained
    0.74
     jammed
    0.70
     geographically
    0.70
     confined
    0.70
     unheard
    0.69
     prone
    0.69
     controlled
    0.67
    Activations Density 0.027%

    No Known Activations