© 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. 2820
    Prev
    Next
    INDEX
    Explanations

    instances of the sound "ha."

    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
     intrusive
    -0.68
     caring
    -0.66
     Parenthood
    -0.65
     interest
    -0.63
     illeg
    -0.61
     Interest
    -0.60
     needing
    -0.60
     Genocide
    -0.59
     lingering
    -0.59
    ingham
    -0.58
    POSITIVE LOGITS
    vantage
    0.78
    ong
    0.77
    ollah
    0.77
    �
    0.75
    én
    0.75
    Beta
    0.75
    Gam
    0.75
    Dispatch
    0.73
    odge
    0.71
    uj
    0.71
    Activations Density 0.023%

    No Known Activations