© 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. 1755
    Prev
    Next
    INDEX
    Explanations

    special character sequences or symbols, possibly indicating formatting or emphasis in text

    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
    Downloadha
    -0.64
    MpServer
    -0.63
    luaj
    -0.62
    appro
    -0.61
    pai
    -0.60
    netflix
    -0.60
    fits
    -0.58
    iac
    -0.57
    riv
    -0.56
     challeng
    -0.56
    POSITIVE LOGITS
    �
    0.62
    Film
    0.55
    �
    0.52
    �
    0.50
    arms
    0.48
     Grace
    0.48
    �
    0.48
     Clinic
    0.47
     Film
    0.47
    �
    0.47
    Activations Density 0.225%

    No Known Activations