© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 577
    Prev
    Next
    INDEX
    Explanations

    expressions related to eligibility for audience access by publishers

    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
     aid
    -0.66
     approaches
    -0.65
     caution
    -0.61
    population
    -0.59
     Garner
    -0.56
     discl
    -0.56
    irrel
    -0.55
     advances
    -0.55
    >[
    -0.55
     influences
    -0.55
    POSITIVE LOGITS
    idia
    0.69
    Cola
    0.69
    Whe
    0.66
    obbies
    0.64
    Beat
    0.63
    cious
    0.63
    ��極
    0.61
    sych
    0.60
    irlfriend
    0.60
    ods
    0.59
    Activations Density 0.011%

    No Known Activations