© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1275
    Prev
    Next
    INDEX
    Explanations

    the frequency of appearances on television or media platforms

    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
    nex
    -0.66
    Tube
    -0.65
    版
    -0.64
    Discussion
    -0.63
     rooting
    -0.63
     grounding
    -0.62
     horizont
    -0.61
     saddle
    -0.59
     heterogeneity
    -0.59
     participation
    -0.58
    POSITIVE LOGITS
    ymes
    0.85
    ype
    0.76
    ippi
    0.75
     occasions
    0.72
    leased
    0.71
    ftime
    0.68
    etime
    0.65
    certain
    0.64
    realDonaldTrump
    0.64
    een
    0.62
    Activations Density 0.124%

    No Known Activations