Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 143
    Prev
    Next
    INDEX
    Explanations

    sentences containing specific dates

    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
    cox
    -0.70
     contrace
    -0.68
     helicop
    -0.67
    escription
    -0.67
    ciating
    -0.66
    abama
    -0.66
    oğ
    -0.66
     mosqu
    -0.65
    dt
    -0.64
     thous
    -0.64
    POSITIVE LOGITS
     arte
    0.61
    Scene
    0.61
    AE
    0.58
    iri
    0.57
    rome
    0.56
    ラン
    0.55
    olitan
    0.55
     Created
    0.54
    ='
    0.54
    edia
    0.54
    Activations Density 0.010%

    No Known Activations