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. 142
    Prev
    Next
    INDEX
    Explanations

    negations and phrases that challenge the concept of independence or ownership

    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
    oway
    -0.83
    aughtered
    -0.77
    VER
    -0.76
    owship
    -0.72
    tons
    -0.70
    original
    -0.69
    very
    -0.69
    rans
    -0.69
    NA
    -0.66
    enery
    -0.66
    POSITIVE LOGITS
     mere
    0.77
     akin
    0.73
     artif
    0.70
     confer
    0.67
     disadvant
    0.67
     merely
    0.65
     implying
    0.65
     conflic
    0.65
     extortion
    0.63
     sectarian
    0.63
    Activations Density 0.139%

    No Known Activations