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. 225
    Prev
    Next
    INDEX
    Explanations

    the word "that" in various contexts

    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
    ��
    -0.89
    omorphic
    -0.86
    furt
    -0.85
    esm
    -0.84
    lopp
    -0.78
    ��
    -0.76
    ominated
    -0.73
    \/\/
    -0.73
    onde
    -0.69
    byss
    -0.69
    POSITIVE LOGITS
     messenger
    0.68
     impression
    0.63
     illusion
    0.62
     someone
    0.61
     guy
    0.60
     same
    0.60
    ^^^^
    0.58
     buddy
    0.57
     option
    0.56
     message
    0.56
    Activations Density 0.116%

    No Known Activations