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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 296
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a conditional relationship or a requirement

    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
     Ples
    -0.72
    anza
    -0.66
    sg
    -0.63
    ���
    -0.62
     ende
    -0.62
    antha
    -0.62
    haw
    -0.61
    cludes
    -0.60
    calling
    -0.59
    erd
    -0.59
    POSITIVE LOGITS
    imental
    0.69
    istor
    0.69
    isphere
    0.69
    iments
    0.67
    itely
    0.64
    tumblr
    0.62
     yours
    0.60
    ICS
    0.60
    icons
    0.59
    icon
    0.58
    Activations Density 0.010%

    No Known Activations