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. 104
    Prev
    Next
    INDEX
    Explanations

    negations and phrases expressing disagreement or denial

    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
    aler
    -0.65
    ims
    -0.62
    liest
    -0.61
    hesis
    -0.60
    kees
    -0.60
    ellen
    -0.60
    thing
    -0.60
    ogen
    -0.60
    IRE
    -0.60
    heads
    -0.59
    POSITIVE LOGITS
    icia
    0.69
    pmwiki
    0.68
     pleasant
    0.64
     horm
    0.63
     Nerd
    0.62
    pload
    0.61
     accident
    0.60
     Punk
    0.60
     advisable
    0.60
    ice
    0.59
    Activations Density 0.060%

    No Known Activations