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. 65
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wait" and its associated context

    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
    uala
    -0.79
    ⓘ
    -0.70
    龍�
    -0.64
    ulkan
    -0.64
    fol
    -0.63
    ��
    -0.63
     miners
    -0.63
    ツ
    -0.62
    姫
    -0.61
    gdala
    -0.61
    POSITIVE LOGITS
    ther
    0.68
    erald
    0.67
    enser
    0.67
    ipers
    0.65
    eter
    0.63
    versive
    0.63
     recip
    0.63
     Parenthood
    0.62
    equal
    0.62
     till
    0.61
    Activations Density 0.029%

    No Known Activations