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. 77
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the potential for improvement or contribution

    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
    umption
    -0.76
    coe
    -0.68
    ios
    -0.65
    leys
    -0.65
    gravity
    -0.64
    hower
    -0.64
    gey
    -0.62
    obar
    -0.62
    oak
    -0.62
    ��
    -0.62
    POSITIVE LOGITS
     answer
    0.72
     afraid
    0.67
    IFIED
    0.60
     ashamed
    0.58
    STATE
    0.58
     offer
    0.58
    _-
    0.55
    Angelo
    0.55
    ifies
    0.54
     learnt
    0.54
    Activations Density 0.036%

    No Known Activations