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. 53
    Prev
    Next
    INDEX
    Explanations

    concepts involving uncertainty or ambiguity

    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
    alian
    -0.86
    ohn
    -0.74
    leys
    -0.72
    ourced
    -0.71
    ourcing
    -0.68
    meter
    -0.68
    kus
    -0.67
    iple
    -0.66
    incerity
    -0.66
    ivia
    -0.66
    POSITIVE LOGITS
     bind
    0.75
    �
    0.69
    -+-+-+-+
    0.65
    ゴン
    0.64
     delaying
    0.62
    ーン
    0.61
    azines
    0.60
    �
    0.60
     promising
    0.60
    =-=-
    0.60
    Activations Density 0.226%

    No Known Activations