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. 245
    Prev
    Next
    INDEX
    Explanations

    references to shared experiences and togetherness

    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
    ワン
    -0.73
    �
    -0.73
    ppo
    -0.73
    theless
    -0.72
    hess
    -0.70
     Stretch
    -0.69
    gling
    -0.69
    ��
    -0.68
    WithNo
    -0.68
    �
    -0.68
    POSITIVE LOGITS
    ima
    0.64
    arium
    0.63
     innoc
    0.63
     herd
    0.61
    upp
    0.60
    othe
    0.60
     subscribing
    0.57
     subscribed
    0.57
     broadcasting
    0.57
     catalog
    0.57
    Activations Density 0.092%

    No Known Activations