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. 250
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing quality and experience

    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
    INESS
    -0.76
    Aw
    -0.71
    sylv
    -0.68
    abeth
    -0.67
    quished
    -0.65
    achus
    -0.64
    iment
    -0.64
    Sounds
    -0.64
    eries
    -0.63
    Skill
    -0.63
    POSITIVE LOGITS
     captcha
    0.71
     BST
    0.65
     QC
    0.64
     pacing
    0.64
     bomber
    0.63
     rewritten
    0.63
     narrator
    0.63
     editing
    0.61
     rendition
    0.61
     authenticated
    0.60
    Activations Density 0.161%

    No Known Activations