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. 362
    Prev
    Next
    INDEX
    Explanations

    references to the character or individual initialed "G."

    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
    cients
    -0.61
     GP
    -0.60
     sincere
    -0.59
     sto
    -0.58
     Gym
    -0.57
     train
    -0.57
     subscribers
    -0.56
     Fifth
    -0.56
     stars
    -0.56
     Git
    -0.56
    POSITIVE LOGITS
    rieve
    1.04
    ARY
    0.99
    entry
    0.95
    arten
    0.94
    iannopoulos
    0.94
    ERAL
    0.93
    wyn
    0.90
    OULD
    0.88
    rosso
    0.87
    iry
    0.86
    Activations Density 0.030%

    No Known Activations