Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 383
    Prev
    Next
    INDEX
    Explanations

    the word "just" and its variations in context

    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
    ations
    -0.66
    avorite
    -0.66
    ophical
    -0.64
    atable
    -0.64
    isu
    -0.62
    ティ
    -0.61
    Gate
    -0.61
    arest
    -0.60
    itivity
    -0.60
    Kin
    -0.60
    POSITIVE LOGITS
    bes
    0.78
     weeks
    0.71
    plug
    0.68
     months
    0.68
     hours
    0.66
    bet
    0.65
    per
    0.65
    ror
    0.64
     rebound
    0.62
     days
    0.61
    Activations Density 0.032%

    No Known Activations