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. 338
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assumptions or beliefs, particularly in a skeptical 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
    AppData
    -0.89
    FactoryReloaded
    -0.79
    window
    -0.76
    soDeliveryDate
    -0.76
    Deal
    -0.76
    antasy
    -0.74
    apply
    -0.72
    ometimes
    -0.71
    quad
    -0.71
    iHUD
    -0.71
    POSITIVE LOGITS
     preserving
    0.72
    asm
    0.67
     simplicity
    0.65
     childbirth
    0.65
     producing
    0.62
     allowing
    0.62
     juggling
    0.61
     incidentally
    0.61
     mankind
    0.61
     raising
    0.61
    Activations Density 0.130%

    No Known Activations