© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 749
    Prev
    Next
    INDEX
    Explanations

    references to indefinite quantities or vague descriptors

    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
    senal
    -0.72
    ategory
    -0.67
    ressor
    -0.66
    irlfriend
    -0.66
    vertisement
    -0.65
    abase
    -0.64
    DeliveryDate
    -0.64
     guiActiveUnfocused
    -0.64
    Cola
    -0.64
     withd
    -0.63
    POSITIVE LOGITS
     cases
    0.82
     laure
    0.79
    ones
    0.73
     fronts
    0.67
     instances
    0.67
     seats
    0.66
     aspects
    0.66
     areas
    0.65
    izations
    0.65
    oft
    0.65
    Activations Density 0.106%

    No Known Activations