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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1019
    Prev
    Next
    INDEX
    Explanations

    sentences or statements that present factual information

    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
     adding
    -0.69
     premier
    -0.67
    reon
    -0.65
     expanding
    -0.62
    \/
    -0.62
     correcting
    -0.60
     arch
    -0.59
    IDE
    -0.58
     escalating
    -0.58
     interior
    -0.58
    POSITIVE LOGITS
     It
    0.76
     Readers
    0.72
     Having
    0.71
     Through
    0.71
     Journalists
    0.68
     Anyone
    0.68
     Components
    0.67
     Together
    0.66
     Along
    0.66
     Throughout
    0.65
    Activations Density 0.635%

    No Known Activations