© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1712
    Prev
    Next
    INDEX
    Explanations

    negative expressions or phrases indicating absence or denial

    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
    quickShipAvailable
    -0.67
     plenty
    -0.63
     intensify
    -0.59
     immensely
    -0.58
    Synopsis
    -0.58
     ways
    -0.58
     pretext
    -0.58
     underway
    -0.57
     quicker
    -0.57
    EStream
    -0.56
    POSITIVE LOGITS
    eal
    0.76
    aea
    0.72
    nor
    0.71
    iatrics
    0.70
    ync
    0.69
    necess
    0.67
    letters
    0.64
    Alert
    0.64
    abase
    0.64
    ear
    0.63
    Activations Density 0.221%

    No Known Activations