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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 986
    Prev
    Next
    INDEX
    Explanations

    phrases expressing negation or unsupported claims

    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
    hyde
    -0.80
    etheless
    -0.75
    leave
    -0.72
    lege
    -0.67
    immer
    -0.67
    empt
    -0.65
    comfort
    -0.64
    perse
    -0.64
    erest
    -0.63
    anship
    -0.63
    POSITIVE LOGITS
    IQ
    0.65
     Waves
    0.61
     waves
    0.60
    TPS
    0.59
     Gutenberg
    0.59
     homeless
    0.58
     photographer
    0.57
    quickShipAvailable
    0.57
     authenticated
    0.55
     underway
    0.55
    Activations Density 0.079%

    No Known Activations