© 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. 1338
    Prev
    Next
    INDEX
    Explanations

    phrases related to being daydreamy or absent-minded

    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
    itone
    -0.89
    hedral
    -0.81
    uds
    -0.78
    iris
    -0.74
    nesota
    -0.74
    issan
    -0.72
    idth
    -0.71
    hest
    -0.71
    verse
    -0.71
    onic
    -0.70
    POSITIVE LOGITS
     ens
    0.68
     sergeant
    0.67
     tremend
    0.67
     recy
    0.67
     Coulter
    0.64
     Niet
    0.64
     handic
    0.64
     timely
    0.63
     mechanic
    0.62
     induct
    0.62
    Activations Density 0.111%

    No Known Activations