© 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. 2169
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe frequency or manner of actions

    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
    phy
    -0.65
    asy
    -0.65
     Torch
    -0.64
     Russo
    -0.63
     Cohen
    -0.62
    fty
    -0.62
     Dunn
    -0.62
     Carter
    -0.61
     Dup
    -0.61
    �
    -0.61
    POSITIVE LOGITS
     solves
    0.85
     translates
    0.81
     collects
    0.75
     employs
    0.75
    oldemort
    0.70
     Accessed
    0.70
    龍�
    0.69
     contains
    0.69
     sells
    0.68
     forgot
    0.68
    Activations Density 0.170%

    No Known Activations