© 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. 1565
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of taking action or doing something

    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
    ovember
    -1.09
    RFC
    -0.80
    ntil
    -0.77
    efer
    -0.75
    phabet
    -0.73
    bda
    -0.73
    oping
    -0.70
    Allows
    -0.69
    ˈ
    -0.68
     CrossRef
    -0.66
    POSITIVE LOGITS
     EW
    0.76
     AW
    0.75
    ocular
    0.66
     Essential
    0.64
    ateful
    0.63
     innocence
    0.61
     EL
    0.59
     inex
    0.58
     intervention
    0.58
    emin
    0.58
    Activations Density 0.066%

    No Known Activations