© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 562
    Prev
    Next
    INDEX
    Explanations

    action-oriented verbs and phrases indicating completion or achievement

    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
    ��
    -0.84
    istani
    -0.73
    ガ
    -0.72
    �
    -0.72
    obe
    -0.70
    agger
    -0.69
    kamp
    -0.68
    orem
    -0.68
    likely
    -0.67
    stru
    -0.67
    POSITIVE LOGITS
     oneself
    0.81
     countless
    0.80
     their
    0.80
     exhaustive
    0.76
     numerous
    0.76
     themselves
    0.75
     rave
    0.73
     endless
    0.72
     utmost
    0.72
     extensive
    0.71
    Activations Density 1.118%

    No Known Activations