© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 801
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "open" and its variations in different contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     anatomy
    -0.69
    agra
    -0.67
    odor
    -0.64
     depended
    -0.63
    uld
    -0.63
     serum
    -0.60
    sels
    -0.60
     flashlight
    -0.59
     urge
    -0.59
     nour
    -0.58
    POSITIVE LOGITS
    \\\\\\\\
    1.01
    CLASS
    0.73
    Cass
    0.73
    Leaks
    0.72
    Barn
    0.71
     Kear
    0.69
    ource
    0.67
    �
    0.67
    ELY
    0.67
    ��
    0.66
    Activations Density 0.018%

    No Known Activations