© 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. 1621
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions taken by individuals that contribute to a memorable impact

    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
    ヴ
    -0.79
    Write
    -0.75
    Story
    -0.72
    Draw
    -0.68
    武
    -0.67
    utral
    -0.65
    Be
    -0.63
    Solution
    -0.61
    Desktop
    -0.61
    Never
    -0.59
    POSITIVE LOGITS
     strides
    0.77
    zens
    0.67
    irlf
    0.67
    zes
    0.66
    lem
    0.64
    inia
    0.62
    ppo
    0.62
    ITED
    0.60
     repairs
    0.60
     sshd
    0.60
    Activations Density 0.036%

    No Known Activations