© 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. 1579
    Prev
    Next
    INDEX
    Explanations

    action verbs that indicate referencing, emphasizing, or invoking topics and themes

    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
    Deal
    -0.69
    AX
    -0.69
    Skill
    -0.67
    ……………………
    -0.66
     upfront
    -0.66
    ENSE
    -0.65
    SIZE
    -0.62
    Min
    -0.62
    ENN
    -0.62
    END
    -0.62
    POSITIVE LOGITS
    ingen
    0.72
    riad
    0.67
     regress
    0.64
     corrupt
    0.62
     recent
    0.62
    guyen
    0.61
    �醒
    0.61
    ternal
    0.61
    ��
    0.60
    terson
    0.60
    Activations Density 0.177%

    No Known Activations