© 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. 1493
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to ethical or theoretical frameworks

    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
    ume
    -0.73
    udeau
    -0.69
     shells
    -0.68
     ages
    -0.66
    hers
    -0.65
    ESH
    -0.63
     VIDEOS
    -0.63
     accompl
    -0.62
    ading
    -0.62
    inals
    -0.61
    POSITIVE LOGITS
    gravity
    0.80
    mut
    0.78
    cultural
    0.76
    property
    0.75
    conserv
    0.70
    etheless
    0.69
    angan
    0.69
    nuclear
    0.68
    fixes
    0.68
    social
    0.68
    Activations Density 0.103%

    No Known Activations