© 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. 3052
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or contrast between two sides or concepts

    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
    anooga
    -0.71
     taxp
    -0.70
    akening
    -0.67
     disse
    -0.65
    insula
    -0.63
    ector
    -0.61
     lineback
    -0.60
     epid
    -0.60
     Berm
    -0.59
    Services
    -0.58
    POSITIVE LOGITS
    ivas
    0.72
    onduct
    0.65
    mitt
    0.65
    ue
    0.64
    uel
    0.64
    av
    0.64
    eat
    0.63
    エル
    0.63
    roc
    0.62
    ugg
    0.62
    Activations Density 0.103%

    No Known Activations