© 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. 2992
    Prev
    Next
    INDEX
    Explanations

    expressions indicating positive affirmations or readiness

    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
     liner
    -0.70
    OPLE
    -0.65
     residence
    -0.63
     Canal
    -0.62
     kil
    -0.60
     tick
    -0.60
     slur
    -0.59
     bragging
    -0.59
     bunny
    -0.58
     rollout
    -0.57
    POSITIVE LOGITS
    bane
    0.78
    halla
    0.76
    Europe
    0.73
    ondon
    0.68
    owship
    0.68
    shape
    0.67
    Beg
    0.67
    Images
    0.67
    Pg
    0.66
    Page
    0.65
    Activations Density 2.875%

    No Known Activations