© 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. 3118
    Prev
    Next
    INDEX
    Explanations

    the word "it" and its various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Rib
    -0.61
    ceptions
    -0.61
    rouse
    -0.58
     Tol
    -0.56
    itzer
    -0.55
    ••••
    -0.55
     Pyr
    -0.53
     Divinity
    -0.52
    lected
    -0.51
    ivable
    -0.51
    POSITIVE LOGITS
     )]
    0.93
     survives
    0.79
     solves
    0.78
     depends
    0.78
    alian
    0.77
    ":"/
    0.76
     happens
    0.74
     follows
    0.73
     doesnt
    0.71
     Anyway
    0.71
    Activations Density 0.023%

    No Known Activations