© 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. 3192
    Prev
    Next
    INDEX
    Explanations

    expressions of comparison involving "in a way that."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    quartered
    -0.88
    etheless
    -0.83
    NetMessage
    -0.82
    urch
    -0.72
    bably
    -0.66
    assed
    -0.65
    seek
    -0.65
     accur
    -0.65
    zed
    -0.64
    cffffcc
    -0.63
    POSITIVE LOGITS
    emale
    0.67
     exceeds
    0.61
     constituent
    0.58
    RIPT
    0.58
    zanne
    0.56
     forg
    0.56
     privileges
    0.56
    erry
    0.55
    anian
    0.55
    enance
    0.55
    Activations Density 0.077%

    No Known Activations