© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    the phrase "since then."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    gio
    -0.76
    owing
    -0.68
    comfort
    -0.67
    close
    -0.67
    ��
    -0.67
    usher
    -0.66
    yrinth
    -0.65
    immer
    -0.63
    umn
    -0.63
    complete
    -0.63
    POSITIVE LOGITS
     unemploy
    0.63
     tu
    0.61
    TERN
    0.59
     executions
    0.58
     superst
    0.58
     headlines
    0.58
     outlook
    0.57
     stocks
    0.57
     analysts
    0.56
     Jal
    0.55
    Activations Density 0.047%

    No Known Activations