© 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. 3106
    Prev
    Next
    INDEX
    Explanations

    variations of the letter "o" in different contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    romeda
    -0.68
    lass
    -0.66
    UTERS
    -0.66
    owship
    -0.64
    voy
    -0.64
    kick
    -0.63
    rix
    -0.63
    luck
    -0.62
    rip
    -0.59
    oppy
    -0.59
    POSITIVE LOGITS
    ğ
    0.99
    quet
    0.90
    ires
    0.81
    IRE
    0.74
    q
    0.69
     ["
    0.67
    Str
    0.67
    zyme
    0.67
    SB
    0.67
    の�
    0.65
    Activations Density 0.141%

    No Known Activations