© 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. 851
    Prev
    Next
    INDEX
    Explanations

    instances of the word "free" in 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
    BuyableInstoreAndOnline
    -0.85
     Nest
    -0.61
     lun
    -0.60
     Rush
    -0.60
     gigg
    -0.59
     fury
    -0.59
     tacit
    -0.58
     Mend
    -0.58
     trem
    -0.58
     laughs
    -0.57
    POSITIVE LOGITS
    Reviewed
    0.79
    vertisements
    0.77
    */(
    0.77
    rons
    0.71
    �
    0.69
     ($)
    0.68
    NetMessage
    0.67
    ror
    0.67
    resses
    0.65
    ront
    0.64
    Activations Density 1.090%

    No Known Activations