© 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. 969
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate intent or purpose in actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     convol
    -0.76
    mbuds
    -0.68
    ouses
    -0.66
    comings
    -0.66
     Puzz
    -0.65
     expire
    -0.63
     Pengu
    -0.63
     throats
    -0.62
     Gleaming
    -0.60
     polymorph
    -0.60
    POSITIVE LOGITS
    ertation
    0.77
     mainly
    0.69
     Pwr
    0.69
    uci
    0.66
     hay
    0.64
     Tow
    0.64
     primarily
    0.63
    IGHT
    0.61
     squarely
    0.61
     mostly
    0.61
    Activations Density 0.036%

    No Known Activations