© 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. 3186
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with" and related phrases indicating relationships or connections

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    イト
    -0.71
     perpend
    -0.68
    セ
    -0.66
    ™:
    -0.65
    ipedia
    -0.65
     activates
    -0.64
    agents
    -0.62
    izoph
    -0.62
     arrang
    -0.62
    �
    -0.61
    POSITIVE LOGITS
    dan
    0.73
    lander
    0.69
    illary
    0.63
    kay
    0.63
     Ambrose
    0.62
     Decay
    0.61
     subsequent
    0.61
     Fellow
    0.59
    icka
    0.58
    chan
    0.58
    Activations Density 0.150%

    No Known Activations