© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2233
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ���
    -0.67
     interpre
    -0.66
     borrow
    -0.62
     WATCHED
    -0.62
    lishes
    -0.61
     residues
    -0.58
     dances
    -0.58
     creeps
    -0.58
     cooks
    -0.57
    ministic
    -0.56
    POSITIVE LOGITS
     particular
    1.11
    fact
    0.73
     fact
    0.73
    flame
    0.70
    osc
    0.69
    efficiency
    0.69
    ethnic
    0.67
    format
    0.66
    uria
    0.65
    purpose
    0.65
    Activations Density 0.160%

    No Known Activations