© 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. 1676
    Prev
    Next
    INDEX
    Explanations

    conditional statements introduced by "if."

    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
    dding
    -0.79
    merce
    -0.71
    gan
    -0.70
    dozen
    -0.70
    grave
    -0.69
    ���
    -0.66
    ────
    -0.65
    oyer
    -0.65
    Member
    -0.65
    tackle
    -0.65
    POSITIVE LOGITS
     true
    0.80
     indeed
    0.78
     anyone
    0.76
     anybody
    0.75
     ever
    0.72
     anything
    0.66
     recall
    0.63
     pellets
    0.63
     pressed
    0.59
     warranted
    0.57
    Activations Density 0.096%

    No Known Activations