© 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. 2692
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce conditional statements

    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
    tenance
    -0.66
     occasional
    -0.61
     +++
    -0.61
    git
    -0.58
    wcsstore
    -0.58
    liction
    -0.58
    usalem
    -0.57
    single
    -0.57
    mis
    -0.57
    onge
    -0.57
    POSITIVE LOGITS
    efined
    0.64
     Roose
    0.62
     Indones
    0.60
     Jol
    0.58
     Hou
    0.58
     Blackburn
    0.58
     Blaz
    0.57
    エル
    0.57
    fram
    0.57
    aeper
    0.57
    Activations Density 0.016%

    No Known Activations