© 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. 1607
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" along with references to events or actions in a sequence

    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
    kj
    -0.72
    ails
    -0.72
    ь
    -0.69
     裏�
    -0.68
    peed
    -0.67
    olas
    -0.66
    rency
    -0.66
    veland
    -0.65
     constitu
    -0.64
    conom
    -0.64
    POSITIVE LOGITS
    SPONSORED
    0.73
     dent
    0.62
    val
    0.61
     stop
    0.61
     fruitful
    0.60
    �
    0.58
     Sear
    0.58
    cho
    0.58
     berth
    0.57
    GER
    0.57
    Activations Density 0.048%

    No Known Activations