Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 388
    Prev
    Next
    INDEX
    Explanations

    the phrase "in order to."

    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
     Discipline
    -0.59
    ages
    -0.59
     Guth
    -0.58
     Ples
    -0.57
    results
    -0.57
     Portug
    -0.55
     Racial
    -0.55
     ende
    -0.54
    eneg
    -0.54
    tu
    -0.53
    POSITIVE LOGITS
    istor
    0.91
    isphere
    0.73
    cosystem
    0.72
    imental
    0.71
    iant
    0.71
     Shed
    0.71
    akura
    0.70
    iox
    0.70
    nery
    0.69
    ascript
    0.68
    Activations Density 0.024%

    No Known Activations