© 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. 2067
    Prev
    Next
    INDEX
    Explanations

    terms associated with divinity and sacredness

    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
    issance
    -0.84
    budget
    -0.78
    soDeliveryDate
    -0.76
    atically
    -0.75
    bars
    -0.75
    ually
    -0.75
    resh
    -0.75
    riber
    -0.74
    atical
    -0.73
    buster
    -0.73
    POSITIVE LOGITS
     unfocusedRange
    0.68
     Second
    0.65
     heights
    0.64
     retribution
    0.62
     collusion
    0.62
     feelings
    0.61
     Being
    0.61
     virginity
    0.60
     paternal
    0.60
     Great
    0.59
    Activations Density 0.101%

    No Known Activations