© 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. 2294
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or distinctions between two entities

    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
    maxwell
    -0.99
    staking
    -0.98
    ertodd
    -0.94
    enhagen
    -0.88
    imentary
    -0.82
    hoe
    -0.77
    icum
    -0.76
    actionDate
    -0.72
    ��
    -0.71
    potion
    -0.70
    POSITIVE LOGITS
     occasions
    0.83
     cultures
    0.82
     societies
    0.82
     countries
    0.80
     civilizations
    0.80
     corners
    0.79
     situations
    0.79
     entities
    0.78
     nations
    0.78
     programs
    0.77
    Activations Density 0.040%

    No Known Activations