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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 567
    Prev
    Next
    INDEX
    Explanations

    questions related to timing and personal experiences

    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
     Trend
    -0.71
    arenthood
    -0.66
    milo
    -0.64
    Js
    -0.62
     negotiations
    -0.61
    Sit
    -0.59
     Ragnar
    -0.59
     deliberations
    -0.58
    Morning
    -0.57
     Killing
    -0.57
    POSITIVE LOGITS
    ��
    0.90
    oso
    0.82
    pei
    0.72
    yrinth
    0.71
     EVER
    0.70
    stellar
    0.69
    anova
    0.69
    etheless
    0.69
    hidden
    0.66
    onyms
    0.66
    Activations Density 0.165%

    No Known Activations