© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 915
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or inability to provide information

    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
    icum
    -0.85
    Repe
    -0.83
     tremend
    -0.81
    regon
    -0.78
    awaru
    -0.77
    uese
    -0.76
    ernel
    -0.74
    retty
    -0.72
    Downloadha
    -0.72
     sclerosis
    -0.72
    POSITIVE LOGITS
     Hayden
    0.67
     [
    0.66
     Coleman
    0.66
     McKay
    0.64
     Birch
    0.64
     Finish
    0.63
    place
    0.61
     Qi
    0.61
     Xuan
    0.61
     Jurassic
    0.60
    Activations Density 0.815%

    No Known Activations