© 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. 909
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the identity or role of individuals

    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
    esson
    -0.82
    aceae
    -0.81
    ordes
    -0.74
    prises
    -0.73
    udos
    -0.72
    rov
    -0.71
    ASY
    -0.66
    OUP
    -0.65
     clich
    -0.65
    andowski
    -0.65
    POSITIVE LOGITS
     rotting
    0.71
    ilk
    0.67
     Sleeping
    0.65
     Nun
    0.65
     resting
    0.63
     deteriorating
    0.63
     pregnant
    0.62
     Jewish
    0.62
     ILCS
    0.61
     tending
    0.61
    Activations Density 0.076%

    No Known Activations