© 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. 875
    Prev
    Next
    INDEX
    Explanations

    terms related to high population density in various environments

    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
    EStream
    -0.82
    erenn
    -0.67
    ========
    -0.66
    rily
    -0.64
    ILD
    -0.64
    abwe
    -0.62
    ilon
    -0.60
    �
    -0.58
    pelled
    -0.57
    orest
    -0.57
    POSITIVE LOGITS
    abal
    0.81
    ev
    0.80
     locker
    0.76
     corridors
    0.75
     jails
    0.71
     rooms
    0.70
     harbor
    0.69
     room
    0.67
     harbour
    0.67
     streets
    0.67
    Activations Density 0.100%

    No Known Activations