© 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. 834
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" to indicate spatial or contextual relationships

    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
    cms
    -0.81
    rupulous
    -0.69
    wash
    -0.63
    own
    -0.63
     sucker
    -0.62
    responsible
    -0.62
     substitute
    -0.61
     mammals
    -0.61
    cially
    -0.60
     stew
    -0.60
    POSITIVE LOGITS
     length
    0.93
     circumference
    0.79
     awhile
    0.72
     diameter
    0.71
     comparison
    0.70
     height
    0.70
     potency
    0.68
     depth
    0.67
     Transparency
    0.67
     brill
    0.66
    Activations Density 0.064%

    No Known Activations