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

    Neuronpedia

    INDEX
    Explanations

    historic terms and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to historical settlements and architectural styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hurting
    -0.72
    Leaks
    -0.71
     itching
    -0.71
    Yep
    -0.70
     Saying
    -0.70
     whispering
    -0.68
     clicking
    -0.68
     Fixes
    -0.68
     whining
    -0.67
     Fix
    -0.64
    POSITIVE LOGITS
     consisted
    1.95
     differed
    1.55
     originated
    1.51
     existed
    1.48
     resembled
    1.46
     belonged
    1.46
     consists
    1.46
     underwent
    1.44
     resided
    1.43
     lasted
    1.42
    Act Density 0.520%

    No Known Activations