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

    Neuronpedia

    INDEX
    Explanations

    the word "most"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "most" and its variations in the context of general statements or common occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onto
    -0.71
    ourge
    -0.68
    orest
    -0.61
    ores
    -0.61
    itiz
    -0.60
     outweigh
    -0.60
    illard
    -0.60
     itch
    -0.59
    heed
    -0.58
     someday
    -0.58
    POSITIVE LOGITS
     case
    1.02
     cases
    0.96
     nutshell
    0.95
     context
    0.94
     meantime
    0.91
     vein
    0.87
     guise
    0.86
     absence
    0.80
     Cases
    0.77
     stead
    0.75
    Act Density 0.194%

    No Known Activations