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

    Neuronpedia

    INDEX
    Explanations

    the phrase "any one."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of numerical quantities or references to singular entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Werner
    -0.67
    bda
    -0.61
     suites
    -0.60
    earchers
    -0.60
    lling
    -0.58
    ounds
    -0.57
     salaries
    -0.57
     subtitles
    -0.57
     heritage
    -0.57
     trenches
    -0.56
    POSITIVE LOGITS
     imaginable
    1.11
     whatsoever
    1.00
    astical
    0.82
     conceivable
    0.80
     besides
    0.76
    else
    0.74
    wcsstore
    0.72
    âĻ¥
    0.72
     except
    0.69
     else
    0.67
    Act Density 0.125%

    No Known Activations