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

    Neuronpedia

    INDEX
    Explanations

    mentions of religious worship services

    oai_token-act-pair · gpt-3.5-turbo

    articles, particularly the definite and indefinite articles 'a' and 'an'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Links
    -0.80
    Sources
    -0.80
    Contents
    -0.76
    reports
    -0.75
    evidence
    -0.73
    aci
    -0.71
    Types
    -0.69
    measures
    -0.67
    letters
    -0.67
    Enjoy
    -0.66
    POSITIVE LOGITS
     bunch
    1.15
     particular
    1.10
     lot
    1.10
    rouse
    1.04
     predetermined
    1.01
    uras
    0.99
     multitude
    0.98
     plethora
    0.97
     certain
    0.96
     whole
    0.94
    Act Density 0.589%

    No Known Activations