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

    Neuronpedia

    INDEX
    Explanations

    sentences where someone is making a statement or providing information

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.80
     ILCS
    -0.71
    famous
    -0.70
    Synopsis
    -0.70
    eatured
    -0.68
    Rated
    -0.67
    Woman
    -0.66
    EEE
    -0.65
    én
    -0.65
    illet
    -0.64
    POSITIVE LOGITS
     nonetheless
    1.08
     none
    1.06
     otherwise
    0.96
     nothing
    0.95
     nevertheless
    0.92
     it
    0.92
     neither
    0.91
     there
    0.90
     doubts
    0.84
     caution
    0.83
    Act Density 0.307%

    No Known Activations