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

    Neuronpedia

    INDEX
    Explanations

    verbs related to decreasing the significance of something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "play"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.82
    Ļ½
    -0.70
     Klux
    -0.68
     Palestin
    -0.67
     millenn
    -0.67
    illard
    -0.66
     overcrowd
    -0.65
    ingen
    -0.63
    icon
    -0.63
    £ı
    -0.62
    POSITIVE LOGITS
    ername
    0.91
    plays
    0.86
    heet
    0.83
    halla
    0.78
    assium
    0.77
     Mellon
    0.76
    dates
    0.75
    hyde
    0.72
    urden
    0.72
    figure
    0.72
    Act Density 0.015%

    No Known Activations