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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public outcry or strong indignation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of public outrage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchin
    -0.78
    ramer
    -0.77
    arnaev
    -0.76
    sembly
    -0.75
     Solitaire
    -0.73
    stood
    -0.71
    essions
    -0.67
    llan
    -0.66
    ccording
    -0.65
    properties
    -0.64
    POSITIVE LOGITS
    ously
    1.18
     indignation
    1.03
    iously
    0.87
     outrage
    0.86
     uproar
    0.85
    ingly
    0.80
    storms
    0.76
    èĥ
    0.75
     outcry
    0.74
    uously
    0.73
    Act Density 0.016%

    No Known Activations