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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the will or wishes of people or communities

    oai_token-act-pair · gpt-3.5-turbo

    references to victims and public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illon
    -0.79
    wcsstore
    -0.72
    ãĤ´ãĥ³
    -0.72
    quit
    -0.71
    pload
    -0.70
    forward
    -0.70
    ptions
    -0.69
    ="#
    -0.68
    arten
    -0.67
    vl
    -0.67
    POSITIVE LOGITS
     respective
    1.01
     latter
    0.86
     Individuals
    0.83
     individuals
    0.82
     wearer
    0.82
     aforementioned
    0.81
     majority
    0.81
     beh
    0.80
     Editors
    0.80
     deceased
    0.77
    Act Density 0.250%

    No Known Activations