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

    Neuronpedia

    INDEX
    Explanations

    words related to concerns or criticisms of various issues or situations

    oai_token-act-pair · gpt-3.5-turbo

    topics related to concerns and criticisms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hereby
    -0.81
    fuck
    -0.76
     :=
    -0.73
    eous
    -0.71
    ffer
    -0.70
    orp
    -0.70
    ãĤ¦ãĤ¹
    -0.70
    emonium
    -0.69
     WITHOUT
    -0.69
     Appears
    -0.68
    POSITIVE LOGITS
     pharmaceutical
    0.78
     fossil
    0.77
     Hurricane
    0.74
     tourism
    0.73
     smartphones
    0.73
     migrant
    0.71
     renewables
    0.70
     globalization
    0.70
     opioids
    0.69
     homegrown
    0.69
    Act Density 0.459%

    No Known Activations