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

    Neuronpedia

    INDEX
    Explanations

    terms related to causing or provoking intense emotions or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to incitement and provocation, particularly in political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichick
    -0.79
    ©¶æ
    -0.72
    framework
    -0.71
     ellipt
    -0.68
     Tunnel
    -0.65
    neau
    -0.65
    iddler
    -0.65
     Accounting
    -0.64
    ighth
    -0.62
     McCl
    -0.62
    POSITIVE LOGITS
    itement
    0.98
     inciting
    0.95
    xual
    0.89
     sidx
    0.80
    Demand
    0.78
     incite
    0.78
    Spread
    0.77
    ãĥĥ
    0.76
    ãĥŁ
    0.76
     cele
    0.76
    Act Density 0.034%

    No Known Activations