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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causing controversy or strong reactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with provocation and public outrage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tags
    -0.82
    models
    -0.77
    Rules
    -0.75
    parts
    -0.75
    coins
    -0.74
    arte
    -0.74
    words
    -0.74
    rics
    -0.72
    sheets
    -0.71
    ãĤ¢ãĥ«
    -0.70
    POSITIVE LOGITS
     lot
    1.17
     flurry
    1.07
    rouse
    1.05
     plethora
    1.05
     hefty
    1.04
     barrage
    1.02
     slew
    1.02
     lengthy
    1.00
     resurgence
    0.98
     reversal
    0.97
    Act Density 0.265%

    No Known Activations