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

    Neuronpedia

    INDEX
    Explanations

    calls to action related to important issues

    oai_token-act-pair · gpt-3.5-turbo

    activist calls to action and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gery
    -0.66
    clair
    -0.63
     Inqu
    -0.58
    olk
    -0.57
    auga
    -0.57
    umn
    -0.56
    nces
    -0.55
    abase
    -0.55
    croft
    -0.55
    angelo
    -0.54
    POSITIVE LOGITS
     FIGHT
    0.67
     Fight
    0.64
    Fight
    0.60
    ãĥ³ãĤ¸
    0.59
    é¾į
    0.58
    éŃĶ
    0.56
     fight
    0.55
    ĪĴ
    0.55
     tracts
    0.54
    urden
    0.52
    Act Density 0.057%

    No Known Activations