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

    Neuronpedia

    INDEX
    Explanations

    references to evaluating or holding law enforcement accountable for their actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )"
    -0.87
    )",
    -0.79
    )\
    -0.67
    \)
    -0.65
     etc
    -0.65
     beneficial
    -0.60
    )[
    -0.60
     english
    -0.60
     cooper
    -0.59
    oday
    -0.58
    POSITIVE LOGITS
    etheless
    0.80
     downright
    0.80
     inexpl
    0.72
     utterly
    0.71
     unmist
    0.69
     reckoning
    0.67
     lurking
    0.67
     unaccount
    0.67
     goddamn
    0.65
     shockingly
    0.65
    Act Density 1.491%

    No Known Activations