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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or implementing solutions

    oai_token-act-pair · gpt-3.5-turbo

    assertions or statements that indicate a need for action or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     carbohyd
    -0.86
    ascus
    -0.82
    quartered
    -0.81
     mysteriously
    -0.80
    ozyg
    -0.78
     unexplained
    -0.77
    ount
    -0.75
     panc
    -0.74
     unsur
    -0.73
     booked
    -0.73
    POSITIVE LOGITS
     Otherwise
    2.01
     Ideally
    1.63
    Otherwise
    1.46
     Unfortunately
    1.40
     Doing
    1.40
     Hopefully
    1.37
     Especially
    1.29
     Sadly
    1.28
     Fortunately
    1.23
     Specifically
    1.22
    Act Density 0.312%

    No Known Activations