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

    Neuronpedia

    INDEX
    Explanations

    phrases related to environmental and financial activities/actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant changes or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.88
    rio
    -0.82
    bart
    -0.70
    iece
    -0.70
    robe
    -0.70
    ety
    -0.69
    jured
    -0.69
    uten
    -0.65
    vale
    -0.65
    dden
    -0.64
    POSITIVE LOGITS
     including
    1.03
    Downloadha
    0.96
     namely
    0.95
     aka
    0.95
     thereby
    0.94
     Flavoring
    0.92
     which
    0.90
    channelAvailability
    0.87
     respectively
    0.87
     etc
    0.86
    Act Density 0.519%

    No Known Activations