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

    Neuronpedia

    INDEX
    Explanations

    organization or event names punctuated with single quotes

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms related to social or economic challenges and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     citiz
    -0.74
     newsp
    -0.74
    hement
    -0.71
     eleph
    -0.67
     oun
    -0.67
     curves
    -0.66
    =-=-
    -0.64
    culus
    -0.63
    awei
    -0.62
    soDeliveryDate
    -0.61
    POSITIVE LOGITS
    ↵
    0.91
    Meanwhile
    0.68
    Experts
    0.68
     Experts
    0.67
    Authorities
    0.66
     Prosecutors
    0.64
    Merit
    0.64
    ³³³³³³³³³³³³³³³³
    0.62
    ³³³³³³³³
    0.62
    Already
    0.61
    Act Density 0.108%

    No Known Activations