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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to starting or initiating activities or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to engagement and recommendations for audiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disbanded
    -0.77
     Sloan
    -0.75
     subcontract
    -0.74
     Sisters
    -0.74
     subordinates
    -0.73
     ministries
    -0.67
     clarified
    -0.67
     merged
    -0.64
     annex
    -0.63
     jointly
    -0.63
    POSITIVE LOGITS
    inge
    0.94
     binge
    0.93
     browsing
    0.89
    ikes
    0.87
    hower
    0.87
     crave
    0.86
     indulge
    0.82
    ophile
    0.82
    itaire
    0.82
     enjoyment
    0.81
    Act Density 1.209%

    No Known Activations