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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology companies and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    effic
    -0.83
     administr
    -0.82
    adequ
    -0.78
     attrition
    -0.76
     consolidate
    -0.76
     weakening
    -0.74
     weaken
    -0.73
     dilig
    -0.72
     consolidated
    -0.71
     jurisd
    -0.70
    POSITIVE LOGITS
     Beyon
    1.10
     selfie
    1.08
     mascot
    1.07
     selfies
    1.05
     Gaga
    0.99
     adorable
    0.97
     Kanye
    0.96
     Doodle
    0.96
     Rih
    0.94
     Madonna
    0.94
    Act Density 2.517%

    No Known Activations