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

    Neuronpedia

    INDEX
    Explanations

    phrases related to text formatting and organization

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Found
    -0.70
    eeks
    -0.67
     Founding
    -0.67
    vous
    -0.65
    rance
    -0.65
    ships
    -0.64
    hur
    -0.64
    ds
    -0.64
    orio
    -0.61
    ipeg
    -0.61
    POSITIVE LOGITS
     differently
    1.19
     accordingly
    1.00
    ependent
    0.90
     by
    0.90
     correctly
    0.88
     incorrectly
    0.88
     separately
    0.87
     externally
    0.87
     geographically
    0.86
     appropriately
    0.85
    Act Density 0.199%

    No Known Activations