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

    Neuronpedia

    INDEX
    Explanations

    phrases motivating or encouraging action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneously
    -0.79
    nel
    -0.74
    APD
    -0.72
    grounds
    -0.71
    anism
    -0.71
    thumbnails
    -0.70
     matters
    -0.70
    Autom
    -0.69
    Types
    -0.67
    agu
    -0.67
    POSITIVE LOGITS
     bunch
    1.14
     lot
    1.10
     glimpse
    1.07
     couple
    1.07
     few
    1.06
     hearty
    1.05
     nice
    1.04
     bit
    1.02
     chance
    1.01
     peek
    0.98
    Act Density 0.256%

    No Known Activations